ISCApad number 98

August 10th, 2006

MESSAGE from :Jean-François Bonastre, Board Member in charge of Student Relations, Grants and Awards.
Dear Colleagues,
I joined the ISCA Board last September. My work concerns mainly the relations between ISCA and the students. For that, I am working together with the ISCA Student Advisory Committee, in order to hear their needs, to help them in organizing both the student web services and student special events. Visit their pages . I am also requesting their advice for all the student related questions, like the grant system evolution.
I am also the “ISCA Grant Manager”, it means that I am dealing with the grant requests. This work is done in collaboration with the ISCA secretary, Emmanuelle, who is in charge of the administrative problems (like money transfers).The Grant system is an important ISCA action, we are receiving an increasing number of requests and the ISCA Board allocated an increasing budget for the grants in 2006. I am trying to manage this budget for a good balance between countries, topics and events. We extend also the grant system, by accepting requests from students and young researchers but also, exceptionally from researchers in special situations like unemployment or coming from low income-level countries. The grant web pages will also change very soon, going from a paper based system to a fully online system. It will help us to reduce the grant acceptance delay.
Finally, my last specific role in the ISCA Board concerns the awards, like the Student Best Paper Award for Internspeech conferences.
I hope to see you in Pittsburgh.
Best,
Jean-François Bonastre

Editorial

Dear Members,
This month, after the presentation by our president in the previous issue (#97), the focus will be on the activity of Jean-Francois Bonastre,ISCA board member in charge of Grants and Awards and Student liaison. His message appears at the top of this issue.
An important and urgent message from our secretariat will draw your attention in section ISCA News and require your personal participation to a survey on critical ISCA activities. Please contribute to our continuous development by answering this questionnaire.
Also you will find below a call for bids for Interspeech 2010.
I remind you of two important and permanent requests:
First, SIG leaders are urged to submit brief activity reports to ISCApad.
Second, if you are aware of new books devoted to speech science and/or technology, please draw my attention to them, so that I can advertise these books in ISCApad.
I wish you refreshing holidays!

Christian Wellekens

TABLE OF CONTENTS

  1. ISCA News
  2. SIG's activities
  3. Courses, internships
  4. Books, databases, softwares
  5. Job openings
  6. Journals
  7. Future Interspeech Conferences
  8. Future ISCA Tutorial and Research Workshops (ITRW)
  9. Forthcoming Events supported (but not organized) by ISCA
  10. Future Speech Science and technology events

ISCA NEWS


IMPORTANT and URGENT message from our secretary
Dear ISCA members,
We are currently conducting an online survey on the activities and services offered by ISCA.
We value your feedback, and we would greatly appreciate it if you took a few moments to respond to some questions. Your answers will help us in our efforts to improve membership services, the ISCA and student websites, and the ISCA conferences and workshops.
You can either find the survey on the isca homepage or click directly here.
We thank you very much for your time.
Best Regards,
David HOUSE & Emmanuelle FOXONET for the ISCA Board
secretariat.

Call for Bids for Interspeech 2010
Organization of INTERSPEECH 2010
CALL FOR PROPOSALS
Individuals or organizations interested in organizing: INTERSPEECH 2010 should submit by 15 December 2006 a brief preliminary proposal, including:
* The name and position of the proposed general chair and other principal organizers.
* The proposed period in September/October 2010 when the conference would be held
* The institution assuming financial responsibility for the conference and any other cooperating institutions
* The city and conference center proposed (with information on that center's capacity)
* Information on transportation and housing for conference participants
* Likely support from local bodies (e.g. governmental) The commercial conference organizer (if any)
* A preliminary budget
Interspeech conferences may be held in any country, although they generally should not occur in the same continent in two consecutive years. (IS2009 will be held in Brighton, UK.) Guidelines for the preparation of the proposal are available on our website. Additional information can be provided by Isabel Trancoso.
Those who plan to put in a bid are asked to inform ISCA of their intentions as soon as possible. They should also consider attending Interspeech 2006 in Pittsburgh to discuss their bids, if possible.
Proposals should be submitted by email to the above address. Candidates fulfilling basic requirements will be asked to submit a detailed proposal by 28 February 2007.

ISCA Archive
ISCA is proud to inform the members that thanks to the continuous efforts of our archivist Professor Wolfgang Hess, all publications of ISCA including all Conference and Workshop Proceedings are now accessible on our website. Abstracts can be accessed by everybody. Members have access to the full papers via a password. We hartily thank Professor Wolfgang Hess for this invaluable contribution.

From ISCA Student activity committee (SAC)

ISCA Speech Labs Listing?
ISCA-SAC is in the process of updating ISCA databases. An important part of this process is to have an extensive list of speech labs and groups from all over the world. Right now, there are 102 labs from 24 countries. Please, check the listing, and enter your group's information at http://www.isca-students.org/new-speech-lab.php if your group is not listed.

Student Panel Discussion during Interspeech 2006: "How to get your dream job? What are they looking for?"
ISCA-SAC (Student Advisory Committee) is organizing a panel discussion on Sunday (at 6:00 p.m.), September 17th, 2006. Panelists will be research group managers and professors from industry and academics, and they will answer students' questions about how to find jobs in industry or academics. Please make the travel arrangements accordingly if you don't want to miss this event. This is a great oppurtunity to learn about what big research companies are looking for during their hiring process. Check ISCA-SAC website later for more information about this event.

ISCA-SAC website's new version launching before Interspeech 2006:
A new version of ISCA-SAC website will be launching right before Interspeech 2006. As you might know, the new website will contain tools to help students to access information in their area easily from a personalized environment. You will see the demo of the website during the conference. Interested students can take a look at the current version of the website, and if they want to volunteer for this effort, send an email to us with your resume.

Do you want to become a board member in ISCA Student Advisory Committee?
ISCA-SAC is looking for new motivated members (PhD students early in their degrees are preferred). There are available positions on ISCA-SAC board. If you want to volunteer for ISCA and contribute to ISCA-SAC efforts (to get an idea please visit our website), get into contact with us by sending email to . There are exciting projects that current board members and volunteering students are working on. Join us!
Murat Akbacak
ISCA-SAC President
PhD Student, University of Colorado at Boulder
Research Intern, University of Texas at Dallas
ISCA student branch

ISCA GRANTS
are available for students and young scientists attending meetings.
For more information: http://www.isca-speech.org/grants

top

SIG's activities


A list of Speech Interest Groups can be found on our web.

top

COURSES, INTERNSHIPS


Call for NATO Advanced Study Institute
International NATO Summer School "E.R.Caianiello" XI Course on
The Fundamentals of Verbal and Non-verbal Communication and the Biometrical Issue
 September 2-12, 2006 Vietri sul Mare Italy
Website for details

Studentships available for 2006/7 at the Department of Computer Science
The University of Sheffield - UK
One-Year MSc in HUMAN LANGUAGE TECHNOLOGY
The Sheffield MSc in Human Language Technology has been carefully tailored to meet the demand for graduates with the highly-specialised multi-disciplinary skills that are required in HLT, both as practitioners in the development of HLT applications and as researchers into the advanced capabilities required for next-generation HLT systems. The course provides a balanced programme of instruction across a range of relevant disciplines including speech technology, natural language processing and dialogue systems.
The programme is taught in a research-led environment. This means that you will study the most advanced theories and techniques in the field, and also have the opportunity to use state- of-the-art software tools. You will also have opportunities to engage in research-level activity through in-depth exploration of chosen topics and through your dissertation.
Graduates from this course are highly valued in industry, commerce and academia. The programme is also an excellent introduction to the substantial research opportunities for doctoral-level study in HLT.
A number of studentships are available, on a competitive basis, to suitably qualified applicants. These awards pay a stipend in addition to the course fees.
See further details of the course
Information on how to apply

Appel a participation: l'Ecole Recherche Multimedia d'Information Techniques & Sciences (ERMITES)
Presqu'ile de Giens - Var (France)/4 au 6 septembre 2006. website
email
ERMITES est organisé avec les soutiens du LSIS, du département d'informatique de l'UFRST USTV, et de l'Association Francophone de la Commmunication Parlée (AFCP).
Objectifs :
La diffusion d'informations audiovisuelles, notamment par le web, est de plus en plus anarchique, ce qui en rend la recherche très hasardeuse. "L'Ecole Recherche Multimedia d'Information: Techniques & Sciences" (ERMITES) regroupe, dans un cadre convivial, une dizaine de spécialistes et une vingtaine de doctorants, postdoc, ingenieurs ou enseignant/chercheurs, qui analyseront les dernières avancées, théoriques et pratiques, des Systèmes Robustes de recherche d'Information Multimodale (SRIM), couplant textes, images, sons ou videos. Le chercheur ou l'inventeur ne doit plus sentir d'antagonisme entre ces différents domaines, mais doit en réaliser une synthèse pour renforcer l'originalité de ses travaux. ERMITES ouvre le vaste champs scientifique nécessaire à l'élaboration de SRIM, et au problème de leur fiabilité. Seront donc traités en particulier les theories de l'information, du signal, des processus aléatoires, de l'apprentissage automatique ; l'analyse de scene computationnelle (audio et video), l'intelligence artificielle, les langages de requêtes pour données XML ; le traitement automatique du langage et de la parole ; sciences cognitives et neurophysiologie de la perception. Plusieurs sessions seront consacrées à des démonstrations de prototypes et de toolbox FREEWARE de qualité (dont certaines construites par les intervenants), notamment :
-apprentissage automatique, modélisation: TORCH, HTK
-traitement de la parole et des images: Sirocco et Spro, Speeral, OCTAVE et librairie image
- traitement langage, entités nommées, XML: PYTHON, UNITEX, GALATEX pour la RI dans des documents semi-structurés.
ERMITES est un lieu privilegie de rencontres qui a pour but de renforcer les liens entre les acteurs du domaine de chaque modalité et théorie traitées. L'Ecole est organisée par sessions de 2 à 3 heures, où chaque spécialiste présente un exposé pédagogique, repris lors de tables rondes avec l'ensemble des participants, où pourront être présentés et discutés les projets de recherche dans lesquels sont engagés les participants.
Intervenants (voir résumés sur le site web )
Organisateurs
Hervé Glotin & Jacques Le Maitre
LSIS / Univ. Sud Toulon Var
BP20132, 83957 La Garde cedex 20
TEl : 04 94 14 20 06 ; 04 94 14 28 24
Fax: 04 94 14 28 97

top

BOOKS, DATABASES, SOFTWARES

Multilingual Speech Processing
Editors: Tanja Schultz & Katrin Kirchhoff ,
Elsevier Academic Press, April 2006
Website

Reconnaissance automatique de la parole: Du signal a l'interpretation
Authors: Jean-Paul Haton
Christophe Cerisara
Dominique Fohr
Yves Laprie
Kamel Smaili
392 Pages
Publisher: Dunod

CFP Special Issue on Multimodal Audiovisual Content Abstraction
International Journal of Image and Video Processing
The accurate management of large volumes of digital multimodal audiovisual content calls for a proper mapping of this content onto representation spaces with a high-level degree of interpretation. This operation referred to as content abstraction may be supervised, unsupervised, automatic, or semiautomatic. Content abstraction here is considered in the large sense and includes (semi-)automatic annotation, content (e.g., keyframe) selection, or summarization. Typical problems are fusion of heterogeneous streams, learning (structured) semantics from low-level features, interrelating document content parts, and extracting salient multimodal content. Tools used in this context arise from signal processing, machine learning, data mining, and knowledge engineering.
Specifically, this special issue will gather high-quality original contributions on all aspects of audiovisual content abstraction. Topics of interest include (but are not limited to):
* “Key” feature extraction/characterization (frames, transitions, shots, story, etc.)
* Summarization of video content
* Similarity measures for video content
* Video content processing for indexing
* Multistream processing/fusion
* Interactive video content characterization
* Mosaicing for content representation
Authors should follow the IJIVP manuscript format described on the website. Prospective authors should submit an electronic copy of their complete manuscripts through the IJIVP manuscript tracking system , according to the following timetable:
Manuscript Due October 1, 2006
Acceptance Notification February 1, 2007
Final Manuscript Due April 1, 2007
Publication Date 2nd Quarter, 2007
Guest Editors:
Stéphane Marchand-Maillet, Viper Group, Computer Vision and Multimedia Laboratory, Department of Computer Science, University of Geneva, CH-1211 Geneva 4, Switzerland
Bernard Mérialdo, Department of Multimedia Communications, Institut Eurécom, 06904 Sophia Antipolis Cedex, France
Marcel Worring, Intelligent Sensory Information Systems, Computer Science Institute, Faculty of Science, University of Amsterdam, 1098 SJ Amsterdam, The Netherlands
Milind R. Naphade, Pervasive Media Management Group, IBM T.J. Watson Research Center, White Plain, NY 10604, USA

top

JOB OPENINGS

We invite all laboratories and industrial companies which have job offers to send them to the ISCApad editor: they will appear in the newsletter and on our website for free. (also have a look at http://www.isca-speech.org/jobs.html as well as http://www.elsnet.org/ Jobs)

Saarland University, Saarbruecken, Germany, 3 doctoral scholarships

Saarland University anticipates the availability of up to three doctoral scholarships within the Partnership International for Research and Education (PIRE)
Meaning Representations in Language Understanding
The partnership for research and education (PIRE), established in 2005, is a collaborative PhD programme between
* Saarland University, Germany
* the Brown Laboratory for Linguistic Information Processing headed by Eugene Charniak
* The Johns Hopkins University Center for Language and Speech Processing (CLSP) headed by Frederick Jelinek
* Charles University (Jan Hajic), Czech Republic.
PIRE is also affiliated with our existing International Graduate College (IGK) co-operation with Edinburgh University.
Each scholarship is funded for two years in the first instance, normally extendable for a third year. Doctoral degrees may be obtained in computational linguistics, phonetics, engineering or informatics, from Saarland University. The official language of the programme is English, and dissertations may be written in English or German.
The nature of the cooperation includes:
* Joint supervision of dissertations by lecturers from Saarbruecken and the US
* A six to twelve months research stay at Brown or Johns Hopkins University
* An intensive research exchange programme between all four participating sites (including, for example, an annual two-week forum attended by college members and lecturers from all four centres)
PhD projects will be in the area of meaning representation for natural language processing and suitable applications (Speech Reconstruction, Machine Translation Systems, ...).
Academic staff in Saarbruecken are William Barry, Matthew Crocker, Martin Kay, Dietrich Klakow, Valia Kordoni, Jonas Kuhn, Manfred Pinkal, Hans Uszkoreit, and Wolfgang Wahlster
In Prague is Jan Hajic is the coordinator
At Brown University Eugene Charniak and Mark Johnson participate.
Academic staff at Johns Hopkins University are Frederick Jelinek, Jason Eisner, Bob Frank, Keith Hall, Sanjeev Khudanpur and Paul Smolensky.
The scholarship currently provides EURO 1468 per month (approximately USD 1835). Additional compensation includes family allowance (where applicable), travel funding, support for carrying out experiments, and an additional monthly allowance for the duration of the stay in the US.
Applicants should hold a strong university degree equivalent to the German Diplom or Magister (e.g. Master's level), in a relevant discipline. Applicants should not be more than 28 years of age. Female scientists and international students are particularly encouraged to apply.
Applications should include:
* a curriculum vitae indicating degrees obtained, disciplines covered (e.g. list of courses or transcript), publications, and other relevant experience
* a sample of written work (e.g. research paper, or dissertation, preferably in English)
* copies of high school and university certificates two references (to be sent directly to the college speaker by the deadline)
* an informal cover letter specifying interests, previous knowledge and activities in any of the relevant research areas. Where possible it should include a brief outline of research interests to be pursued within the scholarship.
Up to three scholarships will be available from October 2006. Your application should be sent to:
PIRE office
Claudia Verburg
Department of Computational Linguistics
Saarland University
P.O. Box 15 11 50
D-66041 Saarbruecken
Germany
by 15. August 2006. Later applications may be considered subject to availability of scholarships.
For additional information please contact
Prof. Dr. Dietrich Klakow
PD Dr. Valia Kordoni or
Prof. Dr. Matthew Crocker
See also:
http://www.coli.uni-saarland.de/projects/igk/
http://www.clsp.jhu.edu/research/pire/
http://www.coli.uni-saarland.de/.

Research positions (PhDs, Postdocs) in spoken language processing at INESC ID, Lisbon Portugal

The Spoken Language Systems Lab (L2F) of INESC ID currently has several open positions for PhD students and postdocs in spoken language processing, covering the following topics:
- audio events detection
- voice morphing
- spontaneous speech recognition
- recognition of different varieties of Portuguese
- use of GRID computing for NLP
Most of these research activities take place in the framework of national projects (e.g. "Rich Transcription of Lectures for E-Learning Applications", "Natural Language Engineering on a Computational GRID") and/or European projects ("Education through Characters with Emotional Intelligence and Role-playing Capabilities that Understand Social Interaction", "Audiovisual Search Engines") or bilateral cooperation programs.
Applicants are expected to have several years experience in the above areas, with good and practical knowledge of C/C++/Java.
Interested candidates should send a letter of motivation until October 1st, along with their detailed CV and names of 3 references by email For more information, please contact Isabel Trancoso at the same address or visit the website.

Positions available at Acapela Group, Mons, Belgium

R&D engineer TTS
R&D engineer ASR
Computational linguist TTS
Details can be found on our website

Position Available: SRI International Speech Technology and Research Laboratory

The Speech Technology and Research (STAR) Laboratory at SRI International seeks a self-motivated, team-oriented researcher in machine translation. Highly qualified postdoctoral fellows may also apply.
The STAR Laboratory is engaged in leading-edge research in speech recognition, automatic spoken language translation, speaker recognition and verification, human-machine interfaces, and other areas of speech/language technology, and offers opportunities for basic research as well as prototyping and collaborative productization. For further details about the SRI STAR Lab please see our Website.
The successful candidate will have the opportunity to work on multiple government-funded research projects and to collaborate with other researchers at SRI and partner institutions. S/he will work on high-performance, deployable machine translation systems for multiple language pairs with varying levels of resources. A PhD with machine translation background is desired. The candidate must have strong engineering capability, with skills in C/C++ and scripting languages in a Unix/Linux environment. Strong oral and written communication skills are expected. Experience in previous NIST MT evaluations and knowledge of speech recognition are highly desirable.
Candidates must be able to work both independently and cooperatively across multiple projects with dynamically forming teams. Characteristics of STAR staff are enthusiasm, self-motivation, initiative, and passion for learning. Please apply via Internet

Open positions at the Adaptive Multimodal Interface Research Lab at University of Trento (Italy)

Areas
Automatic Speech Recognition (PhD Research Fellowship)
Natural Language Processing (PhD Research Fellowship)
Machine Learning (PhD Research Fellowship/Senior Researcher)
HCI/User Interface (Junior Researcher)
Multimodal/Spoken Dialog (Senior Researcher)
The Adaptive Multimodal Interface research lab pursues excellence research in next-generation interfaces for human-machine and human-human communication. The research positions will be funded by the prestigious Marie Curie Excellence grant awarded by the European Commission for cutting edge and interdisciplinary research.
The candidates for PhD research fellowships should have background in speech, natural language processing or machine learning. The successful applicants should have EE or CS degree with strong academic records. The students will be part of an interdisciplinary research team working on speech recognition, language understanding, spoken dialog, machine learning and adaptive user interfaces.
Deadline for application submission is July 11, 2006.
The candidates for the junior/senior researcher positions should have a PhD degree either in computer science, cognitive science or related disciplines. They will have an established international research track record in their field of expertise and leadership skills. Deadline for application submission is November 1, 2006.
The applicants should be fluent in English. The Italian language competence is optional and applicants are encouraged to acquire this skill on the job. The applicants should have good programming skills in most of the following C++/Java/JavaScript/Perl/Python. University of Trento is an equal opportunity employer. Interested applicants should send their CV along with their statement of research interest and three reference letters to: Prof. Ing. Giuseppe Riccardi
The University of Trento is constantly ranked as premiere Italian graduate university institution (see ). DIT Department
-DIT has a strong focus on interdisciplinarity with professors from different faculties of the University (Physical Science, Electrical Engineering, Economics, Social Science, Cognitive Science, Computer Science) with international background.
-DIT aims at exploiting the complementary experiences present in the various research areas in order to develop innovative methods and technologies, applications and advanced services. -English is the official language.

Nuance (Burlington MA)_ #1365 Software Engineer (Burlington MA)

Overview
Nuance Communications, Inc, a worldwide leader in speech and imaging solutions, has an opening for a senior software engineer to maintain and improve acoustic model training and testing toolkits in the Dragon R&D department.
The candidate will join a group of talented speech scientists and research engineers to advance acoustic modeling techniques for Dragon dictation solutions and other Nuance speech recognition products. We are looking for a self-motivated, goal-driven individual who has strong programming and software architecture skills.
Responsibilities
• Maintain and improve acoustic modeling toolkit
o Improve efficiency, flexibility and, when appropriate, architecture of training algorithms
o Improve resource utilization of the toolkit in a large grid computing environment
o Implement new training algorithms in cooperation with speech scientists
o Handle toolkit bug reports and feature requests
o Clean up legacy codes, improve code quality and maintainability
o Perform regression tests and release toolkits
o Improve toolkit documentation
• Improve the software implementation of our research testing framework
• Update acoustic modeling and testing toolkits to work with new versions of speech recognizer
Qualifications
• Bachelor’s or Master’s degree in computer science or electrical engineering
• Strong programming skill using C/C++ and scripting languages Perl/Python in UNIX environment
• Significant experience in creating and maintaining a software toolkit. This includes version control, bug reporting, testing, and releasing code to a user community.
• Ability to work with a large existing code base
• Good software design and architecture skill
• Attention to detail: ability and interest in getting lots of details right on a work task
• Desire and ability to be a team player
? Experience with building acoustic models for speech recognition
? Experience with CVS
? Experience coming up to speed on a large existing code base in a short period of time
? Knowledge of speech recognition algorithms, including model training algorithms
Preference will give to candidates who have experience in maintaining a speech recognition toolkit. Previous experience in computer administration and grid software management is a plus.
Please apply on-line

Sr. Research Scientist at Nuance

Nuance, a worldwide leader in imaging, speech and language solutions, has an opening for a research scientist in speech recognition. The candidate will work on improving recognition performance of speech recognition engine and its main application in Nuance's award-winning dictation products. Dragon NaturallySpeaking® is our market-leading desktop dictation product. The recently released version 8 showed substantial accuracy improvements over previous versions. DragonMT is our new medical transcription server, which brings the benefit of ScanSoft’s dictation technology to the problem of machine assisted medical transcription. We are looking for an individual who wants to solve difficult speech recognition problems, and help get those solutions into our products, so that our customers can work more effectively. Responsibilities
Main responsibilities of the candidate will include:
provide experimental and theoretical analysis of speech recognition problems
formulate new algorithms, create research tools, design and carry out experiments to verify new algorithms
work with other members in the team to improve the performance of our products and add new product features to meet business requirements
work with other team members to deliver acoustic models for products
work with development engineers to insure a high quality implementation of algorithms and models in company products
follow developments in speech recognition to keep our research work state-of-the-art patent new algorithms and write scientific papers when appropriate
Qualifications
Requirements: Ph.D. or Master degree in computer science or electrical engineering good analytical and diagnostic skills
experience with C/C++, scripting using Perl, Python and csh in UNIX environment ability to work with a large existing code base
desire and ability to be a team player
strong desire and demonstrated ability to work on and solve engineering problems.
Preference will give to candidates who have strong speech recognition background. Previous envolvement in DARPA EARS project is a plus. New graduates with good GPA from top universities are encouraged to apply.
The position will be located in our new headquarters in Burlington, MA, which is approximated 15 miles west of Boston. Information about Scansoft and its products. can be found in .
Please apply on-line

Research Engineer - Natural Language Understanding- Nuance

Overview
Nuance, a worldwide leader in imaging, speech and language solutions, has an opening for a research engineer in natural language understanding. Core Technology group in NetASR at Nuance builds the technology behind telephone speech applications. The focus is on call routing and other forms of statistical semantics. We currently automate 7 billion phone calls a year and have been moving fairly aggressively towards more open grammars using a combination of SLM for recognition followed by statistical call routing. This is used both for call center types of applications as well as directory assistance, where there may be millions of destinations with limited training data. The Nuance NLU Group is doing exciting research and product development in C/C++ and we are looking for top talent to join our team.
Responsibilities
The candidate will work in the Network NL group, which develops technology, tools and runtime software to enable our customers to build speech applications using natural language. Some of the current problems include Generating language models for new applications with little application-specific training data. Statistical semantics, e.g. training classifiers for call routing. Robust parsing and other techniques to extract richer semantics than a routing destination.
Responsibilities:
The candidate will work on the full product cycle: speak with professional service engineers or customers to identify NL needs and help with solutions, develop new algorithms, conduct experiments, and write product quality software to deliver these new algorithms in the product release cycle.
Qualifications
Strong software skills. C++ required. Perl/python desirable. Needed both for research code and for product quality, unit-tested code that we ship. Advanced degree in computer science or related field. Experience in natural language processing, especially call routing, language modeling and related areas. Ability to take initiative, but also follow a plan and work well in a group environment. A strong desire to make things “really work” in practice.
Please apply on-line

Principal Engineer - Clinical Language Understanding

Overview
Nuance, a worldwide leader in imaging, speech and language solutions, has an opening for a research engineer in clinical language understanding.
The Clinical Language Understanding group at Nuance is a multi-disciplinary team developing a cutting-edge medical fact extraction engine in Java. Important facts about medications, problems, and procedures are identified in clinical reports, classified, and normalized to standard medical vocabularies.
Responsibilities
The person will be responsible for contributing to the on-going engineering of the Medical Fact Extraction engine. The person will research methods and technologies for improving engine functionality, as well as improving accuracy, performance, and reliability. They will have good software architecture/design skills, to balance API requirements for both research and deployment configurations. They will design, code and test new functionality, and will analyze existing code to extend, optimize and refactor it. The person will also help maintain and enhance systems used for corpus management, document annotation, machine learning algorithm development, and accuracy and performance measurement. They will also work closely with colleagues in Research and in Development.
Qualifications
* Bachelor in computer science or equivalent -- advanced degree preferred.
* Minimum 5 years of experience in software development, preferably in the areas of information extraction and retrieval, knowledge management, document management, or natural language processing.
* Excellent software design, development and diagnostic skills, preferably in Java.
* Excellent scripting and prototyping skills, preferably in Perl.
* Excellent knowledge and understanding of XML, XSLT, and related technologies.
* Significant experience with relational databases.
* Demonstrated ability and desire to learn new technologies rapidly.
* Ability to work well in a multi-disciplinary team.
* Good written and verbal communication skills.
In addition, the applicant must have several of the following:
* Experience in designing and implementing complex commercial applications.
* Experience with computational linguistic research and development, especially as applied to Information Extraction and Retrieval.
* Experience with ontologies and controlled medical vocabularies (e.g. SNOMED).
* Familiarity with clinical documentation standards and medical terminology.
* Experience with applying machine learning approaches
* Experience in conducting computational and/or technical research is a plus.
* Experience developing user interfaces is a plus.
* Experience with Eclipse and Perforce is a plus.
* Experience with Tomcat, Web services, Servlets is a plus.
* Knowledge of Windows and UNIX is a plus.
Please apply on-line

Computational Linguist, Text-to-Speech Synthesis, Boston area

Location: Boston area (Position AXG-1005)
The Computational Linguist will work with the company's technical team to develop and integrate linguistic resources and applications for the company's TTS engine.
Areas of Competence
* Computational Linguistics
* Semantics
* Linguistics
* Speech corpus
* Text corpus
Primary Duties
* Produce and maintain speech corpus, audio data, transcripts and phonetic dictionary, data annotation, and component/model configuration management
* Verify existing corpus
* Developing utilities, lexicons, and other language resources for company's unique TTS
* Adapt text language parsing and analysis software for new TTS needs
Required skills/experience
* Thorough grounding in phonology, phonetics, lexicography, orthography, semantics, morphology, syntax, and other branches of linguistics
* Experience with language parsing and analysis software, such as part-of-speech (POS) and syntactic taggers, semantics, and discourse analysis
* Experience with formant or concatenated based speech synthesis
* Experience working on medium-scale, multi-developer software projects
* Experience with development of speech corpus, transcripts, data annotation, and phonetic dictionary
* Programming experience in C/C++/Matlab/Perl
* Self-motivation and ability to work independently
* Familiarity with concepts and techniques from DSP theory, machine learning and statistical modeling is a plus
Must have a Master/PhD. in Engineering, Computer Science or Linguistics with development or research experience in speech synthesis/recognition/technology.
Direct your confidential response to:
Arnold L. Garlick III
President
Pacific Search Consultants
(949) 366-9000 Ext. 2#
Please refer to Position AXG-1005
Website

Doctoral (PhD) Positions in the field of Content-based Multimedia Information Retrieval and Management Department of Computer Science - Faculty of Sciences - University of Geneva - Switzerland

Context:
The Viper group , part of the Computer Vision and Multimedia Laboratory , has a long research experience in Content-based Multimedia Information Retrieval (image, video, text, ...). Its activities have led amongst other results to the development of interactive demo systems for content-based video ( Vicode ) and image ( GIFT) retrieval and multimedia management. We wish to continue these activities.
Description of posts:
Several doctoral positions are open in relation with international and national project funds awarded on the basis of our research activities in the broad field of content-based multimedia information search, retrieval and management. The research performed will form direct contributions in our current and upcoming projects, including ViCode and the Collection Guide (see our main website for details).
The successful applicants should show knowledge and interest in one or many of the following domains:
* Data mining, statistical data analysis
* Statistical learning
* Signal, image, audio processing
* Knowledge engineering
* Indexing, Databases
* Operation research
Starting date: No later than September 2006.
Salary: 48'000CHF per annum (1st year)
Supervision: Dr. S. Marchand-Maillet and Dr. E. Bruno
Application: Applications by email are welcome to:
Dr. Eric Bruno
Computer Vision and Multimedia Laboratory
Department of Computer Science, University of Geneva
24, rue du General Dufour, CH-1211 Geneva 4
SWITZERLAND
e-mail. This announce (with more info).

top

JOURNALS

Papers accepted for FUTURE PUBLICATION in Speech Communication

Full text available on http://www.sciencedirect.com/ for Speech Communication subscribers and subscribing institutions. Click on Publications, then on Speech Communication and on Articles in press. The list of papers in press is displayed and a .pdf file for each paper is available.

Sacha Krstulovic, Frédéric Bimbot, Olivier Boëffard, Delphine Charlet, Dominique Fohr and Odile Mella, Optimizing the coverage of a speech database through a selection of representative speaker recordings, Speech Communication, In Press, Uncorrected Proof, , Available online 28 July 2006, . (Website) Keywords: Speech database; Cost minimization; Speaker selection; Speaker clustering; Optimal coverage; Multi-models; Speech and speaker recognition; Speech synthesis

Wen Jin and Michael S. Scordilis, Speech enhancement by residual domain constrained optimization, Speech Communication, In Press, Uncorrected Proof, , Available online 28 July 2006, . (Website) Keywords: Speech enhancement; Linear prediction; Constrained optimization

Marcos Faundez-Zanuy, Martin Hagmüller and Gernot Kubin, Speaker verification security improvement by means of speech watermarking, Speech Communication, In Press, Uncorrected Proof, , Available online 25 July 2006, . (Website) Keywords: Biometric; Speech watermarking; Speaker verification

Geng-xin Ning, Shu-hung Leung, Kam-keung Chu and Gang Wei, A dynamic parameter compensation method for noisy speech recognition, Speech Communication, In Press, Uncorrected Proof, , Available online 21 July 2006, . (Website) Keywords: Noisy speech recognition; Model compensation; Dynamic parameter combination

Zekeriya Tufekci, John N. Gowdy, Sabri Gurbuz and Eric Patterson, Applied mel-frequency discrete wavelet coefficients and parallel model compensation for noise-robust speech recognition, Speech Communication, In Press, Uncorrected Proof, , Available online 21 July 2006, . (Website) Keywords: Noise robust ASR; Wavelet; Local feature; Feature weighting

Rupal Patel and Maria I. Grigos, Acoustic characterization of the question-statement contrast in 4, 7 and 11 year-old children, Speech Communication, In Press, Uncorrected Proof, , Available online 21 July 2006, . (Website) Keywords: Prosody; Children; Acoustics; Speech; Development; Acquisition; Questions; Statements; Intonation

Kentaro Ishizuka and Tomohiro Nakatani, A feature extraction method using subband based periodicity and aperiodicity decomposition with noise robust frontend processing for automatic speech recognition, Speech Communication, In Press, Uncorrected Proof, , Available online 21 July 2006, . (Website) Keywords: Speech feature; Noise robust frontend; Subband; Periodicity; Aperiodicity

Tran Huy Dat, Kazuya Takeda and Fumitada Itakura, On-line Gaussian mixture modeling in the log-power domain for signal-to-noise ratio estimation and speech enhancement, Speech Communication, In Press, Uncorrected Proof, , Available online 21 July 2006, . (Website) Keywords: Gaussian mixture modeling; Segmental SNR; Log-normal distributions; Cumulative distribution function equalization; Speech enhancement

Mohammed Bahoura and Jean Rouat, Wavelet speech enhancement based on time-scale adaptation, Speech Communication, In Press, Uncorrected Proof, , Available online 17 July 2006, . (Website) Keywords: Speech enhancement; Wavelet transform; Teager energy operator; Speech recognition; Adaptive thresholds

S.R. Mahadeva Prasanna, Cheedella S. Gupta and B. Yegnanarayana, Extraction of speaker-specific excitation information from linear prediction residual of speech, Speech Communication, In Press, Corrected Proof, , Available online 17 July 2006, . (Website) Keywords: Speaker recognition; Excitation information; LP residual; AANN model; Vocal tract information

Özgül Salor and Mübeccel Demirekler, Dynamic programming approach to voice transformation, Speech Communication, In Press, Corrected Proof, , Available online 17 July 2006, . (Website) Keywords: Voice transformation; Speaker transformation; Codebook; Line spectral frequencies; Dynamic programming

Jonathan Darch, Ben Milner and Saeed Vaseghi, MAP prediction of formant frequencies and voicing class from MFCC vectors in noise, Speech Communication, In Press, Uncorrected Proof, , Available online 7 July 2006, . (Website) Keywords: Formant prediction; Formant estimation; MAP prediction; GMM; HMM; DSR

Jonathan Darch, Ben Milner and Saeed Vaseghi, MAP prediction of formant frequencies and voicing class from MFCC vectors in noise, Speech Communication, In Press, Corrected Proof, , Available online 7 July 2006, . (Website) Keywords: Formant prediction; Formant estimation; MAP prediction; GMM; HMM; DSR

Javier Latorre, Koji Iwano and Sadaoki Furui, New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer, Speech Communication, In Press, Corrected Proof, , Available online 23 June 2006, . (Website) Keywords: Multilingual; Polyglot synthesis; Voice adaptation; Cross-language synthesis; Phone mapping

Frederik Stouten, Jacques Duchateau, Jean-Pierre Martens and Patrick Wambacq, Coping with disfluencies in spontaneous speech recognition: Acoustic detection and linguistic context manipulation, Speech Communication, In Press, Corrected Proof, , Available online 26 May 2006, . (Website) Keywords: Disfluency handling; Spontaneous speech recognition; Disfluency detection

Valentin Ion and Reinhold Haeb-Umbach, Uncertainty decoding for distributed speech recognition over error-prone networks, Speech Communication, In Press, Corrected Proof, , Available online 17 May 2006, . (Website) Keywords: Distributed speech recognition; Channel error robustness; Soft features; Uncertainty decoding

Esfandiar Zavarehei, Saeed Vaseghi and Qin Yan, Inter-frame modeling of DFT trajectories of speech and noise for speech enhancement using Kalman filters, Speech Communication, In Press, Corrected Proof, , Available online 25 April 2006, . (Website) Keywords: Speech enhancement; Kalman filter; AR modeling of DFT; DFT distributions

Antonio Cardenal-López, Carmen García-Mateo and Laura Docío-Fernández, Weighted Viterbi decoding strategies for distributed speech recognition over IP networks, , Speech Communication, In Press, Corrected Proof, , Available online 28 February 2006, . (Website) Keywords: Distributed speech recognition; Weighted Viterbi decoding; Missing data

Veronique Stouten, Hugo Van hamme and Patrick Wambacq, Model-based feature enhancement with uncertainty decoding for noise robust ASR, Speech Communication, In Press, Corrected Proof, , Available online 3 February 2006, . (Website) Keywords: Noise robust speech recognition; Model-based feature enhancement; Additive noise; Convolutional noise; Uncertainty decoding

top

FUTURE CONFERENCES

Publication policy: Hereunder, you will find very short announcements of future events. The full call for participation can be accessed on the conference websites
See also our Web pages (http://www.isca-speech.org/) on conferences and workshops.

FUTURE INTERSPEECH CONFERENCES

INTERSPEECH 2006-ICSLP
INTERSPEECH 2006 - ICSLP, the Ninth International Conference on Spoken Language Processing dedicated to the interdisciplinary study of speech science and language technology, will be held in Pittsburgh, Pennsylvania, September 17-21, 2006, under the sponsorship of the International Speech Communication Association (ISCA).
The INTERSPEECH meetings are considered to be the top international conference in speech and language technology, with more than 1000 attendees from universities, industry, and government agencies. They are unique in that they bring together faculty and students from universities with researchers and developers from government and industry to discuss the latest research advances, technological innovations, and products. The conference offers the prospect of meeting the future leaders of our field, exchanging ideas, and exploring opportunities for collaboration, employment, and sales through keynote talks, tutorials, technical sessions, exhibits, and poster sessions. In recent years the INTERSPEECH meetings have taken place in a number of exciting venues including most recently Lisbon, Jeju Island (Korea), Geneva, Denver, Aalborg (Denmark), and Beijing.
ISCA, together with the INTERSPEECH 2006 - ICSLP organizing committee, would like to encourage submission of papers for the upcoming conference in the following
TOPICS of INTEREST
Linguistics, Phonetics, and Phonology
Prosody
Discourse and Dialog
Speech Production
Speech Perception
Physiology and Pathology
Paralinguistic and Nonlinguistic Information (e.g. Emotional Speech)
Signal Analysis and Processing
Speech Coding and Transmission
Spoken Language Generation and Synthesis
Speech Recognition and Understanding
Spoken Dialog Systems
Single-channel and Multi-channel Speech Enhancement
Language Modeling
Language and Dialect Identification
Speaker Characterization and Recognition
Acoustic Signal Segmentation and Classification
Spoken Language Acquisition, Development and Learning
Multi-Modal Processing
Multi-Lingual Processing
Spoken Language Information Retrieval
Spoken Language Translation
Resources and Annotation
Assessment and Standards
Education
Spoken Language Processing for the Challenged and Aged
Other Applications
Other Relevant Topics
SPECIAL SESSIONS
In addition to the regular sessions, a series of special sessions has been planned for the meeting. Potential authors are invited to submit papers for special sessions as well as for regular sessions, and all papers in special sessions will undergo the same review process as papers in regular sessions. Confirmed special sessions and their organizers include:
* The Speech Separation Challenge, Martin Cooke (Sheffield) and Te-Won Lee (UCSD)
* Speech Summarization, Jean Carletta (Edinburgh) and Julia Hirschberg (Columbia)
* Articulatory Modeling, Eric Bateson (University of British Columbia)
* Visual Intonation, Marc Swerts (Tilburg)
* Spoken Dialog Technology R&D, Roberto Pieraccini (Tell-Eureka)
* The Prosody of Turn-Taking and Dialog Acts, Nigel Ward (UTEP) and Elizabeth Shriberg (SRI and ICSI)
* Speech and Language in Education, Patti Price (pprice.com) and Abeer Alwan (UCLA)
* From Ideas to Companies, Janet Baker (formerly of Dragon Systems)
IMPORTANT DATES
Notification of paper status: June 9, 2006
Early registration deadline: June 23, 2006
Tutorial Day: September 17, 2006
Main Conference: September 18-21, 2006
Further information via Website or send email
Organizer
Professor Richard M. Stern (General Chair)
Carnegie Mellon University
Electrical Engineering and Computer Science
5000 Forbes Avenue
Pittsburgh, PA 15213-3890
Fax: +1 412 268-3890
Email

INTERSPEECH 2007-EUROSPEECH
August 27-31,2007,Antwerp, Belgium
Chair: Dirk van Compernolle, K.U.Leuven and Lou Boves, K.U.Nijmegen
Website
Important dates
Proposals for special sessions: November 1, 2006
Proposals for tutorials: January 8, 2007
Four-page paper deadline: March 23, 2007
Notification of paper acceptance: May 25, 2007
Early registration deadline: June 22, 2007
Tutorial Day: August 27, 2007
Main conference: August 28-31, 2007

INTERSPEECH 2008-ICSLP
September 22-26, 2008, Brisbane, Queensland, Australia
Chairman: Denis Burnham, MARCS, University of West Sydney.

INTERSPEECH 2009-EUROSPEECH
Brighton, UK,
Chairman: Prof. Roger Moore, University of Sheffield.

top

FUTURE ISCA TUTORIAL AND RESEARCH WORKSHOP (ITRW)

ITRW on Experimental Linguistics

28-30 August 2006, Athens Greece
CALL FOR PAPERS
AIMS
The general aims of the Workshop are to bring together researchers of linguistics and related disciplines in a unified context as well as to discuss the development of experimental methodologies in linguistic research with reference to linguistic theory, linguistic models and language applications.
SUBJECTS AND RELATED DISCIPLINES
1. Theory of language
2. Cognitive linguistics
3. Neurolinguistics
4. Speech production
5. Speech acoustics
6. Phonology
7. Morphology
8. Syntax
9. Prosody
10. Speech perception
11. Psycholinguistics
12. Pragmatics
13. Semantics
14. Discourse linguistics
15. Computational linguistics
16. Language technology
MAJOR TOPICS
I. Lexicon
II. Sentence
III. Discourse
IMPORTANT DATES
1 February 2006, deadline of abstract submission
1 March 2006, notification of acceptance
1 April 2006, registration
1 May 2006, camera ready paper submission
28-30 August 2006, Workshop
CHAIR
Antonis Botinis, University of Athens, Greece
Marios Fourakis, University of Wisconsin-Madison, USA
Barbara Gawronska, University of Skövde, Sweden
ORGANIZING COMMITTEE
Aikaterini Bakakou-Orphanou, University of Athens
Antonis Botinis, University of Athens
Christoforos Charalambakis, University of Athens
SECRETARIAT
ISCA Workshop on Experimental Linguistics
Department of Linguistics
University of Athens
GR-15784, Athens GREECE
Tel.: +302107277668
Fax: +302107277029
e-mail
Workshop site address

2nd ITRW on PERCEPTUAL QUALITY OF SYSTEMS

Berlin, Germany, 4 - 6 September 2006
WORKSHOP AIMS
The quality of systems which address human perception is difficult to describe. Since quality is not an inherent property of a system, users have to decide on what is good or bad in a specific situation. An engineering approach to quality includes the consideration of how a system is perceived by its users, and how the needs and expectations of the users develop. Thus, quality assessment and prediction have to take the relevant human perception and judgement factors into account. Although significant progress has been made in several areas affecting quality within the last two decades, there is still no consensus on the definition of quality and its contributing components, as well as on assessment, evaluation and prediction methods.
Perceptual quality is attributed to all systems and services which involve human perception. Telecommunication services directly provoke such perceptions: Speech communication services (telephone, Voice over IP), speech technology (synthesis, spoken dialogue systems), as well as multimodal services and interfaces (teleconference, multimedia on demand, mobile phones, PDAs). However, the situation is similar for the perception of other products, like machines, domestic devices, or cars. An integrated view on system quality makes use of knowledge gained in different disciplines and may therefore help to find general underlying principles. This will assist the increase of usability and perceived quality of systems and services, and finally yield better acceptance.
The workshop is intended to provide an interdisciplinary exchange of ideas between both academic and industrial researchers working on different aspects of perceptual quality of systems. Papers are invited which refer to methodological aspects of quality and usability assessment and evaluation, the underlying perception and judgment processes, as well as to particular technologies, systems or services. Perception-based as well as instrumental approaches will complement each other in giving a broader picture of perceptual quality. It is expected that this will help technology providers to develop successful, high-quality systems and services.
WORKSHOP TOPICS
The following non-exhaustive list gives examples of topics which are relevant for the workshop, and for which papers are invited:
- Methodologies and Methods of Quality Assessment and Evaluation
- Metrology: Test Design and Scaling
- Quality of Speech and Music
- Quality of Multimodal Perception
- Perceptual Quality vs. Usability
- Semio-Acoustics and -Perception
- Quality and Usability of Speech Technology Devices
- Telecommunication Systems and Services
- Multi-Modal User Interfaces
- Virtual Reality
- Product-Sound Quality
IMPORTANT DATES
April 15, 2006 (updated): Abstract submission (approx. 800 words)
May 15, 2006: Notification of acceptance
June 15, 2006: Submission of the camera-ready paper (max. 6 pages)
September 4-6, 2006: Workshop
WORKSHOP VENUE
The workshop will take place in the "Harnack-Haus", a villa-like conference center located in the quiet western part of Berlin, near the Free University. As long as space permits, all participants will be accommodated in this center. Accommodation and meals are included in the workshop fees. The center is run by the Max-Planck-Gesellschaft and can easily be reached from all three airports of Berlin (Tegel/TXL, Schönefeld/SXF and Tempelhof/THF). Details on the venue, accommodation and transportation will be announced soon.
PROCEEDINGS
CD workshop proceedings will be available upon registration at the conference venue and subsequently on the workshop web site.
LANGUAGE
The official language of the workshop will be English.
LOCAL WORKSHOP ORGANIZATION
Ute Jekosch (IAS, Technical University of Dresden)
Sebastian Möller (Deutsche Telekom Labs, Technical University of Berlin)
Alexander Raake (Deutsche Telekom Labs, Technical University of Berlin)
CONTACT INFORMATION
Sebastian Möller, Deutsche Telekom Labs, Ernst-Reuter-Platz 7,
D-10587 Berlin, Germany
phone +49 30 8353 58465, fax +49 30 8353 58409
Website

ITRW on Statistical and Perceptual Audition ( 2006)

A satellite workshop of INTERSPEECH 2006 -ICSLP
September 16, 2006, Pittsburgh, PA, USA
Website
This will be a one-day workshop with a limited number of oral presentations, chosen for breadth and provocation, and an informal atmosphere to promote discussion. We hope that the participants in the workshop will be exposed to a broader perspective, and that this will help foster new research and interesting variants on current approaches.
Topics
Generalized audio analysis
Speech analysis
Music analysis
Audio classification
Scene analysis
Signal separation
Speech recognition
Multi-channel analysis
In all cases, preference will be given to papers that clearly involve both perceptually-defined or perceptually-related problems, and statistical or machine-learning based solutions.
Important dates
Submission of a 4-6 pages long paper deadline (double column) April 21 2006
Notification of acceptance June 9, 2006

NOLISP'07: Non linear Speech Processing

May 22-25, 2007 , Paris, France

6th ISCA Speech Synthesis Research Workshop (SSW-6)

Bonn (Germany), August 22-24, 2007
A satellite of INTERSPEECH 2007 (Antwerp)in collaboration with SynSIG
Details will be posted by early 2007
Contact
Prof. Wolfgang Hess

ITRW on Robustness

November 2007, Santiago, Chile

top

FORTHCOMING EVENTS SUPPORTED (but not organized) by ISCA

IV Jornadas en Tecnologia del Habla

Zaragoza, Spain
November 8-10, 2006
Website

Call for papers-International Workshop on Spoken Language Translation (IWSLT 2006)

Evaluation campaign for language translation
Palulu Plaza Kyoto (right in front of Kyoto Station) (Japan)
November 30-December 1 2006
Website
Spoken language translation technologies attempt to cross the language barriers between people having different native languages who each want to engage in conversation by using their mother-tongue. Spoken language translation has to deal with problems of automatic speech recognition (ASR) and machine translation (MT).
One of the prominent research activities in spoken language translation is the work being conducted by the Consortium for Speech Translation Advanced Research (C-STAR III), which is an international partnership of research laboratories engaged in automatic translation of spoken language. Current members include ATR (Japan), CAS (China), CLIPS (France), CMU (USA), ETRI (Korea), ITC-irst (Italy), and UKA (Germany).
A multilingual speech corpus comprised of tourism-related sentences (BTEC*) has been created by the C-STAR members and parts of this corpus were already used for previous IWSLT workshops focusing on the evaluation of MT results using text input () and the translation of ASR output (word lattice, NBEST list) using read speech as input (). The full BTEC* corpus consists of 160K of sentence-aligned text data and parts of the corpus will be provided to the participants for training purposes.
In this workshop, we focus on the translation of spontaneous speech which includes ill-formed utterances due to grammatical incorrectness, incomplete sentences, and redundant expressions. The impact of spontaneity aspects on the ASR and MT systems performance as well as the robustness of state-of- the-art MT engines towards speech recognition errors will be investigated in detail.
Two types of submissions are invited:
1) participants in the evaluation campaign of spoken language translation technologies,
2) technical papers on related issues.
Evaluation campaign (see details on our website)
Each participant in the evaluation campaign is requested to submit a paper describing the utilized ASR and MT systems and to report results using the provided test data.
Technical Paper Session
The workshop also invites technical papers related to spoken language translation. Possible topics include, but are not limited to:
+ Spontaneous speech translation
+ Domain and language portability
+ MT using comparable and non-parallel corpora
+ Phrase alignment algorithms
+ MT decoding algorithms
+ MT evaluation measures
Important Dates
+ Evaluation Campaign
May 12, 2006 -- Training Corpus Release
August 1, 2006 -- Test Corpus Release [00:01 JST]
August 3, 2006 -- Result Submission Due [23:59 JST]
September 15, 2006 -- Result Feedback to Participants 2006
September 29, 2006 -- Paper Submission Due
October 14, 2006 -- Notification of Acceptance
October 27, 2006 -- Camera-ready Submission Due
- system registrations will be accepted until release of test corpus
- late result submissions will be treated as unofficial result submissions
+ Technical Papers
July 21, 2006 -- Paper Submission Due [23:59 JST]
September 29, 2006 -- Notification of Acceptance
October 27, 2006 -- Camera-ready Submission Due
Contact
Michael Paul
ATR Spoken Language Communication Research Laboratories
2-2-2 Hikaridai, Keihanna Science City, Kyoto 619-0288 Japan

Call for papers International Symposium on Chinese Spoken Language Processing (ISCSLP'2006)

Singapore Dec. 13-16, 2006
Conference website
Topics
ISCSLP'06 will feature world-renowned plenary speakers, tutorials, exhibits, and a number of lecture and poster sessions on the following topics:
* Speech Production and Perception
* Phonetics and Phonology
* Speech Analysis
* Speech Coding
* Speech Enhancement
* Speech Recognition
* Speech Synthesis
* Language Modeling and Spoken Language Understanding
* Spoken Dialog Systems
* Spoken Language Translation
* Speaker and Language Recognition
* Indexing, Retrieval and Authoring of Speech Signals
* Multi-Modal Interface including Spoken Language Processing
* Spoken Language Resources and Technology Evaluation
* Applications of Spoken Language Processing Technology
* Others
The official language of ISCSLP is English. The regular papers will be published as a volume in the Springer LNAI series, and the poster papers will be published in a companion volume. Authors are invited to submit original, unpublished work on all the aspects of Chinese spoken language processing.
The conference will also organize four special sessions:
* Special Session on Rich Information Annotation and Spoken Language Processing
* Special Session on Robust Techniques for Organizing and Retrieving Spoken Documents
* Special Session on Speaker Recognition
* Special Panel Session on Multilingual Corpus Development
Schedule
* Full paper submission by Jun. 15, 2006
* Notification of acceptance by Jul. 25, 2006
* Camera ready papers by Aug. 15, 2006
* Early registration by Nov. 1, 2006
Please visit the conference website for more details.

ISCSLP 2006-Special session on speaker recognition

Singapore, Dec 13-16, 2006
Website
Chair:
Dr Thomas Fang Zheng, Tsinghua Univ., Beijing.
Speaker recognition (or voiceprint recognition, VPR) is one of the most important branches in speech processing. Its applications become wider and wider in various fields, such as public security, anti-terrorism, justice, telephony banking, personal services, and so on. However, there are still many fundamental and theoretical problems to solve, such as issues of background noises, cross-channel, multiple-speakers, and short speech segment for training and testing.
The purpose of this special session is to invite researchers in this field to present their state-of-art technical achievements. Papers are invited to cover, but not limited to, the following topics:
* Text-dependent and text-independent speaker identification
* Text-dependent and text-independent speaker verification
* Speaker detection
* Speaker segmentation
* Speaker tracking
* Speaker recognition systems and application
* Resource creation for speaker recognition
This special session also provides a platform for developers in this field to evaluate their speaker recognition systems using the same database provided by this special session. Evaluation of speaker recognition systems will cover the following tasks:
* Text-independent speaker identification
* Text-dependent and text-independent speaker verification
* Text-independent cross-channel speaker identification
* Text-dependent and text-independent cross-channel speaker verification
Final details on these tasks (including evaluation criteria) will be made available in due course. The development and testing data will be provided by the Chinese Corpus Consortium (CCC). The data sets will be extracted from two CCC databases, which are CCC-VPR3C2005 and CCC-VPR2C2005-1000. Participants are required to submit a full paper to the conference describing their algorithms, systems and results.
Schedule for this special session
* Feb. 01, 2006: On-line registration open, CLOSED on May 1st, 2006
* May. 01, 2006: Development data made available to participants
* May. 21, 2006 (revised): Test data made available to participants
* Jun. 7, 2006 (revised):Test results due at CCC
* Jun. 10, 2006: Results released to participants
* Jun. 15, 2006: Papers due (using ISCSLP standard format)
* Jul. 25, 2006: The full set of the two databases made available to the participants of this special session upon request
* Dec. 16, 2006: Conference presentation
This special session is organized by the CCC .
Please address your enquiries to Dr. Thomas Fang Zheng.
Download the Speaker Recognition Evaluation Registration Form

top

FUTURE SPEECH SCIENCE AND TECHNOLOGY EVENTS


2006 IEEE International Workshop on Machine Learning for Signal Processing

(Formerly the IEEE Workshop on Neural Networks for Signal Processing)
September 6 - 8, 2006, Maynooth, Ireland
MLSP'2006 webpage
The sixteenth in a series of IEEE workshops on Machine Learning for Signal Processing (MLSP) will be held in Maynooth, Ireland, September 6-8, 2006. Maynooth is located 15 miles west of Dublin in Co. Kildare, Ireland?s equestrian and golfing heartland (and home to the 2006 Ryder Cup). It is a pleasant 18th century planned town, best known for its seminary, St. Patrick's College, where Catholic Priests have been trained since 1795. Co.Kildare.
The workshop, formally known as Neural Networks for Signal Processing (NNSP), is sponsored by the IEEE Signal Processing society (SPS) and organized by the MLSP technical committee of the IEEE SPS. The name of the NNSP technical committee, and hence the workshop, was changed to Machine Learning for Signal Processing in September 2003 to better reflect the areas represented by the technical committee.
Topics
The workshop will feature keynote addresses, technical presentations, special sessions and tutorials, all of which will be included in the registration. Papers are solicited for, but not limited to, the following areas:
Learning Theory and Modeling; Bayesian Learning and Modeling; Sequential Learning; Sequential Decision Methods; Information-theoretic Learning; Neural Network Learning; Graphical and Kernel Models; Bounds on performance; Blind Signal Separation and Independent Component Analysis; Signal Detection; Pattern Recognition and Classification, Bioinformatics Applications; Biomedical Applications and Neural Engineering; Intelligent Multimedia and Web Processing; Communications Applications; Speech and Audio Processing Applications; Image and Video Processing Applications.
A data analysis and signal processing competition is being organized in conjunction with the workshop. This competition is envisioned to become an annual event where problems relevant to the mission and interests of the MLSP community will be presented with the goal of advancing the current state-of-the-art in both theoretical and practical aspects. The problems are selected to reflect the current trends to evaluate existing approaches on common benchmarks as well as areas where crucial developments are thought to be necessary. Details of the competition can be found on the workshop website.
Selected papers from MLSP 2006 will be considered for a special issue of Neurocomputing to appear in 2007. The winners of the data analysis and signal processing competition will also be invited to contribute to the special issue.
Paper Submission Procedure
Prospective authors are invited to submit a double column paper of up to six pages using the electronic submission procedure described at the workshop homepage. Accepted papers will be published in a bound volume by the IEEE after the workshop and a CDROM volume will be distributed at the workshop.
Chairs
General Chair:Seán MCLOONE, NUI Maynooth,
Technical Chair:Tülay ADALI , University of Maryland, Baltimore County

Workshop on Multimedia Content Representation, Classification and Security (MRCS)

September 11 - 13, 2006
Istanbul, Turkey
Workshop website
In cooperation with
The International Association for Pattern Recognition (IAPR)
The European Association for Signal-Image Processing (EURASIP)
GENERAL CHAIRS
Bilge Gunsel,Istanbul Technical Univ.,Turkey
Anil K. Jain, Michigan State University, USA
TECHNICAL PROGRAM CHAIR
Murat Tekalp,Koc University, Turkey
SPECIAL SESSIONS CHAIR
Kivanc Mihcak, Microsoft Research, USA
Prospective authors are invited to submit extended summaries of not more than six (6) pages including results, figures and references. Submitted papers will be reviewed by at least two members of the program committee. Conference Proceedings will be available on site. Please check the website for further information.
IMPORTANT DATES
Notification of Acceptance: June 10, 2006
Camera-ready Paper Submission Due: July 10, 2006
Topics
The areas of interest include but are not limited to:
- Feature extraction, multimedia content representation and classification techniques
- Multimedia signal processing
- Authentication, content protection and digital rights management
- Audio/Video/Image Watermarking/Fingerprinting
- Information hiding, steganography, steganalysis
- Audio/Video/Image hashing and clustering techniques
- Evolutionary algorithms in content based multimedia data representation, indexing and retrieval
- Transform domain representations
- Multimedia mining
- Benchmarking and comparative studies
- Multimedia applications (broadcasting, medical, biometrics, content aware networks, CBIR.)

Workshop on Speech in Mobile and Pervasive Environments

(in conjunction with ACM Mobile HCI '06)
Espoo, Finland
September 12, 2006
Workshop website
Organisers
* Amit A. Nanavati, IBM India Research Laboratory.
* Nitendra Rajput, IBM India Research Laboratory.
* Alexander I. Rudnicky, Carnegie Mellon University.
* Roberto Sicconi, IBM T.J. Watson Research Center.
Programme Committee
* Abeer Alwan, UCLA, USA.
* Peter Boda, Nokia Research Center, Finland.
* Shrikanth S. Narayanan, USC, USA.
* David Pearce, Motorola, UK.
* Harry Printz, Promptu, USA.
* Markku Turunen, University of Tampere, Finland.
Theme
Traditionally, voice-based applications have been accessed using dumb telephone devices through Voice Browsers that reside on the server. The proliferation of pervasive devices and the increase in their processing capabilities, client-side speech processing is emerging as a viable alternative. This workshop will explore the various issues that arise while doing speech processing on resource-constrained, possibly mobile devices. The workshop will highlight the many open areas that require research attention, identify key problems that need to be addressed, and also discuss a few approaches for solving some of them, in order to make the next generation of conversational systems.
Topics of Interest
All areas that enable, optimise or enhance Speech in mobile and pervasive environments and devices. Possible areas include, but are not restricted to:
* Robust Speech Recognition in Noisy and Resource-constrained Environments
* Memory/Energy Efficient Algorithms
* Multimodal User Interfaces for Mobile Devices
* Protocols and Standards for Speech Applications
* Distributed Speech Processing
* Mobile Application Adaptation and Learning
* Prototypical System Architectures
* User Modelling
Intended Audience
This cross-disciplinary burgeoning area invites researchers interested in any aspect of the intersection of Speech processing and Mobile computing -- speech recognition, speech synthesis, multimodal interfaces, mobile HCI, distributed speech processing, mobile applications, voice user interface design, memory/energy efficient algorithms -- to meet and pave the way forward. We anticipate a good mix of industrial and academic participation which should lead to lively discussions. There appear to be many isolated groups of people working in these areas who need to come together as a community.
Submissions
We invite position papers (upto 8 pages - shorter papers are also welcome). Electronic submission is required. Submissions should be formatted according to at ACM SIG style . All submissions should be in PDF (preferred) or Postscript format. If any of these requirements is a problem for you, please feel free to contact the workshop organisers.
We also welcome participation without paper submission.
Please email your submissions and participation requests to:
Amit A. Nanavati
Nitendra Rajput
Note: Registration for this workshop in included in the MobileHCI'06 conference registration fee. Alternatively, participants can register only for the workshop - one day registration fee.
Seed Questions
* How do we construct speech systems with small footprints of memory and power consumption ?
* How to do speech recognition in noisy environments ?
* How can we distribute processing more efficiently given the increased available computing power on handhelds ?
* How do we make such devices adapt automatically to the user, task and environment ?
* What novel applications and services can be deployed on such devices ?
* What are the acoustic and linguistic implications ?
* Evaluation, Benchmarks and Performance modelling of mobile speech systems.
* What is the role of standards like VoiceXML/SALT in this domain ?
Key Dates
* Position Paper Submission Deadline: June 30, 2006
* Notification of Acceptance: July 10, 2006
* Early Registration Deadline: July 20, 2006
* Workshop Timing: 8:30AM -- 6:00PM, September 12, 2006.
Websites
* SiMPE Workshop
* ACM Mobile HCI '06

Ninth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2006)

Brno, Czech Republic, 11-15 September 2006
Website
The conference is organized by the Faculty of Informatics, Masaryk University, Brno, and the Faculty of Applied Sciences, University of West Bohemia, Pilsen. The conference is supported by International Speech Communication Association.
TSD SERIES
TSD series evolved as a prime forum for interaction between researchers in both spoken and written language processing from the former East Block countries and their Western colleagues. Proceedings of TSD form a book published by Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI) series.
TOPICS
Topics of the conference will include (but are not limited to):
text corpora and tagging
transcription problems in spoken corpora
sense disambiguation
links between text and speech oriented systems
parsing issues, especially parsing problems in spoken texts
multi-lingual issues, especially multi-lingual dialogue systems
information retrieval and information extraction
text/topic summarization
machine translation semantic networks and ontologies
semantic web speech modeling
speech segmentation
speech recognition
search in speech for IR and IE
text-to-speech synthesis
dialogue systems
development of dialogue strategies
prosody in dialogues
emotions and personality modeling
user modeling
knowledge representation in relation to dialogue systems assistive technologies based on speech and dialogue applied systems and software facial animation visual speech synthesis Papers on processing of languages other than English are strongly encouraged.
ORGANIZERS
Frederick Jelinek, USA (general chair)
Hynek Hermansky, USA (executive chair)
KEYNOTE SPEAKERS
Eduard Hovy, USA
Louise Guthrie, GB
James Pustejovsky, USA
FORMAT OF THE CONFERENCE
The conference program will include presentation of invited papers, oral presentations, and a poster/demonstration sessions. Papers will be presented in plenary or topic oriented sessions.
Social events including a trip in the vicinity of Brno will allow for additional informal interactions.
CONFERENCE PROGRAM
The conference program will include oral presentations and poster/demonstration sessions with sufficient time for discussions of the issues raised. The conference will welcome three keynote speakers - Eduard Hovy, Louise Guthrie and James Pustejovsky, and it will offer two special panels devoted to Emotions and Search in Speech.
IMPORTANT DATES
May 15 2006 .............. Notification of acceptance
May 31 2006 .............. Final papers (camera ready) and registration
July 23 2006 ............. Submission of demonstration abstracts
July 30 2006 ............. Notification of acceptance for demonstrations sent to the authors
September 11-15 2006 ..... Conference date
The contributions to the conference will be published in proceedings that will be made available to participants at the time of the conference.
OFFICIAL LANGUAGE
of the conference will be English.
ADDRESS
All correspondence regarding the conference should be addressed to
Dana Hlavackova, TSD 2006
Faculty of Informatics, Masaryk University
Botanicka 68a, 602 00 Brno, Czech Republic
phone: +420-5-49 49 33 29
fax: +420-5-49 49 18 20
email
LOCATION
Brno is the the second largest city in the Czech Republic with a population of almost 400.000 and is the country's judiciary and trade-fair center. Brno is the capital of Moravia, which is in the south-east part of the Czech Republic. It had been a Royal City since 1347 and with its six universities it forms a cultural center of the region.
Brno can be reached easily by direct flights from London and Munich and by trains or buses from Prague (200 km) or Vienna (130 km).

MMSP-06

IEEE Signal Processing Society 2006 International Workshop on Multimedia Signal Processing (MMSP06),
October 3-6, 2006,
Fairmount Empress Hotel, Victoria, BC, Canada
Website
- A Student Paper Contest with awards sponsored by Microsoft Research. To enter the contest a paper submission must have a student as the first author
- Overview sessions that consist of papers presenting the state-of-the-art in methods and applications for selected topics of interest in multimedia signal processing
- Wrap-up presentations that summarize the main contributions of the papers accepted at the workshop, hot topics and current trends in multimedia signal processing
- New content requirements for the submitted papers
- New review guidelines for the submitted papers
SCOPE
Papers are solicited for, but not limited to, the general areas:
- Multimedia Processing (modalities: audio, speech, visual, graphics, other; processing: pre- and post- processing of multimodal data, joint audio/visual and multimodal processing, joint source/channel coding, 2-D and 3-D graphics/geometry coding and animation, multimedia streaming)
- Multimedia Databases (content analysis, representation, indexing, recognition, and retrieval)
- Multimedia Security (data hiding, authentication, and access control)
- Multimedia Networking (priority-based QoS control and scheduling, traffic engineering, soft IP multicast support, home networking technologies, wireless technologies)
- Multimedia Systems Design, Implementation and Applications (design: distributed multimedia systems, real-time and non real-time systems; implementation: multimedia hardware and software; applications: entertainment and games, IP video/web conferencing, wireless web, wireless video phone, distance learning over the Internet, telemedicine over the Internet, distributed virtual reality)
- Human-Machine Interfaces and Interaction using multiple modalities
- Human Perception (including integration of art and technology)
- Standards
SCHEDULE
- Notification of acceptance by: June 8, 2006
- Camera-ready paper submission by: July 8, 2006 (Instructions for Authors)
Check the workshop website for updates.
Manage your subscription at: http://ewh.ieee.org/enotice/ options.php?LN=CONF

CFP Fifth Slovenian and First International LANGUAGE TECHNOLOGIES CONFERENCE IS-LTC 2006

Slovenian Language Technologies Society
Information Society - IS 2006
Ljubljana, Slovenia/October 9 - 10, 2006
conference website
The Slovenian Language Technologies Society invites contributions to its biennial conference to be held in the scope of the Information Society - IS 2006, taking place October 9 - 13, 2006 at the Jožef Stefan Institute in Ljubljana, Slovenia.
The official languages of the conference are English and Slovene. The conference will be organised in two tracks, one for contributions in English, and the other for those in Slovenian. The accepted papers will be published in printed proceedings, as well as on-line, on the conference Web site http://nl.ijs.si/is-ltc06/.
Conference Topics
We invite papers from academia, government, and industry on all areas of traditional interest to the HLT community, as well as related fields, including but not limited to:
* development, standardisation and use of language resources
* speech technologies
* machine translation and other multi- and cross-lingual processing
* semantic web and knowledge representation related HLT
* statistical and machine learning of language models
* information retrieval and extraction, question answering
* HLT applications
* presentations of HLT related projects
Invited speakers
> Nick Campbell, Chief Researcher, Media Information Science Laboratories
ATR, Japan
Steven Krauwer, Coordinator of ELSNET (European Network of Excellence in Human Language Technologies)
Utrecht University, Netherlands
Title of talk: Strengthening the smaller languages in Europe
Guidelines for Submissions
Submitted papers should present original research relevant to the field of human language technologies. Overview papers on HLT research and applications are also welcome.
The contributions should be written in English or Slovene. They should be 4 or 6 pages long and formatted according to the conference style guidelines, which are available from the conference Web site.
The papers will be published in printed proceedings, as well as on-line, on the conference Web site. Some papers will be chosen for re-submission to the journal Informatica.
Important Dates
June 25th paper submission deadline
September 15th camera ready submission
October 9 - 10 conference
Organising Committee
Tomaž Erjavec, Jožef Stefan Institute
Vojko Gorjanc, University of Ljubljana
Jerneja Žganec Gros, Alpineon
Information
Up to date information is available at http://nl.ijs.si/is-ltc06/ or email.

Call for papers- 9th DIMACS Implementation Challenge Workshop: Shortest Paths

WEBSITE
Goals
Shortest path problems are ones of the most fundamental combinatorial optimization problems with many applications, both direct and as subroutines in other combinatorial optimization algorithms. Algorithms for these problems have been studied since 1950's and still remain an active area of research. One goal of this Challenge is to create a reproducible picture of the state of the art in the area of shortest path algorithms. To this end we are identifying a standard set of benchmark instances and generators, as well as a benchmark implementations of well-known shortest path algorithms. Another goal is to enable current researchers to compare their codes with each other, in hopes of identifying the more effective of the recent algorithmic innovations that have been proposed. The final goal is to publish proceedings containing results presented at the Challenge Workshop, and a book containing the best of the proceedings papers.
Scope
The Challenge addresses a wide range of shortest path problems, including all sensible combinations of the following:
* Point-to-point, single-source, all-pairs.
* Non-negative arc lengths and arbitrary arc lengths (including negative cycle detection).
* Directed and undirected graphs.
* Static and dynamic problems. The latter include those dynamic in CS sense (arc additions, deletions, length changes) and those dynamic in OR sense (arc transit times depending on arrival times).
* Exact and approximate shortest paths.
* Compact routing tables and shortest path oracles.
Implementations on any platform of interest, for example desktop machines, supercomputers, and handheld devices, are encouraged.
How to participate
People interested in submitting papers to the Challenge Workshop can find benchmark instances, generators, and code for the problems they address at the Challenge website, along with detailed information on file formats. Your work can take two different directions.
1. Defining instances for algorithm evaluation. The instances should be natural and interesting. By the latter we mean instances that cause good algorithms to behave differently from the other instances. Interesting real-life application data are especially welcome.
2. Algorithm evaluation. Description of implementations of algorithms with experimental data that supports conclusions about practical performance. Common benchmark instances and codes should be used so that there is common ground for comparison. The most obvious way for such a paper to be interesting (and selected for the proceedings) is if the implementation improves state-of-the-art. However, there may be other ways to produce and interesting paper, for example by showing that an approach that looks well in theory does not work well in practice by explaining why this is the case.
Challenge Book
The best papers presented at the Challenge Workshop will be selected for publication in a book published in the DIMACS Book Series.
Important dates
- August 25, 2006: Paper submission deadline
- September 25, 2006: Author notification
- November 13-14, 2006: Challenge Workshop, DIMACS Center, Rutgers University, Piscataway, NJ
Organizing Committee
Camil Demetrescu, University of Rome "La Sapienza"
Andrew Goldberg, Microsoft Research
David Johnson, AT&T Labs - Research
Advisory Committee
Paolo Dell'Olmo, University of Rome "La Sapienza"
Irina Dumitrescu, University of New South Wales
Mikkel Thorup, AT&T Labs-Research
Dorothea Wagner, Universitaet Karlsruhe

Call for papers 8th International Conference on Signal Processing

Nov. 16-20, 2006, Guilin, China
website
The 8th International Conference on Signal Processing will be held in Guilin, China on Nov. 16-20, 2006. It will include sessions on all aspects of theory, design and applications of signal processing. Prospective authors are invited to propose papers in any of the following areas, but not limited to:
A. Digital Signal Processing (DSP)
B. Spectrum Estimation & Modeling
C. TF Spectrum Analysis & Wavelet
D. Higher Order Spectral Analysis
E. Adaptive Filtering &SP
F. Array Signal Processing
G. Hardware Implementation for Signal Processing
H. Speech and Audio Coding
I. Speech Synthesis & Recognition
J. Image Processing & Understanding
K. PDE for Image Processing
L. Video compression &Streaming
M. Computer Vision & VR
N. Multimedia & Human-computer Interaction
O. Statistic Learning & Pattern Recognition
P. AI & Neural Networks
Q. Communication Signal processing
R. SP for Internet and Wireless Communications
S. Biometrics & Authentification
T. SP for Bio-medical & Cognitive Science
U. SP for Bio-informatics
V. Signal Processing for Security
W. Radar Signal Processing
X. Sonar Signal Processing and Localization
Y. SP for Sensor Networks
Z. Application & Others

CFP CI 2006 Special Session on Natural Language Processing for Real Life Applications

November 20-22, 2006 San Francisco, California, USA
Website
Topics
The Special Session on Natural Language Processing for Real Life Applications will cover the following topics (but is not limited to):
1. speech recognition, in particular
* multilingual speech recognition
* large vocabulary continuous speech recognition with focus on the application
2. real life dialog systems
* natural language dialog systems
* multimodal dialog systems
3. speech-based classification
* speaker classification, i.e. exploiting paralinguistic features of the speech to gather information about the speaker (for example age, gender, cognitive load, and emotions)
* language and accent identification
Paper Submission
Please submit papers for the special session directly to the session chair (christian.mueller@dfki.de). DO NOT submit the papers through the IASTED website. Otherwise, the papers will be handled as general papers for the conference. Each submission will be reviewed by at least two independent reviewers. The final selection of papers for the session will be done by the session chair; acceptance/rejection letters and review comments along with registration information will be provided by IASTED by the general Notification deadline.
Formatting instructions
Please follow the formatting instructions provided by IASTED. Website.
Important Dates
Submissions due June 15, 2006
Notification of acceptance August 1, 2006
Camera-ready manuscripts due September 1, 2006
Registration Deadline September 15, 2006
Conference November 20 - 22, 2006
Registration
All papers accepted for the special session are required to register before the general conference registration deadline.

ELEVENTH AUSTRALASIAN INTERNATIONAL CONFERENCE ON SPEECH SCIENCE AND TECHNOLOGY

AUCKLAND, NEW ZEALAND, 6-8 DECEMBER 2006
Conference Website Conference Website
The Australasian Speech Science and Technology Association (ASSTA) is a scientific association that aims to advance the understanding of speech science and its application to speech technology. ASSTA and the University of Auckland are pleased to announce the Eleventh International Conference on Speech Science and Technology (SST2006).
Conference Themes
Submissions are invited for oral and poster presentations. Submissions should describe original contributions to spoken language, speech science and/or technology that will be of interest to an audience including scientists, engineers, linguists, psychologists, speech and language therapists, audiologists and other professionals. Submissions are invited in all areas of speech science and technology, but particularly in the following areas:
Speech production
Acoustic phonetics
Acoustics of accent change
Music and speech processing
Emotional speech, voice, intonation and prosody
Applications of speech science and technology
Speech Processing for Forensic Applications
Speech recognition and understanding
Speaker recognition and classification
Speech enhancement and noise cancellation
Pedagogical technologies for speech and singing
Corpus management and speech tools
Contributions of speech science and technology to Phonetics and Phonology of Australian and New Zealand English audiology and speech language therapy (PANZE)
Combined session with Australasian Conference on Robotics and Automation
Keynote Speakers
Prof. Joseph Perkell, Massachusetts Institute of Technology
Prof. Pat Keating, University of California Los Angeles
Prof. Michael Corballis, University of Auckland.
Important Dates
. Abstract submission closing date - Monday, 28 August 2006
. Acceptance notice date - Monday, 25 September 2006
. Manuscript closing date - Monday, 6 November 2006
. Early registration date for conference and pre-conference workshop - Sunday, 29 October 2006
. Presenter/Author registration Deadline - Sunday, 29 October 2006
. Pre-conference tutorials and workshops - 5 December 2006
. SST 2006 Conference, 6-8 December
Important Contacts:
Abstract and Manuscript Submission: these should be submitted online. Click on the "Submission" link and follow the guidelines posted. Word and Latex templates, and a comprehensive author's guide for submissions, are available on the website.
Registration: An online registration form can be found on the conference website. Any queries regarding your registration should be directed either to the University Conference Management or to the Conference Chair Dr Catherine Watson.
Pre-Conference Workshops: Any enquiries regarding the Pre-Conference workshops should be sent to Assoc. Prof. Paul Warren.
Conference Organising Committee: Dr Catherine Watson (chair), Assoc. Prof. Paul Warren, Dr Waleed Abdulla, Dr Elaine Ballard, Helen Charters, Dr. Claire Fletcher Flynn, Dr Bernard Guillemin, Dr William Thorpe, Assoc. Prof. Suzanne Purdy, Dr Peter Keegan
Conference Advisory Committee Prof. Cathy Best, Prof. Bob Bogner, Prof. Herve Bourlard, Prof. Anne Cutler, Prof. Hiroya Fujisaki, . Jonathan Harrington, Prof. Hynek Hermansky, Prof. Louis Pols, Prof. Peter Thorne, Prof. Roger Wales, Assoc. Prof. Paul Warren, Assoc. Prof. Thomas Fang Zheng Pre-Conference Workshops: Morning 1. Speech Processing Waleed Abdulla, University of Auckland 2. Intonation and Prosody in AuE and NZ Janet Fletcher, University of Melbourne and Paul Warren, Victoria University of Wellington Afternoon 3. Speech database management and access Jen Hay, University of Canterbury 4. The phonetics of Maori Peter Keegan, University of Auckland Accommodation: A variety of accommodation options have been arranged at special conference rates. An accommodation reservation form can be downloaded from the website http://www.assta.org/sst/2006/. Other hotels within walking distance of the University include The Copthorne, Duxton, Rydges and Quest on Mount. Information regarding these hotels can be found on the www.nz.com website

CFP - IEEE/ACL 2006 Workshop on Spoken Language Technology

Aruba Marriott
Palm Beach, Aruba
December 10 -- December 13, 2006
Workshop website
Workshop Topics
Spoken language understanding; Spoken document summarization, Machine translation for speech; Spoken dialog systems; Spoken language generation; Spoken document retrieval; Human/Computer Interactions (HCI); Speech data mining; Information extraction from speech; Question/Answering from speech; Multimodal processing; Spoken language systems, applications and standards.
Submissions for the Technical Program
The workshop program will consist of tutorials, oral and poster presentations, and panel discussions. Attendance will be limited with priority for those who will present technical papers; registration is required of at least one author for each paper. Submissions are encouraged on any of the topics listed above. The style guide, templates, and submission form will follow the IEEE ICASSP style. Three members of the Scientific Committee will review each paper. The workshop proceedings will be published on a CD-ROM.
Schedule
Camera-ready paper submission deadline July 15, 2006
Hotel Reservation and Workshop registration opens July 30, 2006
Paper Acceptance / Rejection September 1, 2006
Hotel Reservation and Workshop Registration closes October 15, 2006
Workshop December 10-13, 2006
Registration and Information
Registration and paper submission, as well as other workshop information, can be found on the SLT website.

Organizing Committee
General Chair: Mazin Gilbert, AT&T, USA
Co-Chair: Hermann Ney, RWTH Aachen, Germany
Finance Chair: Gokhan Tur, SRI, USA
Publication Chair: Brian Roark, OGI/OHSU, USA
Publicity Chair: Eric Fosler-Lussier, Ohio State U., USA
Industrial Chair: Roberto Pieraccini, Tell-Eureka, USA

IEEE International Symposium on Multimedia - ISM 2006

Conference website
Special track: Remote Sensors for Audio Processing
In recent decades, the cost of acoustic technologies has declined dramatically. Advances in networks, storage devices, and power management have made it practical to consider the remote location of sensors that either transmit data to a central processing facility or store the data for later retrieval. Nonetheless, many challenges remain for the fabrication, deployment and use of remote sensors. In locations with limited infrastructure, power management and the ability for the user to access or retrieve the data are paramount. In some situations, the need for localization or improved signal to noise ratio may dictate the use of microphone arrays or other signal enhancement techniques. Deployment in hostile environments such as arctic or deep sea conditions requires additional considerations. Remote sensors are capable of generating large acoustic or mixed media datasets. With these large corpora, the need for automated processing becomes critical as the staffing requirements for human analysis are both cost and labor prohibitive. The development of automated analysis can yield valuable data such as seasonal or diel patterns of animals, perimeter intrusion detection, access control, and a myriad of other applications. This special session invites researchers to submit high quality papers describing either preliminary or mature results on topics related to audio for remote sensors.
Topics of interest
· Audio classification and detection tasks for remote sensors (speech, bioacoustics, auditory scene analysis, etc.)
· Deployment issues
· Power management
· Networking/Storage/Data Management
· Array processing
· Remote audio sensors in challenging environments
· Applications of remote sensors with a significant audio component
Submissions and deadlines
The written and spoken language of ISM2006 is English. Authors should submit an 8-page technical paper manuscript in double-column IEEE format including authors' names and affiliations, and a short abstract electronically. Submissions should be directed to Prof. Marie Roch , following the formatting instructions available in the submission guidelines for regular papers. Note that papers should not be submitted directly to ISM web site. Only electronic submissions will be accepted. All papers should be in Adobe portable document format (PDF). The paper should have a cover page, which includes a 200-word abstract, a list of keywords, and author's phone number and e-mail address. The Conference Proceedings will be published by the IEEE Computer Society Press.
Important dates:
· August 8 - submission of papers
· September 10 - Notification of acceptance of papers
· September 25 - Camera-ready papers due
· December 11-13 - Conference at Paradise Point Resort & Spa in San Diego , California

CFP ICASSP 2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing
April 15-20, 2007
Honolulu, Hawaii, U.S.A.
conference website
Tutorial Proposals Due August 4, 2006
Special Session and Panel Proposals Due August 4, 2006
Notification of Special Session & Tutorial Acceptance September 8, 2006
TOPICS
* Audio and electroacoustics
* Bio imaging and signal processing * Design and implementation of signal processing systems
* Image and multidimensional signal processing
* Industry technology tracks
* Information forensics and security
* Machine learning for signal processing
* Multimedia signal processing
* Sensor array and multichannel systems
* Signal processing education
* Signal processing for communications
* Signal processing theory and methods
* Speech processing
* Spoken language processing
Submission of Papers
Prospective authors are invited to submit full-length, four-page papers , including figures and references, to the ICASSP Technical Committee. All ICASSP papers will be handled and reviewed electronically. Please note that the submission dates for papers are strict deadlines.
Tutorial, Special Session, and Panel Proposals
Tutorials will be held on April 15 and 16, 2007. Brief proposals should be submitted by August 4, 2006, to Hideaki Sakai by email and must include title, outline, contact information for the presenter, and a description of the tutorial and material to be distributed to participants together with a short biography of the presenter and a list of publications related to the proposal. Special session and panel proposals should be submitted by August 4, 2006, to Phil Chou through the the ICASSP 2007 website and must include a topical title, rationale, session outline, contact information, and a list of invited speakers.
Important Deadlines
Tutorial Proposals Due: August 4, 2006
Special Session and Panel Proposals Due: August 4, 2006
Notification of Special Session & Tutorial Acceptance: September 8, 2006
Submission of Camera-Ready Papers: September 29, 2006
Notification of Acceptance (by email): December 15, 2006
Author's Registration Deadline: February 2, 2007
Chairs
General Chairs
K. J. Ray Liu, University of Maryland, College Park
Todd Reed, University of Hawaii
Technical Program Chairs
Anthony Kuh, University of Hawaii
Yih-Fang Huang, University of Notre Dame

16th International Congress of Phonetic Sciences

Saarland University, Saarbrücken,
6-10 August 2007.
The first call for papers will be made in April 2006. The deadline for *full-paper submission* to ICPhS 2007 Germany will be February 2007. Further information is available under conference website

RECENT ADVANCES IN NATURAL LANGUAGE PROCESSING (RANLP-07)

SAMOKOV hotel, Borovets, Bulgaria
conference website
RANLP-07 tutorials: September 23-25, 2007 (Sunday-Tuesday)
RANLP-07 workshops: September 26, 2007 (Wednesday)
6th Int. Conference RANLP-07: September 27-29, 2007 (Thursday-Saturday)
We are pleased to announce that the dates for RANLP’07 have been finalised (see above). Building on both the successful international summer schools organised for more than 17 years, and previous conferences held in 1995, 1997, 2001, 2003 and 2005, RANLP has become one of the most influential, competitive and far-reaching conferences, with wide international participation from all over the world. Featuring leading lights in the area as keynote speakers or tutorial speakers, RANLP has now grown into a larger-scale meeting with accompanying workshops and other events. In addition to the 6 keynote speeches and tutorials on hot NLP topics, RANLP07 will be accompanied by workshops and shared task competitions.
Volumes of selected papers are traditionally published by John Benjamins Publishers and previous conferences have enjoyed support from the European Commission.
Important dates
: Conference 1st Call for Papers: October 2006;
Call for Workshop proposals: November 2006,
deadline of proposals end of January 2007;
Workshop selection: early March 2007;
Conference Submission deadline: March 2007 with notification 30 May 2007;
Workshop Submission deadline: 15 June 2007 with notification in July 2007;
RANLP-07 tutorials, workshops and conference: 23-30 September 2007
The conference will be held in the picturesque resort of Borovets. It is located in the Rila mountains and is one of the best known ski and tourist resorts in South-East Europe. The conference venue Samokov hotel offers excellent working and leisure facilities. Borovets is only 1 hour away from Sofia international airport.
THE TEAM BEHIND RANLP-07
Galia Angelova, Bulgarian Academy of Sciences, Bulgaria (Chair of the Organising Committee)
Kalina Bontcheva, University of Sheffield, UK
Ruslan Mitkov, University of Wolverhampton, UK (Chair of the Programme Committee)
Nicolas Nicolov, Umbria Communications, Boulder, USA
Nikolai Nikolov, INCOMA Ltd., Shoumen, Bulgaria
Kiril Simov, Bulgarian Academy of Sciences, Bulgaria (Workshop Coordinator)
E-mail

Multimedia Content Access: Algorithms and Systems (EI121)

Part of the IS&T/SPIE International Symposium on Electronic Imaging 28 January - 1 February 2007, San Jose, California, USA
Conference Chairs:
Alan Hanjalic, Technische Univ. Delft (Netherlands);
Raimondo Schettini, DISCo/Univ. degli Studi di Milano-Bicocca (Italy);
Nicu Sebe, Univ. van Amsterdam (Netherlands)
Topics
Content Analysis:
* image, audio and video characterization (feature extraction)
* fusion of text, image, video and audio data
* content parsing, clustering and classification
* semantic modeling
* image, video and audio similarity measures
* object and event detection and recognition
* benchmarking of content analysis methods and algorithms
* generic methods and algorithms for content analysis
* affective content analysis.
Content Management and Delivery:
* (Internet) multimedia databases
* multimedia standards (e.g. SVG, SMIL, MPEG-7)
* efficient peer-to-peer storage and search techniques
* indexing and data organization
* system optimization for search and retrieval
* storage hierarchies, scalable storage
* personalized content delivery.
Content Search/Browsing/Retrieval:
* multimedia data mining
* active learning and relevance feedback
* query models
* browsing and visualization
* search issues in distributed and heterogeneous systems
* benchmarking search, browsing, and retrieval algorithms and systems
* generation of video summaries and abstracts
* cognitive aspects of human/machine systems.
Internet Imaging and Multimedia:
* peer-to-peer imaging systems for the Internet
* content creation and presentation for the Internet
* web cameras: impact on content analysis techniques
* interactive multimedia creation for the Internet
* content rating, authentication, non-repudiation, and cultural differences in content perception
* XML applications
* web crawling, caching, and security
* semantic web
* (adaptable) user interfaces.
Applications:
* commerce
* medicine
* news
* entertainment
* wearable and ubiquitous computing
* management of meetings
* biometrics
* cultural heritage and education
* collaborative systems and multi-device applications
* life log applications
* military and civilian security applications.
The conference program will include invited keynote presentations, invited special sessions, and a panel of experts who will be discussing the remaining research challenges related to multimedia content analysis, management and retrieval.
Important Dates
Paper Proposals (5,000 words): 04 August 2006 (last extension)
Final Manuscript Due Date: 13 November 2006
200-word Final Summary: 20 November 2006

CFP International Conference on Information Sciences, Signal Processing and their Applications (ISSPA 2007)

ISSPA 2007 marks the 20th anniversary of launching the first ISSPA in 1987 in Brisbane, Australia. Since its inception, ISSPA has provided, through a series of 8 symposia, a high quality forum for engineers and scientists engaged in research and development of Signal and Image Processing theory and applications. Effective 2007, ISSPA will extend its scope to add the new track of information sciences. Hence, the intention that the previous full name of ISSPA is replaced after 2007 by the following new full name: International Conference on Information Sciences, Signal Processing and their Applications. ISSPA is an IEEE indexed conference.
ISSPA 2007 will be organized between February 12 to 15, 2007 in Sharjah, United Arab Emirates (UAE) by three prominent institutions located in Sharjah in the United Arab Emirates: University of Sharjah, American University of Sharjah, and Etisalat University College.
The regular technical program will run for three days along with an exhibition of signal processing and information sciences products. In addition, tutorial sessions will be held on the first day of the symposium.
Topics
Papers are invited in, but not limited to, the following topics:
1.Filter Design Theory and Methods
2. Multirate Filtering & Wavelets
3.Adaptive Signal Processing
4.Time-Frequency/Time-Scale Analysis
5.Statistical Signal & Array Processing
6.Radar & Sonar Processing
7.Speech Processing & Recognition
8.Fractals and Chaos Signal Processing
9.Signal Processing in Communications
10.Signal processing in Networking
11. Multimedia Signal Processing
12. Nonlinear signal processing
13.Biomedical Signal and Image Processing
14.Image and Video Processing
15.Image Segmentation and Scene Analysis
16. VLSI for Signal and Image Processing
17.Cryptology, Steganography, and Digital Watermarking
18. Image indexing & retrieval
19.Soft Computing & Pattern Recognition
20. Natural Language Processing
21.Signal Processing for Bioinformatics
22. Signal Processing for Geoinformatics
23.Biometric Systems and Security
24.Machine Vision
25.Data visualization
26. Data mining
27. Sensor Networks and Sensor Fusion
28.Signal Processing and Information Sciences Education
29.Others
How to submit?
Prospective authors are invited to submit full length (four pages) papers for presentation in any of the areas listed above (indicate area in your submission). We also encourage the submission of proposal for student session, tutorial and sessions on special topics. All articles submitted to ISSPA 2007 will be peer-reviewed using a blind review process.
For more details and submission of papers please see : conference website
Important Dates
Full Paper Submission: September 15, 2006
Tutorials/Special Sessions Proposals: September 15, 2006
Notification of Paper Acceptance: November 15, 2006
Final Accepted Paper Submission: December 1, 2006
Conference: February 12 to 15, 2007 Contact person:
Dr Mohammed Al-Mualla ISSPA07 Publicity Chair

top