ISCApad number 76

October 1st, 2004

Dear ISCA members,

Many of you will attend in the next days the Interspeech-ICSLP conference in Jeju (Korea). Please stop by our stand and contact members of the Isca Board for all questions about the Association. You are all invited to attend the General Assembly of Members on October 6th in Hall A from 5PM to 6PM. Have a safe journey to Jeju.

Do not forget to send the information you want to display for members in time to be included in IscaPad (last week of each month).

TABLE OF CONTENTS

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

ISCA NEWS

Organisation of INTERSPEECH 2008 ICSLP
CALL FOR PROPOSALS
Individuals or organisations interested in organizing INTERSPEECH 2008-ICSLP should submit by 15 December 2004 a brief preliminary proposal, including:
* The name and position of the proposed general chair and other principal organizers.
* The proposed period in September 2008 when the conference would be held
* The institution assuming financial responsibility for the conference and any other sponsoring institutions
* The city and conference center proposed (with information on that center's capacity)
* Information on transportion and housing for conference participants
* Likely support from local bodies (e.g. governmental)
* The commercial conference organizer (if any)
* A preliminary budget
Guidelines for the preparation of the proposal are available at http://www.isca-speech.org/guidelinesEurospeech.html . Additional information can be provided by Julia Hirschberg.
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 2009.

ISCA Archive:
Professor Wolfgang Hess has started an important archiving process of all publications of ISCA including ICSLP, Eurospeech and ITRW proceedings. Access to full papers is restricted to ISCA members on our website http://www.isca-speech.org/archive.html.
Recently ICSLP 2002 and Eurospeech 2003 have been added to the collection.

ISCA Annual General Meeting
The next ISCA General Assembly will take place on Wednesday 6 October from 6 to 7 pm in Jeju during ICSLP 2004. An agenda will be sent by email to all members in early September.

-New development on membership services :
It is now possible to apply forISCA membership and renew online. Members benefit a discounted rate for Speech Communication subscription.
The online subscription gives members access not only to the current year's Speech Communication volumes but also to the Speech Communication archive dating back to 1995.
If you are interested in subscribing either to the paper version alone or to the paper version+online access, please indicate this on the renewal form (http://www.isca-speech.org/index_VIP.html) ) and it will be billed directly by Elsevier.
Individual, FULL member and STUDENT : paper version only: 85 EUR
Individual, FULL member and STUDENT : paper version + online access*: 95 EUR
Institutional Member, paper version only : 600 EUR

- A full list of members (including membership numbers and subcription expiry dates) is available online at: http://www.isca-speech.org/member_list.html

-ISCApad publishes now a list of papers
accepted for publication in Speech Communication. These papers can be also viewed on the website of ScienceDirect (http://www.sciencedirect.com) if your institution has subscribed to Speech Communication.

-ISCA Grants
are available for students attending meetings. Even if no information on the grants is advertised on the conference announcement,students may apply.
For more information: http://www.isca-speech.org/grants

top

COURSES, DATABASES, SOFTWARES

- German-French Summerschool on Cognitive and physical models of speech production, perception and perception-production interaction
sponsored by the German French University (DFH) Saarbrucken. 19th-24th of September 2004 in Lubmin, Germany (Baltic Sea).
Contact(see ISCApad 69)

-Information on on-going theses
could be very useful for thesis supervisors, researchers as well as PhD students. A list of speech theses is available under the section HLTheses at http://www.elsnet.org

top

JOB OPENINGS

(also have a look at http://www.isca-speech.org/jobs as well as http://www.elsnet.org > Jobs)

RESEARCH AND DEVELOPPEMENT OPPORTUNITIES IN THE LORIA LABORATORY, FRANCE (Nancy)
Position at the LORIA laboratory, Speech group.
Job Title: Research Engineer
Job Function :Research and development
Job Type : Fixed Term (11 months)
Closing date for applications: 1 November 2004
Further Information : http://www.loria.fr/equipes/parole
UNIX programming skills, C, Shell
Required level : PhD in Computer Science with specialty of Speech Recognition or engineer level with at last 2 years of experience in Speech Recognition
Job description

A research engineer is needed for the LORIA laboratory to work on the European Project HIWIRE. The applicant will develop, run and analyze the experiments in automatic speech recognition. Applicants should hold a PhD in Computer Science with specialty in Speech Recognition or have an engineer level with at last 2 years of experience in Speech Recognition. He should have a good grasp of statistics and speech processing. The ideal candidate will have experience in noise robustness and speaker adaptation. UNIX programming skills are highly desirable (C, C++, Java, Shell).

HIWIRE (Human Input That Works In Real Environments) European project concerned with vocal technologies to support human-machine interaction, in the context of aircraft cockpits. The goal of the project is :
- to enable vocal dialogues with equipments in commercial aircraft cockpits
- to improve the potential for vocal interaction with PDAs and other mobile devices in aeronautic application environments.
The project will focus on two main targets :
- improved robustness of speech recognition system against the environment ;
- improved tolerance to user behavior.
This appointment is for a fixed term of up to 11 months, starting between 1 October, 2004 and 1 January, 2005.

Send your motivation letter, your CV and academic references to contact persons: Irina Illina or Dominique Fohr
Speech group
LORIA-CNRS & INRIA Lorraine
B.P. 239
54506 Vandoeuvre-les-Nancy
France
tel: +33(0)3.83.59.20.27
fax: +33(0)3.83.41.30.79

Speech Recognition Programmer & Scientist at the ESAT/PSI SPEECH GROUP
Katholieke Universiteit Leuven, Belgium
A position is available for a speech recognition programmer and scientist within the ESAT Speech Group.
Focus of the work will be on further implementation of our speech recognition software architecture and further optimization of the existing system. The work is situated on the edge of research and implementation. The candidate will also become responsible for supporting novice users of the software package. The position is currently open and is initially available till 30 SEP 2006.
Candidates should have a degree in electrical engineering or computer science. Given the type of work, candidates should have programming experience on a UNIX or Windows platform using a higher level language such as C/C++/JAVA. Good communication skills will be an asset as well. Previous experience in speech recognition is not required, but definitely welcome.
The work will be carried out within the framework of several ongoing and future research projects of which the main one is FLAVOR. More details about the ESAT speech group and the Flavor project in particular can be found at http://www.esat.kuleuven..ac.be/~spch
Interested applicants should send their CV to Prof. Dirk VAN COMPERNOLLE
KULeuven, ESAT-PSI
Kasteelpark Arenberg 10
3001 Heverlee
BELGIUM

POST DOC or RESEARCH ENGINEER POSITION at Institut Eurecom-Sophia Antipolis-France
Department: Multimedia Communications
Eurecom (http://www.eurecom.fr ) is an international teaching and research institute , founded in 1991 as a joint initiative by Ecole Polytechnique Federale de Lausanne (EPFL) and Ecole Nationale Superieure des Telecommunications (ENST- Paris). It welcomes students from several engineering schools and universities ENST Paris, ENST Brittany, INT Evry, EPFL, ETHZ (Zurich), Helsinki University of Technology, Politecnico di Torino...They receive an education in Communications Systems (Networking, Multimedia, Security, Mobile Communications, Web services...) Professors, lecturers and PhD students conduct research in these domains. Speech processing is under the responsibility of Professor Chris Wellekens in the Dpt Multimedia Communications.
Spoken languages at the Institute are French end English for the lectures. English is the usual language for research exchanges. Speech research involves speaker identification using speaker clustering or eigenvoices, phonemic variabilities of lexicons, optimal feature extraction, Bayesian networks and variational techniques, navigation in audio databases (segmentation in speakers, wordspotting,...).
Job description: POST DOC or RESEARCH ENGINEER The European project DIVINES, a STREP/6th FP has been accepted by the Commission and will start in January 2004. Eight labs and companies are partners: Multitel (B), Eurecom (F), France Telecom R/D (F), University of Oldenburg (D), Babeltechnologies (B), Loquendo (I), Politecnico di Torino (I), LIA (F). A collaboration with Mac Gill University (Montreal) has also be negotiated. The aim of the project is to analyse the reasons why recognizers are unable to reach the human recognition rates even in the case of lack of semantic content. All weaknesses will be analyzed at the level of feature extraction, phone and lexical models. Focus will be put on intrinsic variabilities of speech in quiet and noisy environment as well as in read and spontaneous speech. The analysis will not be restricted to tests on several databases with different features and models but will go into the detailed behavior of the algorithms and models. Suggestions of new solutions will arise and be experimented. The duration of the project is for 3 years.
The Speech group is looking for a Post-doc or research engineer who acquired a hands-on practice of speech processing. He/she must have an excellent practice of signal and speech analysis as well as a good knowledge of optimal classification using Bayesian criteria. He/she must be open-minded to original solutions proposed after a rigorous analysis of the low level phenomena in speech processing. Fluency in english is mandatory (write, understand and speak). He/she should be able to represent Eurecom at the periodical meetings. Ability to work in a small team is also required.
Application.
-send a detailed resume (give details on your activity since your PhD graduation)
-send a copy of your thesis report (either as a a printed document or as a CDROM) DO NOT attach your thesis in an e-mail!)
-send a copy of your diploma)
-send the names and email addresses of two referees.)
-send the list of your publications (you must have several))
to Professor Chris J. Wellekens, Dpt of Multimedia Communications, 2229 route des Cretes, BP 193, F-06904 Sophia Antipolis Cedex, France.
Additional informations
Contact Professor Chris Wellekens (http://www.eurecom.fr/~welleken )

POST-DOCTORAL POSITION IN ASR
Application Deadline: 30th November 2004
Start date (latest): 1st March 2005
Applications are invited for a Post-Doctoral position to be held 9 months in Technical University of Crete, Chania, Greece followed by 9 months at LORIA, Nancy, France.
The successful applicant should have a PhD in the area of Computer Science, Statistics, Engineering, Mathematics or Physics. The candidate sould have a strong speech/signal processing background with emphasis in speech recognition. Good knowledge of statistical modeling and front-end techniques for robust speech recognition is a plus. Strong software skills are important (C/C++, script languages).
The project involves the development of novel feature extraction algorithms and statistical models for automatic speech recognition. The collaboration is part of the MUSCLE Network of Excellence EU Project (www.muscle-noe.org) and extends over 18 months. The parties involved are:
- The "Speech and Dialogue Group" at the Technical University of Crete, Greece (http://www.speech.tuc.gr)
- The "Computer Vision, Speech and Signal Processing Group" at the Technical University of Athens, Greece (http://cvsp.cs.ntua.gr)
-The "Speech Group" at INRIA-LORIA of Nancy, France (http://www.loria.fr/equipes/parole)
Note that for the first 9 months, the candidate will be based at TUC Chania (or NTUA Athens), Greece and for the the last 9 months the candidate will work at INRIA-LORIA, Nancy, France.
The stipend is 29660 Euros/year tax free with social security paid by MUSCLE. More information about MUSCLE Fellowships can be found at:
* http://www.cwi.nl/projects/muscle/public/events/fellowship-program.html
* http://www.muscle-noe..org/ifp.html
. Please send a CV and the names of 3 referees to Alex Potamianos and Khalid Daoudi by Oct 30th 2004.
For further information, interested candidates can contact any of the following:
* Alex Potamianos
* Khalid Daoudi
* Petros Maragos
* Vasilis Digalakis

RESEARCH OPPORTUNITIES IN THE AMI TRAINING
PROGRAMME AMI (Augmented Multiparty Interaction) is an integrated project funded by the EC Framework 6 programme from January 2004 for 3 years.
AMI is concerned with multimodal technologies to support human interaction, in the context of smart meeting rooms and remote meeting assistants. The project aims to develop new tools for understanding, searching and browsing meetings data captured from a wide range of devices, as part of an integrated multimodal group communication. AMI will thus address a range of multidisciplinary research including natural speech recognition, speaker tracking and segmentation, visual shape tracking, gesture recognition, multimodal dialogue modelling, meeting dynamics, summarisation, browsing and retrieval.
AMI supports a training programme whose objective is to provide opportunites for undergraduates, masters students, Ph.D. students and postdoctoral researchers to take part in AMI.
* The training programme funds internships and exchanges.
* Visits typically occupy at least 3 months for undergraduates and masters students and at least 6 months for Ph.D. students and postdoctoral researchers.
* Funding covers travel and living expenses, but not salary. Living expenses will typically be 1250 Euro/month.
* The programme is open to all, but priority is given to researchers who are members of AMI teams, researchers who intend to visit AMI teams, researchers who can demonstrate close connections with AMI research, proposals with an industrial component,.
* A specific programme funds visits of 6 months or more to the International Computer Science Institute, Berkeley, CA.
In this case typical living expenses are 2000 Euro/Month. For Ph.D. students and postdoctoral researchers, visits to ICSI will typically be at least 6 months. Senior scientists are also encouraged to apply, in which case proposals for shorter visits will also be entertained.

HOSTING SITES AMI's 15 partners and associated companies and institutions (details on http://www.amiproject.org) will act as hosts for the training programme. The project is jointly managed by IDIAP (CH) and The University of Edinburgh (UK). The training programme is managed by the University of Sheffield (UK).

HOW TO APPLY
The application form can be downloaded from http://www.dcs.shef.ac.uk/~linda/AMI/training.htm.
You will need the written support of your home institution and the host institution. You will also need an academic reference.
Enquiries may be addressed to Linda Perna, AMI training programme administrator.

WHEN TO APPLY You can apply at any time but applications will be considered on a quarterly basis, with deadlines of 15th September and 15th December.
Professor Phil Green
AMI Training Manager
Department of Computer Science
University of Sheffield
Regent Court 211 Portobello St., Sheffield S1 4DP UK phone: (44) 114 22 21828 fax: (44) 114 22 21810
Contact person: Phil Green
http://www.dcs.shef.ac.uk /people/P.Green
 

-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.

Taisuke Ito, Kazuya Takeda and Fumitada Itakura, Analysis and recognition of whispered speech, Speech Communication, In Press, Corrected Proof, Available online 23 September 2004

Jean Vroomen, Sabine van Linden, Mirjam Keetels, Béatrice de Gelder and Paul Bertelson, Selective adaptation and recalibration of auditory speech by lipread information: dissipation, Speech Communication, In Press, Corrected Proof, Available online 23 September 2004

J.P. Barker, M.P. Cooke and D.P.W. Ellis, Decoding speech in the presence of other sources, Speech Communication, In Press, Corrected Proof, Available online 22 September 2004

Akiko Kusumoto, Takayuki Arai, Keisuke Kinoshita, Nao Hodoshima and Nancy Vaughan, Modulation enhancement of speech by a pre-processing algorithm for improving intelligibility in reverberant environments, Speech Communication, In Press, Uncorrected Proof, Available online 23 July 2004

Mark M.J. Houben, Armin Kohlrausch and Dik J. Hermes, Perception of the size and speed of rolling balls by sound, Speech Communication, In Press, Corrected Proof, Available online 20 August 2004, .

Kalle J. Palomäki, Guy J. Brown and DeLiang Wang, A binaural processor for missing data speech recognition in the presence of noise and small-room reverberation, Speech Communication, In Press, Corrected Proof, Available online 20 August 2004,

Michael L. Seltzer, Bhiksha Raj and Richard M. Stern, A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition, Speech Communication, In Press, Corrected Proof, Available online 20 August 2004,

Masataka Goto, A real-time music-scene-description system: predominant-F0 estimation for detecting melody and bass lines in real-world audio signals, Speech Communication, In Press, Corrected Proof, Available online 20 August 2004,

M.P. Cooke and D.P.W. Ellis, Introduction to the special issue on the recognition and organization of real-world sound, Speech Communication, In Press, Corrected Proof, Available online 18 August 2004,

Bhiksha Raj, Michael L. Seltzer and Richard M. Stern, Reconstruction of missing features for robust speech recognition, Speech Communication, In Press, Uncorrected Proof, Available online 8 August 2004, . Proof, Available online 6 August 2004,

Hiroshi G. Okuno, Kazuhiro Nakadai and Hiroaki Kitano, Effects of increasing modalities in recognizing three simultaneous speeches, Speech Communication, In Press, Uncorrected Proof, Available online 3 August 2004,

Geoffrey L. Collier, A comparison of novices and experts in the identification of sonar signals, Speech Communication, In Press, Uncorrected Proof, Available online 30 July 2004, .

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 (ICSLP)-2004 , Jeju, KOREA, OCTOBER 5-9, 2004 (see CFP in ISCApad 71)
http://www.icslp2004.org

-Interspeech (Eurospeech)-2005, Lisbon, Portugal,September 4-8, 2005
Chair: Isabel Trancoso, INESC ID Lisboa
http://www.interspeech2005.org

-Interspeech (ICSLP)-2006, Pittsburg, PA, USA
Chair: Richard M.Stern, Carnegie Mellon University,USA http://www.interspeech2006.org

-Interspeech (Eurospeech)-2007, Antwerp, Belgium , August 27-31,2007
Chair: Dirk van Compernolle, K.U.Leuven and Lou Boves, K.U.Nijmegen

top

FUTURE ISCA TUTORIAL AND RESEARCH WORKSHOP (ITRW)

-Statistical and Perceptual Audio Processing
October 2-3, 2004 Jeju, Korea
(see ISCApad 71)

- NOLISP'05: Non linear speech processing
April 19-22 April 2005, Barcelona, Spain
organized by Cost 277 Contact person: Marcos Faundez-Zanuy(see ISCApad 66)

-ISCA Workshop on Plasticity in Speech Perception
Organized by: UCL Centre for Human Communication, UCL, London, UK
co-sponsored by the Acoustical Society of America
15-17 June 2005; London, UK
INVITED SPEAKERS:
Anne Cutler, Max Planck Institute, Netherlands
James Flege, University of Alabama at Birmingham, USA
Patricia Kuhl, University of Washington, USA
David Moore, MRC Institute of Hearing Research, UK
Christophe Pallier, Inserm Cognitive Neuroimaging Unit, France
David Pisoni, Indiana University, USA
Franck Ramus, CNRS Cognitive and Psycholinguistic Sciences Laboratory, France
Stuart Rosen, UCL, UK
Jenny Saffran, University of Wisconsin - Madison, USA
Glenn Schellenberg, University of Toronto Mississauga, Canada
Sophie Scott, UCL, UK
http://www.psp2005.org.uk
Contact: Valerie Hazan

top

FORTHCOMING EVENTS SUPPORTED (but not organized) by ISCA

- International Workshop on Spoken Language Translation Evaluation campaign on spoken language translation
A satellite event of Interspeech-ICSLP 2004 September 30 - October 1, 2004, Kyoto, Japan (see ISCApad 71)

-4th International Symposium on Chinese Spoken Language Processing (ISCSLP'04)
December 16-18, 2004, Hong Kong, China

Pan European Voice Conference (PEVOC 6) http://www.pevoc6.com/home.htm
August 31 - September 3, 2005, London, UK

top

FUTURE SPEECH SCIENCE AND TECHNOLOGY EVENTS

- ACM Multimedia 2004
October 10-15, New York, NY USA
http://www.mm2004.org (see ISCApad68)

-6th International Conference on Multimodal Interfaces(ICMI'04)
October 13-15, 2004 The Atherton Hotel/State College, PA, USA http://www.icmiplace.org (see ISCApad70)

-Workshop MIDL 2004, Language and dialectal variety identification by humans and machines
organised by the MIDL consortium of the Modelling for the Identification of Languages project supported by the interdisciplinary STIC-SHS program of CNRS.
Partners are LIMSI-CNRS, ILPGA/LPP Paris3, TELECOM PARIS (ENST) and DGA, with the support of AFCP.
Place and date: Paris, 29-30 November 2004
http://www.limsi.fr/MIDL

Tenth Australian International Conference on Speech Science & Technology
Macquarie University, Sydney, 8th-10th December, 2004
For details: http://www.assta.org/sst/2004
Steve Cassidy,Conference Chair

-Conference on A Century of Experimental Phonetics: Its History and Development from Theodore Rosset to John Ohala
Universite Stendhal, Grenoble, France on February 24-25, 2005.
Conference room Jacques Cartier, Maison des Langues et de la Culture.
Contributions of 20 minutes or posters are welcome
Send a 200 word abstract at 100ans at icp.inpg.fr

Beyond HMM
IEICE/IPS/ATR workshop on statistical modeling approach for speech recognition
Kyoto, Japan, December 20, 2004
http://www.ieice.org/iss/sp/eng/workshop/beyondHMM.html

-ICASSP 2005
Philadelphia, PA, USA, March 19-23, 2005
http://www.icassp2005.com

-NODALIDA 2005
the 15th Nordic Conference of Computational Linguistics
Joensuu, Finland, May 20-21, 2005
http://phon.joensuu.fi/ nodalida2005/
1000 word abstract before January 31,2005 to be mailed to nodalida2005
Registration before March 31,2005
Contact: Stefan Werner

Deaf and Hearing Impaired Children Europe 2005
London 13-14 May 2005
Promoting joined-up working for Europe’s professionals with deaf children and their families.
The meeting is designed to bring together the wide range of professionals and voluntary organisations throughout Europe with an interest in childhood hearing impairment. There is a growing awareness of the need to work collaboratively across organisations and professional boundaries and with the users themselves if the goal of delivering high quality hearing services to all of Europe’s children who need them is to be achieved. This meeting will provide exciting opportunities to explore these challenges. It will also raise the profile of hearing impairment and an awareness of the needs of our children across Europe.
The meeting will be held under the auspices of NDCS (National Deaf Children’s Society) and RNID (Royal National Institute for Deaf People) and will be organised by The Ear Foundation. The meeting will be held in central London on 13/14 May 2005..
Registration form and further details from:
Brian Archbold
http://www.dhice.org

top