======================================================================= ISCApad number 41 October 12th, 2001 ======================================================================= Dear ISCA members, Welcome to ISCApad#41. It comes earlier in the month as promised. The regular date of issue will be the first week of each month. Do not forget to send the information you want to display for the members in time to be included (last week of each month). The purpose of ISCApad is to inform you about the life of your association and on the activities of the international speech science and technology community. TABLE OF CONTENTS ================= *ISCA News *Journals *Future events *Job openings * Appended detailed informations. ======================================================================== ISCA NEWS ========= - Organizers of ITRW workshops and ISCA and ISCA supported conferences are also invited to publish a short report after the event. - Proceedings of the ITRW and ISCA-conferences can be ordered at the secretariat of ISCA info@isca-speech.org. An order form is also available via the ISCA website. - Grants for Eurospeech 2001. Reports on their current activity and the benefits accrued from their participation in Eurospeech 2001 have been received from the following ISCA-grant recipients: Name, Affiliation, Country Genqing Wu, Tsinghua University, China Pengju Yan, Tsinghua University, China Kimiko Tsukada, Macquarie University ,Australia Annemie Van Hirtum, KULeuven, Belgium Koutras Athanasios, University of Patras, Greece Potamitis Ilyas, University of Patras, Greece Liu Yi, Hong Kong University, China Zaki Ahmed, Univerisite de Bordeaux, France Hyunsong Chung, UCL, UK Louloudis Dimitris, University of Patras, Greece Podhorski Adam, Technical University of Szeczecin, Poland Yablonsky Serge, St. Petersburg Transport University, Russia Huang Yinfei, Tsinghua University, China Odette Scharenborg, University of Nijmegen, The Netherlands Manuel Rodriguez, Hourcadette University of Los Andes Merida, Venezuela Maxine McCotter, University of Stirling, UK Julie Voce, UMIST, UK Xuejing Sun, Northwestern University, USA The full text of the above reports will be soon found at www.isca-speech.org , under "grants" We recommend the participants to ITRW and conferences to have a look at the same site at the conditions to benefit an ISCA grant. Details can be obtained by contacting (grant@isca-speech.org). -IEEE-MMSP01: organized in Cannes (with sunny weather) from Oct 3-5 with the support of ISCA was successful:130 participants coming from all over the world with a high participation of US speakers from the major US universities and Companies in spite of the flight restrictions due to September 11, 2001 terrorist actions. Aside the classical domains in Image, Video and Speech, emerging domains are Watermarking, Multimedia for Mobile Applications and Joint Audio-Visual Communication Mode. JOURNALS ======== - Computer Speech and Language Special Issue on New Computational Paradigms for Acoustic Modelling in Speech Recognition - Deadline extended to 31 October 2001 (see below) - Speech Communication Special Issue on Adaptation Methods in Speech Recognition. Submission deadline: March 1st, 2002. Guest editors: Dr Jean Claude Junqua, PSTL, S.Barbara and Prof. Chris Wellekens, Institut Eurecom, Sophia Antipolis (see below) - Eurasip Journal on Applied Signal Processing Special Issue on Joint Audio-Visual Speech Processing Submission deadline: 31 October, 2001 Guest Editors: Chalapathy Neti, Gerasimos Potamianos (IBM T.J. Watson Research Ctr), Juergen Luettin (Ascom Systec AG), Eric-Vatiokotis Bateson (ATR International Editorial Board Representative: Prof. Tsuhan Chen, CMU, U.S.A. (see below) FUTURE EVENTS ============= Publication policy: Hereunder, you will find very short announcements of future events. The full call for participation is appended to ISCApad only once and later referred to a previous issue of ISCApad. See also our Web pages (http://www.isca-speech.org) on conferences and workshops. - WI-2001 and IAT-2001 Joint Conference The First Asia-Pacific Conference on Web Intelligence The Second Asia-Pacific Conf. on Intelligent Agent Technology Maebashi TERRSA, Maebashi City, Japan, October 23-26, 2001 http://kis.maebashi-it.ac.jp/wi01/ http://kis.maebashi-it.ac.jp/iat01/ - International Workshop on Information Presentation and Natural Multimodal Dialogue Verona, Italy, 14-15 December 2001 http://i3p-class.itc.it/events/ipnmd2001.html (see ISCApad40) - InSTIL 2002 Symposium http://dbs.tay.ac.uk/instil Speech Technology in the Learning and Assistive Interface San Diego State University 25-26 March 2002 Advance Notice, Preliminary Registration and Call for Papers InSTIL is a Special Interest Group of CALICO, EUROCALL and ISCA and an affiliate of IALLT (see below) - ITRW on TEMPORAL INTEGRATION IN THE PERCEPTION OF SPEECH Aix-en-Provence, France, 8-10 April 2002 mailto:tips@lpl.univ-aix.fr http://www.lpl.univ-aix.fr/~tips (see ISCApad40) - The Fifth Symposium on Natural Language Processing 2002 + Oriental COCOSDA Workshop 2002 Hua Hin, Prachuapkirikhan, Thailand, 9-11 May 2002 http://kind.siit.tu.ac.th/snlp-o-cocosda2002/ or http://www.links.nectec.or.th/itech/snlp-o-cocosda2002/ (see ISCApad40) - ITRW on MULTI-MODAL DIALOGUE IN MOBILE ENVIRONMENTS(IDS'02) June 17-21, 2002 , Kloster Irsee, Germany http://www.sigmedia.org/ids02 (see below) - 7th International Workshop SPEECH AND COMPUTER (SPECOM'2002) 02-05 September 2002 St.-Petersburg, Russia E-mail: specom@mail.iias.spb.su http://www.spiiras.nw.ru/eng/structure/speech.htm (see below) - ITRW on Advanced ASR for Telecom Applications Palais des Papes, Avignon, France, 27-29 November 2002 Provisional website: http://smada.research.kpn.com (Click on Events and Activities) (see ISCApad40) - MMSP-02 (IEEE Signal Processing Society / ISCA) 2002 International Workshop on Multimedia Signal Processing St. Thomas, US Virgin Islands, December 9-11, 2002 http://mmsp02.njit.edu (see ISCApad40) JOB ANNOUNCEMENTS ================= - ASSISTANT PROFESSORSHIP IN SPEECH COMMUNICATION at GRAZ UNIVERSITY OF TECHNOLOGY, GRAZ, AUSTRIA (see below) - UNIVERSITY COLLEGE LONDON Department of Phonetics and Linguistics THREE RESEARCH FELLOW/RESEARCHER POSTS CURRENTLY AVAILABLE (see below) ======================================================================== APPENDED DETAILED INFORMATIONS ======================================================================== JOURNALS ======================================================================== COMPUTER SPEECH AND LANGUAGE SPECIAL ISSUE ON NEW COMPUTATIONAL PARADIGMS FOR ACOUSTIC MODELLING IN SPEECH RECOGNITION THIRD CALL FOR PAPERS - DEADLINE EXTENDED TO 31 OCTOBER 2001 AIM In recent years there has been an increased interest in approaches to speech and pattern processing that go beyond the conventional hidden Markov model (HMM) framework. This has been motivated by limitations of current systems both in their error performance and by the fact that current statistical modelling assumptions are inconsistent with that of natural speech signals. Researchers observe that current models are fragile in noise, are limited in their ability to handle pronunciation variation, and are costly for large vocabulary spontaneous speech transcription. They also point to limitations of HMMs in that they might not best represent the crucial non-stationary temporal behaviour of speech. The aim of this issue is to bring together up-to-date reviews of new computational techniques, including those that are being explored in other fields, with original work on extending and evaluating these techniques on speech recognition tasks. Papers are therefore solicited in the area of computational paradigms for acoustic modelling in speech recognition. Topics of interest include (but are not limited to): * Extensions and developments of HMMs, such as multi-stream models, factorial HMMs and graphical models in general * Computational models motivated by the need to accommodate structure in speech patterns which is potentially relevant for recognition but which is absent from the conventional HMM formalism (e.g. trajectories, linguistic features). * Computational models which accommodate novel feature extraction techniques that go beyond the traditional fixed frame-rate analyses. * Non-HMM-based approaches, or hybrid systems combining other classifiers with HMMs * Theoretical developments (of HMMs and extensions) which appear to have significant implications for speech processing. Manuscript submission Authors should send copies of their papers to one of the guest editors, Martin Russell or Jeff Bilmes, by the extended deadline of 31 October 2001. Authors should follow the CSL guidelines for paper submission; electronic submissions are encouraged preferably in postscript or Adobe pdf. Guest Editors Professor Martin J Russell, School of Electronic and Electrical Engineering, The University of Birmingham, Edgbaston, Birminhgham B15 2TT, U.K. E-mail: m.j.russell@bham.ac.uk Tel: +44 (0) 121 414 3093; Fax: +44 (0) 121 414 4291 or Jeff A Bilmes, Department of Electrical Engineering, University of Washington, 418 EE/CSE, Box 352500, Seattle, WA 98195-2500, USA. E-mail: bilmes@ee.washington.edu Phone (206) 543-2150. ======================================================================== SPEECH COMMUNICATION Special Issue on Adaptation Methods in Speech Recognition. Papers are invited on the following topics: -speaker adaptation -channel and noise compensation -task adaptation -lexicon adaptation -language adaptation Guest editors: Dr Jean Claude Junqua, PSTL, S.Barbara (USA) and Prof.Chris Wellekens, Institut Eurecom, Sophia Antipolis (F) Deadline for submission: March 1st 2002. Guidelines to the authors: see any recent issue of Speech Communication. Send papers to: Professor Chris J.Wellekens, Institut Eurecom, 2229 route des Cretes, BP 193, F-06904 Sophia Antipolis, France. welleken@eurecom.fr ======================================================================== EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING Special Issue on Joint Audio-Visual Speech Processing The aim of this special issue is to highlight innovative research in joint audio and video signal processing and its application to improved practical speech recognition and synthesis. Prospective papers should be unpublished and present solid research work offering innovative contributions either from a methodological or application point of view. Topics of interest include (but are not limited to): * Audio-visual speech recognition * Audio-visual speaker recognition * Audio-visual speaker change detection * Audio-visual emotion analysis * Audio-visual speaker localization * Audio-visual speech synthesis * Face detection, tracking and region of interest extraction. * Visual speech processing * Fusion methodologies and source reliability estimation Prospective authors should follow the EURASIP JASP manuscript format (see http://asp.hindawi.com/) and submit an electronic copy of their complete manuscript through the EURASIP JASP's web submission system at http://asp.hindawi.com/, according to the following timetable. Manuscript Due: Oct 31, 2001 Acceptance Notification: March 31, 2002 Final Manuscript Due: May 15, 2002 Publication Date: Third Quarter, 2002 Guest Editors: Chalapathy Neti, Gerasimos Potamianos IBM T.J. Watson Research Ctr Rte 134, Yorktown Heights, NY 10598 U.S.A {cneti,gpotam}@us.ibm.com Juergen Luettin Ascom Systec AG Gewerbepark, CH-5506 Maegenwil SWITZERLAND juergen.luettin@ascom.ch Eric-Vatiokotis Bateson ATR International 2-2-2 Hikaridai Kyoto 619-0288, JAPAN bateson@isd.atr.co.jp Editorial Board Representative: Prof. Tsuhan Chen, Carnegie Mellon University, U.S.A. ======================================================================== FUTURE EVENTS ======================================================================== Second InSTIL 2002 Symposium San Diego State University 25-26 March 2002 InSTIL is a non-profit association and all net proceeds will be used to assist the activities of the SIG for the benefit of the research community. The theme of the Symposium --------------------------- Building on the original theme of InSTIL 2000, the Symposium acknowledges the obvious, namely that many advances in the integration of ST in CALL have been driven by concerns outside CALL. The theme is also sufficiently broad to cover all the areas of interest of InSTIL members, in other words speech recognition, synthesis, analysis, manipulation, visualization, animation, talking heads, etc.... Work related to any area of Speech Therapy which impacts on Education and Learning is also welcome. Informal enquiries may be made at the point of sending an abstract. We intend the symposium to be an interdisciplinary meeting point for researchers and practitioners. Contributions relating to basic research, method development, system design and evaluation are welcome. Format of the event ------------------- This will be a full symposium open to presenters or simply members of the CALL or Speech Community not yet actively involved in the field. As in Dundee, we will run one day Training Seminars in parrallel. Each thematic session will be introduced by a tutorial presentation by an invited expert. All papers will be presented in plenary sessions with time for demonstration and discussion. Other contributions will be presented in poster sessions followed by a plenary discussion. A small exhibition is planned both for commercial systems and research prototypes. The Symposium will also see the first presentation on American soil of the poster exhibition entitled "An Illustrated History of Speech Technology in Language Learning". Proceedings ----------- The Symposium Contributions and, where possible Courseware Demos, will be published in a CD-ROM which will be available to participants at the time of the Symposium. Subsequently, revised contributions will be published in an edited volume or in the InSTIL Journal. Registration Fees ----------------- Symposium, (including CD-ROM proceeding):US$ 150 (Early Bird). Late registration: US$ 175. Important dates --------------- 31/10/2001 Preliminary registration and deadline for submission of title and abstract. PLEASE SEND YOUR 200 TO 400 ABSTRACT TO P.DELCLOQUE@MSEC.AC.UK. Figures and pictures should be sent as separate attachments. 30/11/2001 Notification of acceptance, instructions for authors will be sent before December 7th, 31/01/2002 Deadline for early registration and for sending 4 pages of A4 contribution. International Scientific Committee ---------------------------------- Monique Adriaen Nick Campbell Michael Cohen Ronald Cole Philippe Delcloque Rodolfo Delmonte Kathleen Egan Aline Germain-Rutherford Goh Kawai Eric Keller Ton Koet Steve Larocca Mary-Ann Lyman-Hager Philippe Martin Dominic Massaro Brigitte Zellner-Keller Organizing Committee -------------------- Philippe Delcloque Mary-Ann Lyman-Hager Payment ------- Payment by credit card or bank transfer to or by cheque in dollars. This will be dealt with from November 2001. Participation can be guaranteed only after payment is received. For more information, contact P.DELCLOQUE@MSEC.AC.UK . http://www.instil.org/ ======================================================================== ITRW on MULTI-MODAL DIALOGUE IN MOBILE ENVIRONMENTS (IDS'02) June 17 through June 21, 2002 Kloster Irsee (Southern Germany) http://www.sigmedia.org/ids02 The workshop will cover all aspects of spoken, but also multi-modal interaction in mobile environments and will emphasise design issues and applications. Moreover, the workshop will focus on research and results, give information on tools and run prototype demonstrators of the expected future application. The latest developments within the area of multi-modal dialogue in mobile environments will be discussed among researchers and industrialists active in the area. The workshop is organised as a collaboration between the University of Southern Denmark, DaimlerChrysler AG and the German Research Center for Artificial Intelligence (DFKI). Laila Dybkjær Natural Interactive Systems Laboratory University of Southern Denmark Denmark laila@nis.sdu.dk Paul Heisterkamp, Wolfgang Minker Speech Understanding Systems DaimlerChrysler AG Germany paul.heisterkamp@daimlerchrysler.com wolfgang.minker@daimlerchrysler.com Elisabeth Andre University of Augsburg Germany andre@informatik.uni-augsburg.de WORKSHOP THEMES The workshop focuses on research issues, applications and tools concerned with the following interdisciplinary topics which are all part of general research and development of the main areas of multi-modal dialogue in mobile environments. Papers may discuss theories, applications, evaluation, limitations, general tools and techniques. Discussion papers that critically evaluate approaches or processing strategies and prototype demonstrations are especially welcome. Speech and its Interpretation -> robust algorithms for automatic speech recognition and understanding in mobile environments -> spontaneous, conversational and disfluent speech -> spoken dialogue processing -> speech and language modelling -> microphone and processing devices Design Issues -> dialogue control -> situation awareness -> pro-active dialogue -> geo-position awareness -> spatial reference (input and output) -> attention raising -> multi-modality and safety considerations -> ergonomics and usability Applications -> applications for mobile environments -> co-ordination of multiple applications -> conflict description and solving -> industrial applications and commercialised products Dialogue Systems Architecture -> integration of local and server-based dialogue -> technical integration management Evaluation of Dialogue Strategies and Systems -> strategies and paradigms especially adapted to mobile environments SCIENTIFIC PROGRAMME The format of the workshop will be a non-overlapping mixture of oral and poster sessions. A number of tutorial lectures will be given by internationally recognised experts from the area of multi-modal dialogue systems. All poster sessions will be opened by an oral summary by the session chair. A number of poster sessions will be succeeded by a discussion session focussing on the subject of the session. It is our belief that this general format will ensure a lively and valuable workshop. The organisers would like to encourage researchers and industrialists to take the opportunity to bring their applications as well as their demonstrator prototypes and design tools for demonstration to the workshop. If sufficient interest is shown, a special demonstrator/poster session will be organised and followed by a discussion session. A booklet containing the abstracts of the accepted papers and the proceedings from the workshop will be available The official language of the workshop is English. At the opening of the workshop hardcopies of the abstracts and proceedings on CD-ROM will be available. An edition of Lecture Notes in Computer Science collecting the full-paper versions presented at the workshop is planned. TIMING AND DATES - -> February 15, 2002: Deadline for submission of summary - -> April 1, 2002: Notification of acceptance/rejection - -> May 15, 2002: Deadline for submission of accepted paper and advance registration - -> June 7, 2002: Final programme available on web - -> June 17 - 21, 2002: Workshop CONTACT INFORMATION Comments on IDS'02 Workshop to: ids02-info@sigdial.org Comments on webpages to: sigmedia@dfki.de To subscribe to this list: majordomo@sigdial.org with the body text: subscribe ids02-info ======================================================================== 7th International Workshop SPEECH AND COMPUTER (SPECOM'2002) 02-05 September 2002 St.-Petersburg, Russia Organized by St-Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS) The workshop is aimed to discuss the ROBUST SPEECH UNDERSTANDING (RSU) problem and some closely connected aspects. GENERAL CHAIR: Rafael M. Yusupov, SPIIRAS, St-Petersburg, Russia ORGANIZING COMMITTEE CHAIR: Yuri Kosarev, SPIIRAS, Russia DEADLINE for abstract submission 15 April 2002 CONTACTS: Dr.Y.Kosarev E-mail: specom@mail.iias.spb.su http://www.spiiras.nw.ru/eng/structure/speech.htm ======================================================================== JOB ANNOUNCEMENTS ======================================================================== ASSISTANT PROFESSORSHIP IN SPEECH COMMUNICATION at GRAZ UNIVERSITY OF TECHNOLOGY, GRAZ, AUSTRIA Graz University of Technology (www.tugraz.at) has recently established a Signal Processing and Speech Communication Laboratory led by Prof. Gernot Kubin, see www.inw.tugraz.at/spsc. Research and teaching activities focus on: * Theory and Algorithms for Nonlinear Signal Processing * Applications of Signal Processing for the Internet * Speech Communication The diversity of topics calls for a high degree of interaction across disciplines and with several industrial research partners. We serve students from three different study programs, i.e., electrical engineering, telematics, and audio engineering. The group has an immediate opening for an Assistant Professor of Speech Communication ("Universitaetsassistent" according to the new Austrian university law). A strong background in speech signal processing and/or spoken language engineering as well as a doctorate in a relevant discipline are required. Prior experience as a post-doctoral researcher is a plus, preferentially in speech recognition/dialogue systems research, while all specializations within speech communication are welcome. Successful candidates are expected to further develop their scientific career through top-level research, to develop and teach lecture courses and labs in speech signal processing and spoken language engineering, to supervise student projects, and to initiate and direct research projects funded from public sources or through industrial cooperations. Applicants who want to work towards the "habilitation" degree are highly welcome and will be actively supported. Fluency in English or German is a must. The gross yearly all-inclusive salary is EUR 43,600 with a teaching commitment equivalent to 6 ECTS points per semester. The contract extends over a duration of 6 years. Graz University of Technology is an equal opportunity employer. The laboratory is housed in the award-winning architecture of Riegler & Riewe. Contemporary art and culture are strong in Graz (www.graztourism.at) which is the second largest city of Austria located in the south-eastern province of Styria at the cross-roads of major continental-European cultures. It enjoys a vibrant student life with three universities and excellent leisure time opportunities in the larger Alps-Adriatic region. UNESCO has included the historic centre of Graz in its World Heritage List and Graz will be the Cultural Capital of Europe in 2003. Applications with a detailed CV, covering research, teaching, and project management experience, copies of relevant publications and two letters of reference are due by October 15, 2001. For further information, please contact Prof. Gernot Kubin at +43-699-10721996, g.kubin@ieee.org, ======================================================================== UNIVERSITY COLLEGE LONDON Department of Phonetics and Linguistics THREE RESEARCH FELLOW/RESEARCHER POSTS CURRENTLY AVAILABLE Project 1: Synthetic talking face controlled by speech (2 posts) This project, with partners in Sweden, the Netherlands and the UK aims to provide hearing-impaired people with lipreading cues derived from acoustic speech. Posts are available for a Researcher (ref. 1) with skills in speech perception and a Research Fellow (ref. 2) with experience in speech recognition. The Researcher post is 0.8 FTE with a starting salary of GBP 21,620 pro rata and is available from 1 November 2001 to 30 September 2004. The Research Fellow post has a starting salary from GBP 21,620 to GBP 26,327 per annum depending on qualifications. This full-time post is for between 18 to 24 months depending on salary. Project 2: Use of auditory-visual speech in 2nd language training (1 post) This EPSRC-funded post (ref. 3) is available for 20 months. The main responsibility will be to carry out trials of a computer-based training system for Spanish learners of English. A background in speech perception and in phonetics or phonology at Master's or PhD level is essential. Conversational Spanish and an interest in computer-assisted learning are desirable. Starting salary between GBP 21,620 and GBP 26,327 per annum. Send requests for further information and applications including the names of two academic referees and a CV to Dr A Faulkner, Department of Phonetics and Linguistics, 4 Stephenson Way, London NW1 2HE (or email to andyf@phon.ucl.ac.uk). Tel. 020 7679 7408/7401. Closing dates are Monday, 15 October 2001 for post 1 and Wednesday, 31 October 2001 for posts 2 and 3. All salaries include a London Allowance. Further particulars can be found at http://www.phon.ucl.ac.uk/jobs/ ======================================================================== All additional information at the ISCA web-site: http://www.isca-speech.org The ISCA secretariat can be contacted at: info@isca-speech.org Requests concerning membership, Speech Communication and ordering Proceedings should be forwarded to the Secretariat. For message distribution at ISCA list contact: public@isca-speech.org Short messages will be forwarded on a monthly scheme basis to all ISCA members. ========================================================================