Subject: ISCApad #20 Date: Thu, 30 Dec 1999 12:05:52 GMT From: Isabel Trancoso To: isca_members@isca-speech.org ============================================================================ ISCApad number 20 December 30, 1999 ============================================================================ Dear ISCA members, Welcome to ISCApad #20 - the last one in 1999. This has been a truly momentous year for our association, with new SIGs, numerous workshops, Eurospeech'99 and, of course, the change from ESCA to ISCA. Our first message in 2000 will include the results of the elections for the extended ISCA Board. In the meantime, here are other relevant announcements (in chronological order of forthcoming events): - IEE seminar: State-of-the-art in Speech Synthesis, London, UK, April 13, 2000 http://www.iee.org.uk/Events/e13apr00.htm - XLDB - 1st. Int'l Workshop on Very Large Telephone Speech Databases, Athens, Greece (a satellite event to LREC 2000) May 29th, 2000 http://www.speechdat.org/XLDB/XLDB.html - NORSIG2000, Vildmarkshotellet, Sweden, June 13-15, 2000 http://www.es.isy.liu.se/norsig2000/ - Invited session on AVSP at SCI'2000, Orlando, Florida (USA), July 23-26, 2000 http://www.iiis.org/isas/ - InSTIL 2000, University of Abertay Dundee, Scotland August 29-30, 2000 http://dbs.tay.ac.uk/instil2000/ - ITRW ASR2000 - International Workshop on Automatic Speech Recognition: Challenges for the Next Millennium, Paris, France September 18-20 http://www-tlp.limsi.fr/asr2000 - Prosody 2000: speech recognition and synthesis, Krakow, Poland October 2-5, 2000 http://ptfon.wmid.amu.edu.pl - Workshop on Multi-Lingual Speech Communication, Kyoto, Japan October 11-13, 2000 http://www.msc2000.atr.co.jp/MSC/ ISCA greetings for the New Year, Isabel Trancoso ============================================================================ IEE seminar: STATE-OF-THE-ART IN SPEECH SYNTHESIS http://www.iee.org.uk/Events/e13apr00.htm Thursday, 13 April 2000 to be held at Savoy Place, London Organized by: Professional Group E5 (Signal Processing), in association with Professional Group A8 (Speech and Language Engineering), ISCA SynSIG (the Speech Synthesis special interest group of the International Speech Communication Association) and the Institute of Acoustics. The quality of speech synthesis systems has improved drastically over the last few years. However there are still many research issues which remain unresolved. Improvements are still necessary in the naturalness, flexibility and the intelligibility of the synthesized speech. This colloquium aims to bring together researchers active in speech synthesis research - including (but not limited to) - speech synthesis techniques: articulatory synthesis, formant synthesis, concatenative synthesis - signal processing: modelling techniques (Harmonic, TD-PSOLA), speech unit selection, segment concatenation, voice transformation - database development: automatic segmentation, special purpose signal editors, specialised recording equipment (EGG, prompting), validation techniques - prosody: labelling strategies, automatic labelling, automatic prediction/modelling, emotional speech - multilinguality: language-independent methodologies for synthesis - assessment of synthesis systems - speech synthesis applications [If there is sufficient interest, a Web site for the colloquium will be set up containing example audio files of systems demonstrated at the colloquium] If you are interested in making a technical contribution to this colloquium, please submit a 300-word abstract (electronically) by Friday, 4 February 2000 to : Dr Justin Fackrell Corporate Research and Development Division Lernout & Hauspie Speech Products NV Flanders Language Valley 50 B-8900 Ieper BELGIUM Email: justin.fackrell@lhs.be ============================================================================ 1st Call for Papers XLDB - 1st. Int'l Workshop on Very Large Telephone Speech Databases a satellite event to LREC 2000 in Athens May 29th, 2000 supported by ELRA and ISCA http://www.speechdat.org/XLDB/XLDB.html In recent years, several very large telephone speech databases have become available to the SLP community. It is now time to critically assess the quality and utility of these databases, both for Speech Technology and Speech Research. The XL-DB workshop thus focuses on three aspects: * Collection, Annotation and Access * Research and Gaining new Knowledge * Application and Service Development Contributions to these areas are highly welcome. The web-site features a registration form for the XLDB-mailing list. Take advantage of this mailing list to receive the most up-to-date information on this workshop! Important Dates Abstracts due: 28. 01. 2000, Notification of acceptance : 18. 02. 2000 Note that all contributions must be made electronically, either by e-mail or the submission form on the XLDB web-site. ============================================================================ NORSIG 2000 http://www.es.isy.liu.se/norsig2000/ Final call for Papers 2000 IEEE Nordic Signal Processing Symposium will be held at Vildmarkshotellet which is situated close to Norrkoping, Sweden. The symposium is the fourth in a series of biannual gathering of researchers specializing in signal processing and their applications. NORSIG 2000 will be devoted to all aspects of theory, design, implementation and applications of signal processing. Papers describing new research are invited for technical sessions within - but not limited to - the following topics: - Linear, non-linear and adaptive signal processing - Statistical signal and array processing - Neural networks for signal and information processing - Image analysis and multidimensional signal processing - Audio and speech processing - Medical image and signal processing - Signal processing for wireless communications - Mixed signal processing - Multimedia signal and information processing - Filters and filtering - Implementation of signal processing algorithms - Demonstration of systems for applied signal processing - Other (Specify) Schedule Submission of 2-3 page summary: February 1, 2000 Notification of acceptance: March 1, 2000 Submission of final paper: April 25, 2000 NORSIG 2000 Symposium: June 13 - 15, 2000 The final paper is restricted to four pages. Refer to the submission guidelines at http://www.es.isy.liu.se/norsig2000/ for more information on submission and acceptable formats. Contact Prof. Lars Wanhammar NORSIG2000 Dept of Electrical Engineering Linkoping University SE-581 83 LINKOPING, SWEDEN URL: http://www.es.isy.liu.se/norsig2000 e-mail: norsig2000@isy.liu.se fax: +46-13-139282 ============================================================================ INVITED SESSION ON AVSP An Invited Session of the 4th World Multiconference on Systemics, Cybernetics and Informatics (SCI'2000) on Audio-Visual Speech Processing (AVSP), i. e. recognition, synthesis, coding and related areas, is to be held on July 23-26, 2000 in Orlando, Florida (USA). It aims to promote research in our interdisciplinary scientific area: Visual and Audio-Visual Speech. Take this opportunity to meet and to discuss the progress we all expect in our fascinating interdisciplinary challenge! There will be oral presentations of papers describing ongoing work in our 'Audio-Visual Speech' community. Best papers will be selected for awards and recommended for journal publications. Multiple author books will be published by the International Institute of Informatics and Systemics, based on the best invited sessions. If you are interested in participating in this AVSP Session of SCI'2000, you should send extended abstracts (500 to 1500 words in English) by 20th of January 2000. These should be sent as text attachments to rogozan@lium.univ-lemans.fr For further information please see the Conference web page: http://www.iiis.org/isas/ or contact Dr Alexandrina ROGOZAN Laboratoire d'Informatique de l'Universite du Maine 72085 Le Mans Cedex 9, France Email: rogozan@lium.univ-lemans.fr FAX: + 33 2 43 83 38 68 ============================================================================ InSTIL 2000 - CALL FOR PAPERS http://dbs.tay.ac.uk/instil2000/ August 29-30, 2000 University of Abertay Dundee, Scotland InSTIL 2000, the first symposium organised by the InSTIL group "Integrating Speech Technology in (Language) Learning" will be held on 29 August to 30 August 2000 at the University of Abertay Dundee, Scotland. Keynote Speakers include Ron Cole, Eric Keller, Dominic Massaro and Brigitte Zellner, one (or possibly two) more will be announced in January 2000. The two-day Symposium is supported by the InSTIL SIG three parent associations, CALICO, EUROCALL and ISCA. It builds on the excellence and excitement of the ISCA workshop STiLL 98, held in Marholmen, Sweden. The Symposium runs as a satellite event to the CALL Conference, EUROCALL 2000 (31/8 to 2/9/2000). Please note that no identical paper will be allowed to be presented in both events. If submitting to both, please indicate your preference in terms of inclusion. Title: Integrating Speech Technology in the (Language) Learning and Assistive Interface Sub-themes: In the selection process, preference will be given to submissions for Papers, Show & Tell Demonstrations and Posters (please specify) related to at least one of the following areas: 1) Any of the areas covered by STiLL 98. (Speech Technology in Language Learning). 2) Any of the areas of interest to the InSTIL group shown on our Web Site at http://dbs.tay.ac.uk/instil/ including the re-education of disability and its impact on the learning interface. Submissions of 200 to 400 words (maximum) should be sent before 29 February 2000 to the following address, preferably by e-mail: Nick Annan, InSTIL 2000, Division of Languages, Dundee Business School University of Abertay Dundee, Bell Street, DUNDEE DD1 1HG Tel: (Philippe Delcloque) 44- (0)1382-308 460 Fax: 44 (0)1382- (0)1382-308 400 (marked for Nick's attention) Email: n.annan@tay.ac.uk All submissions will be acknowledged by e-mail, numbered sequentially and sent to the Chair of the Scientific Committee, Rodolfo Delmonte for distribution to the Scientific Panel. The Scientific Panel will include at least the following names: Reiko Akahane-Yamada, Jared Bernstein, Ron Cole, Rodolfo Delmonte, (Chair of Panel and co-organiser of Symposium), Kathleen Egan, Maxine Eskenazi, Aline Germain, Ton Koet, Melissa Holland, Steve La Rocca, Philippe Martin, Dominic Massaro, Patti Price, Andrew Sapeluk and Brigitte Zellner. Submissions will be refereed on a double blind basis using a criterion-referencing system, details of which can be found at the conference website. All applicants will be notified of the Panel's decision by 31 March 2000. The symposium, which will also include several free hands-on workshops and a separate one-day training event, will be open to presenters as well as parties simply interested in the field. More details of the Symposium will be given on the InSTIL 2000 Web Site. The Organisation Committee: Nick Annan, Ines Carradice, Philippe Delcloque, Rodolfo Delmonte, Ton Koet. ============================================================================ ASR2000 ISCA ITRW International Workshop on Automatic Speech Recognition: Challenges for the Next Millennium Paris, France September 18-20 Call for Papers http://www-tlp.limsi.fr/asr2000 email: asr2000@limsi.fr Organized by the Spoken Language Processing Group of the LIMSI-CNRS with the sponsorship from ISCA and the GFCP/SFA. The last decade has seen impressive advances in the capability and performance of speech recognizers. However, despite the extent of progress and the emergence of commercially available products, there are many outstanding research issues that need to be addressed before the core speech recognition problem can be considered solved. Speech recognizers remain extremely sensitive to the acoustic and the linguistic properties of the data, and in particular to mismatches between training conditions and conditions of real use. Also porting to a new language or task requires substantial investment of time and) money, and requires the knowledge of speech recognition experts. Some of the challenges for speech recognition research are to address these problems by investigating robust generic technology, low-cost development strategies, portability and adaptability. Scope: The ISCA ASR-2000 workshop will focus on core speech recognition technology and in particular on recent advances and prospective work. Topics of interest include, but are not limited to, the following: - Robust generic technology - Acoustic modeling and adaptation - Language modeling and adaptation - Lexical and phonological modeling - Efficient decoding - Portability and low-cost system development) - Modeling of speaking styles and non-native speech - Enhancing the recognizer output (confidence measures, punctuation, audio segmentation, speaker and channel information, ...) Prospective authors are invited to electronically submit a full paper (4-8 pages) for review (starting April 1st, 2000). Important dates: Electronic submission of draft papers: May 1, 2000 Notification of acceptance: June 15 Early registration: August 1 Final papers due: August 1 Workshop: September 18-20 ============================================================================ Prosody 2000: speech recognition and synthesis Web site: http://ptfon.wmid.amu.edu.pl Workshop Kraksw, Poland 2-5 October, 2000 CALL FOR PAPERS & APPLICATION DEMONSTRATIONS Organized by: Polish Phonetic Association Deutsche Gesellschaft fur Sprachwissenschaft (Sektion Computerlinguistik) In collaboration with: The International Speech Communication Association - ISCA The scope of the workshop will range from the traditional processing of suprasegmentals to the rapidly growing field of multimodal applications in which prosody plays a role. The conference is of interest to several scientific communities, including Human Language Technologies, Linguistics, Phonetics, Phoniatrics and Musicology. Prosody 2000 will be a forum for cross-discipline initiatives and innovative applications, presentation of scientific progress in the field, demonstrations of prototypes based on this research and of the innovative multimodal products now appearing on the market. The Call for Papers is addressed to researchers engaged in either academic or industrial research. In order to support the multi-disciplinary goal of the conference, the international organising committee includes representatives of the different scientific communities. Details of the submission and registration procedures as well as general workshop information can be found on the above web site. ============================================================================ Workshop on Multi-Lingual Speech Communication October 11-13, 2000 Kyoto, Japan [http://www.msc2000.atr.co.jp/MSC/] Supported by ATR, ISCA, IEEE SP Society, NLP, and other domestic academic societies. CALL FOR PAPERS This workshop is planned for researchers and system developers to discuss multi-lingual information processing in speech commu- nication technologies. It will be valuable to share knowledge and experiences in multi-lingual information processing to cope with the increasing interest in applying speech and language technologies to new languages and the inherent demands in trans- lingual information processing technologies such as speech trans- lation, language independent man-machine dialogue and information mining. The workshop will cover all scientific and engineering topics in speech communication technology with multi-lingual as- pects. It will encompass not only speech technologies but also language technologies and human interface design. We highly ap- preciate the attendance of researchers and developers in various fields for flexible thinking about new approaches to the current problems and new applications for global and individual communi- cation. Popular topics: Multi-lingual speech technologies: * Acoustic modeling for speech recognition * Language modeling for speech recognition and understanding * Speech synthesis * Prosody modeling Speech translation technologies: * System architecture * Spoken language translation * Intermediate information expression * System evaluation Spoken dialogue technologies: * Man-machine interface design * Dialogue modeling (These topics are just currently popular topics. New technologies and applications are welcome.) Important Dates: April 25, 2000 Deadline for submission of summary June 1, 2000 Notification of acceptance/rejection July 31, 2000 Deadline for submission of camera-ready paper and advance registration October 11-13, 2000 Workshop Organizers: Yoshinori Sagisaka (ATR, Japan) Alex Waibel (CMU, USA and University of Karlsruhe, Germany) Victor Zue (MIT, USA) International Scientific Committee: Kiyoaki Aikawa (NTT, Japan) Hiyan Alshawi (AT&T, USA) Christian Boitet (GETA, CLIPS, IMAG, France) Wen Gao (Institute of Computing Technology, China) Akira Kurematsu (University Electro-Communications, Japan) Gianni Lazzari (ITC-IRST, Italy) Kai-fu Lee (Microsoft, China) Satoshi Nakamura (Nara Institute of Science and Technology, Japan) Patti Price (SRI, USA) Salim Roukos (IBM, USA) Frank K. Soong (Lucent, USA) Keh-Yih Su (Behavior Design Corporation, Taiwan) Takao Watanabe (NEC, JAPAN) Cliff Weinstein (MIT, USA) Dekai Wu (HKUST, China) Jae-Woo Yang (ETRI, Korea) Secretaries: Toshiyuki Takezawa and Tomoko Matsui Address: ATR, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0288 Japan Tel: +81 774 95 1352/1387 FAX: +81 774 95 1308 E-mail: sec@msc2000.atr.co.jp ============================================================================ 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: publicity@isca-speech.org Short messages will be forwarded on a monthly scheme basis to all ISCA members. =============================================================================