October 31, 2003


Welcome to the sixth  IEEE Signal Processing Society Speech Technical Committee (STC) newsletter.      As always we would like to invite contributions of events, publications, workshops, and career information to the newsletter.   Topics for issue number seven ...

New SPS Technical Committee  (Fred Mintzner)   

Election of New STC Members  (S. Parthasarathy and Rick Rose)   
Revised Paper Review Process for ICASSP 2004 in Montreal

Speech Communications Error Handling in Spoken Dialog Systems (Julia Hirschberg)

SWIM: Special Workshop in Maui Lectures by Masters in Speech Processing
2004 HLT/NAACL Human Language Technology Conference
Odessey 2004 ISCA Tutorial and Research Workshop on Speaker and Language Recognition
Special Session on Language Understanding and Communication in ITCC2004
Second International Conference of the Global WordNet Association
SCI 2004: 8th World Conference on Systemics, Cybernetics, and Informatics

Links to conferences and workshops organized by date  (Rick Rose)

New IEEE Signal Processing Society Technical Committee

Insofar as biomedical signal processing offers new and promising opportunities for signal processing research, the Board of Governors supports in principle the establishment of a new technical committee on biomedical signal processing. Furthermore, the Board of Governors authorizes creation of an ad hoc committee, chaired by the President-Elect, to develop a proposal for establishing a biomedical signal processing technical committee
As recommended by the Technical Directions Committee, the Board of Governors approves a change in the name of the Technical Committee now known as the Neural Networks for Signal Processing (NNSP) Technical Committee to the Machine Learning for Signal Processing (MLSP) Technical Committee.
back to top

Speech Technical Committee New Member Elections

In October, six new members were elected to the Speech Technical Committee.  They will each serve three year terms on the committee.  They will join the existing members who can be found on the STC web page    Perspective members are nominated by existing committee members in technology areas with retiring members, and the STC elects new members from these nominees.   Each member serves a three year term.   The new members are given here along with short descriptions of their background:
back to top

Michiel Bacchiani's  area of expertise is automatic speech recognition.  He received his PhD from Boston University with his dissertation work in pronunciation modeling for ASR.   He participated in the JHU ASR Workshop in the summer of 1996 and collaborated with researchers at the Advanced Telecommunication Research laboratories in Kyoto Japan through multiple internships over the period from 1994 to 1998.   In 1999, Dr. Bacchiani joined AT&T Labs Research and lead the design and development of the ASR component of the Scanmail voicemail navigation system.  Dr. Bacchiani is currently involved with developing algorithms for speech data mining. He has served as co-organizer of the ISCA Tutorial and Research Workshop on Prosody in Speech Recognition and Understanding (Prosody 2001). 
[new members]

William Byrne's  area of expertise is automatic speech recognition.  He is an Associate Research Professor with dual appointments at CLSP and Dept. of Electrical & Computer Engineering at JHU.  He is author/co-author of 60+ refereed articles in journals and conference proceedings.   He has made many contributions to ASR and statistical modeling for speech and language, specifically in acoustic adaptation, pronunciation modeling, discriminative training, novel decoding procedures, and statistical machine translation.  He is the organizer/co-chair of  ASRU '03.  He has also served as organizer/co-chair of PMLA '02 (satellite workshop of ICSLP), on the program committee of the NAACL Conference on Human Language Technologies (2003), as an invited panelist to the  NSF Symposium on Next Generation ASR (2003), and as guest editor for a special issue of Speech Communication on Pronunciation Modeling and Lexicon Adaptation.
 [new members]

Tatsuya Kawahara's area of expertise is speech recognition and understanding.  He is a Professor with Kyoto University and an Invited Researcher with ATR Spoken Language Translation Research Labs, Japan.  He was also a visiting researcher at AT&T Bell Labs during 1995-1996.  He received Ph.D degree in 1995 from Kyoto University.   He has published more than 100 technical papers covering speech recognition, confidence measures, and spoken dialogue systems.  He has served as publications/publicity chair for the  IEEE & ISCA workshop on Spontaneous Speech Processing and Recognition 2003 and as editorial board member for the  IEEE-TSAP Special Issue on Spontaneous Speech Processing.  He is now managing several big speech recognition/understanding projects in Japan including a free large vocabulary continuous speech recognition software project ( and spontaneous speech recognition project with Prof. Furui.
[new members]

Esther Levin's area of expertise speech recognition and spoken dialog systems.  She is a professor of Computer Science at the City College of New York.  She has had over 16 years of  experience in the areas of speech and language processing with Bell Labs, AT&T Labs, and Telelog.  She has an extensive publication history in the areas of speech recognition, machine learning, neural networks and spoken dialog systems.   She has served as member of several technical committees and as co-chair of the ASRU’93 workshop.
[new members]

Roberto Pieraccini's  area of expertise is speech recognition and spoken dialog systems.  He is with the IBM T.J. Watson Research Center in Yorktown Heights, NY.   He has work for Bell Labs, AT&T Labs, and most recently with SpeechWorks in New York City.  He has served as co-chair of the ASRU’93 workshop, as a previous member of the STC, and as member of several conference committees.
[new members]

Alan  Black's area of expertise is text-to-speech synthesis.  He is an associate professor with the Language Technologies Institute at Carnegie Mellon University.  He is Chief Scientist and co-founder of Cepstral, LLC a 14 person for-profit speech synthesis company in Pittsburgh and has authored over 75 refereed publications ranging from natural language processing to low level speech processing.  He is active in all areas of TTS from better language generation to new waveform synthesis techniques, has published in text processing, prosody, lexicons, unit selection synthesis, as well as uses of synthesis in spoken dialog systems and speech to speech translation. He has served as a principal author and lead developer of the open source Festival speech synthesis system and on the scientific committee for the IEEE Speech Synthesis Workshop.
[new members]

Jean-Pierre Martens' area of expertise is text-to-speech-syntheis.  He is a member of the Dept. of Electronics and Information Systems at the University of Gent in Belgium.  He has served on the program committee of the IEEE Signal Processing Symposium (1998, 2000) and on the organizing committee of IEEE ProRisc (1993-2000).  He has also served as chairman of steering committee of Spoken Dutch Corpus project and as organizer/chairman/member of scientific committees for numerous workshops/symposia.
[new members]

back to top

Revised Paper Review Process for ICASSP 2004 in Montreal

The paper review process for ICASSP 2004 in Montreal is about to begin.   The preliminary count of submitted papers in the speech area is 523 as compared to 526 papers submitted last year to ICASSP 2003.  The review procedure for this year's papers, however, will be significantly different from previous years.  In the December, 2002 edition of the STC newsletter there was a brief discussion of the review process for ICASSP 2003.  In that process, two STC members or SAP Transaction Associate Editors were assigned to review each submitted paper. The decisions made for each paper and the comments returned to the authors were based on the collective reviews of those two reviewers. 

This year, a team of close to 150 volunteer reviewers has been assembled to assist in the review process for ICASSP 2004 in Montreal.   The major aspect of the new process is the fact that their will be three reviews for each paper, and authors will be provided with a separate set of comments from each of three reviewers.   The volunteer reviewers will be listed on the ICASSP web page and in the printed proceedings as "reviewers" or part of the "scientific committee of  ICASSP".

The policy of having reviewing teams consisting of STC members and SAP Transactions Associate Editors (AEs) will continue as in previous ICASSPs. Each STC member will be paired with a colleague and assigned a set of papers in their area.   Based on last year's distribution, each pair
will receive approximately 27 papers. Each pair will also be given a target acceptance rate.  Each reviewing team will also be assigned a set of reviewers from the larger group of volunteers for their area.   The pair will split the papers in half.  Each STC member / AE will review all
their papers and also obtain 2 additional reviews for their papers from the set of volunteers.  After obtaining two additional reviews per paper, the pair will get together and merge the papers into a ranked list of papers.   Since an area may contain multiple pairs of reviewers, the committee will  meet and discuss the papers area by area, and resolve any conflicts/questions.
back to top

Call for Participation

Special Workshop in Maui (SWIM)

Lectures by Masters in Speech Processing

Maui, Hawaii, January 12-14, 2004

The Center for integrated acoustic infor
mation Research (CIAIR) at Nagoya University in Japan and IEEE Signal Processing Society is inviting you to participate in the Special Workshop in Maui (SWIM): Lectures by Masters in Speech Proceesing to take place at Maui Prince Hotel and Resort during January 12-14, 2004. This historic workshop is organized to bring together eight pioneers who have collectively shaped the field of speech processing. In this historic event, eight lectures will be given by:

In addition, there will be 32 invited and submitted poster presentations on four topics:


Hüseyin Abut, Chair, San Diego State University          Kazuya Takeda, Nagoya University, Japan

Richard V. Cox, AT&T Research                                   Yoh'ichi Tohkura, NTT Science & Core Research

John H.L. Hansen, University of Colorado                     Sadaoki Furui, Tokyo Institute of technology, Japan

Chin-Hui Lee, Georgia Institute of Technology             Shigeki Sagayama, University of Tokyo, Japan

B.H. “Fred” Juang,    Georgia Institute of Technology

Web:                             An IEEE Signal Processing Society Cooperating Workshop
back to top

    HLT/NAACL 2004

 Human Language Technology Conference of the

      North American Chapter of the Association for Computational Linguistics
May 2-7, 2004
Boston, Mass  USA

 HLT/NAACL 2004 continues the combination of the Human Language Technology Conferences (HLT) and North American Chapter of the American Association for Computational Linguistics (NAACL) Annual Meetings begun in 2003. This year's conference will include a special emphasis on bringing together researchers with common interests in computational linguistics, information retrieval, and speech research.  Human language technology incorporates a broad spectrum of disciplines working towards enabling computers to interact with humans using natural language, and providing improved services such as automatic translation, speech recognition, information retrieval, textsummarization, and information extraction.

HLT/NAACL 2004 will run from Sunday May 2 through Friday May 7.  The schedule will include full papers, late-breaking (short) papers, posters and demonstrations.  Invited speakers and panelists will discuss the state of today's human language technology.  The conference will also host tutorials and workshops, including a workshop organized by and devoted to graduate students.
The conference especially encourages submissions that discuss synergistic combinations of language technologies (e.g., Speech with Information Retrieval, Machine Translation with Speech, Question Answering with Natural Language Processing, etc.).  The conference will give special consideration to papers that address the topic of learning from and exploiting knowledge encoded in massive, unstructured collections like the Web.
The conference organization is overseen by a board representing the North American Chapter of the Association for Computational Linguistics (NAACL), ACM-SIGIR, the International Speech Communication Association (ISCA), and HLT funding agencies in North America.

back to top

Odyssey 2004

Call for papers

ISCA Tutorial and Research Workshop

on Speaker and Language Recognition 

May 31 - June 4, 2004

We invite you to 2004: A Speaker Odyssey, an ISCA Tutorial and Research
Workshop on speaker and language recognition held at the scenic Hotel Beatriz in Toledo, Spain.

In cooperation with the ISCA Speaker and Language Characterization SIG, the IEE, and technical cosponsorship by the IEEE Signal Processing Society, this workshop is hosted by The Universidad Politécnica de Madrid (UPM), School of Telecommunication Engineering (EUITT). The need for fast, efficient, accurate, and robust means of recognizing people and languages is of growing importance for commercial, forensic, and government applications. The aim of this workshop is to continue to foster interactions among researchers in speaker and language recognition as the successor of the 1994 Automatic Speaker Recognition Workshop (Martigny), the 1998 RLA2C Workshop (Avignon), and 2001: A Speaker Odyssey (Crete).

Feature Tracks and Topics

Feature tracks cover new techniques and forensic speaker recognition. Topics of interest include speaker verification, identification, segmentation and clustering; text-dependent and -independent speaker recognition; multispeaker training and detection; speaker characterization and adaptation; features for speaker recognition; robustness to channels, classification, and fusion in speaker recognition; speaker recognition corpora and evaluation; use of extended training data; speaker recognition with speech recognition; forensics, multimodality, and multimedia speaker recognition; language, dialect, and accent recognition; speaker synthesis and transformation; biometrics; human recognition; and commercial applications.

NIST SRE ‘04 Workshop Evaluation Track

The NIST Speaker Recognition Evaluation 2004 Workshop will be held during this week and after the Odyssey Workshop. Those wishing to evaluate their systems are encouraged to do so via the NIST SRE. The NIST Workshop is open to participants only. Please contact Dr. Alvin Martin to participate and see the NIST website for details:


Proposal due :: 15 January 2004
Notification of acceptance :: 27 February 2004
Final papers due :: 30 March 2004
Preliminary program :: 21 April 2004
Workshop :: 31 May – 4 June 2004

back to top

Special Session on

Language Understanding and Communication 

in the International Conference on Information Technology:

Coding and Computing

ITCC 2004

The Orleans, Las Vegas, Nevada, USA
April 5-7, 2004
Sponsored by IEEE computer Society
The huge tide of economic globalization provides to the Natural Language Processing and Understanding Technology with great opportunities as well as severe challenges. Since the first word was uttered, people have searched for ways to communicate their ideas, thoughts, and opinions to others.  Today, businesses are expanding their borders, becoming more global, as they seek out new markets and customer bases. With the pace of information transfer via fast PCs and networks, this goal becomes quite a challenge.  Language Understanding and Communication have become increasingly important in recent years due to rapid advancements in the field of speech recognition, natural language processing, Multi-lingual Multi-function Multi-media intelligent systems, and knowledge engineering. This session serves as an international forum for academic and industrial researchers and practitioners to discuss the application of new computer technologies to languages understanding and communication. The main objective of this session is to bring together researchers to exchange ideas and experience related to the fields. It will provide an international forum for an overview of the most recent trends in the active research fields and a common starting-point to tackle the most acute problems of information processing and information technology.

Topics of interest include but are not limited to the following:
Natural Language Understanding
Multi-lingual Multi-function Multi-media intelligent systems
Machine translation
Information retrieval
Spoken dialogue
Natural language interfaces
Information extraction
Text summarization
Adaptive interfaces
Terminology and ontologies
Lexical resources and corpora
Computer-assisted language learning
Speech modeling
Speech segmentation
Speech recognition
Text-to-speech synthesis
Document categorization
Natural language learning
WWW-based applications
E-commerce, education, entertainment
Knowledge representation
Text mining
Knowledge acquisition
Machine learning
Pattern recognition and automated scientific discovery
Soft computing and uncertainty management for data mining
Artificial intelligence

Authors are invited to submit papers describing in detail the original contribution on the topics. Interested authors should send a draft paper, formatted in the style ofIEEE Proceedings format, including keywords, and a cover page listing the name, affiliation, complete address, telephone, e-mail, and facsimile information for the corresponding author, before October 30, 2003, to the Session chair. Electronic submission (PostScript or PDF) is strongly encouraged.
The Proceedings will be published by IEEE Computer Society. A special issue of an international journal of Information is being planned consisting of selected papers from the special session. 
Paper Submission Deadline:    October 30, 2003
Acceptance Notification:    November 21, 2003
Camera-Ready Paper due (5 pages): December 19, 2003 
Conference: April 5-7, 2004
Professor Fuji Ren
Dept. of Information Science and Intelligent Systems
Faculty of Engineering, The University of Tokushima
2-1 Minamijosanjima, Tokushima, 770-8506, Japan
Tel/Fax: +81-88-656-9684 Fax: +81-88-656-6575
back to top


2nd International Conference of the Global WordNet Association

Masaryk University, Brno, Czech Republic

January, 20 - 23, 2004

The Global Wordnet Association is pleased to announce the Second International Conference of the Global WordNet Association (GWC'04).  The conference will be held at Masaryk University, Brno (Czech Republic), January, 20 - 23, 2004.
Details about the conference can be found on the conference website:

Details about the Association can be found on the GWA website:
A. Linguistics and WordNet:
        a. In depth analysis of Semantic Relations,
        b. Theoretical definitions of word meaning,
        c. Necessity and Completeness issues.
B. Architecture of WordNet:
        a. Language independent and language dependent components
C. Tools and Methods for Wordnet Development:
        a. User and Data entry interface, organization,
        b. Extending and enriching wordnets
D. WordNet as a lexical resource and component of NLP and MT:
        a. Word sense disambiguation using wordnet,
        b. Ontologies and WordNet,
        c. The Lexicon and WordNet
E. Applications of WordNet:
        a. Information Extraction and Retrieval,
        b. Document Structuring and Categorization,
        c. Automatic Hyperlinking
        d. Language Teaching,
        e. Psycholinguistic Applications
F. Standardization, distribution and availability of wordnets and
        wordnet tools.

 Keynote speaker:
    German Rigau (Basque Country University, Spain)
    Wordnet and Project Meaning
Conference program:
The conference program will include oral presentations and two special sessions - Poster session (for parallel poster presentations) and Demonstration session, where authors are invited to present actual projects, developed software or interesting material relevant to the topics of the conference. The demonstrations presented will not appear in the printed version of the Proceedings of GWC 2004. The authors of the demonstrations should provide an abstract, which will be included in the CD version of the Proceedings.  The Proceedings will be published by Masaryk University in both paper and CD format.
Important dates:
05-Nov-2003:    Final Papers
05-Dec-2003:     Deadline for Registration
20-23-Jan-2004:  Conference

Conference Chairs:
        Christiane Fellbaum and Piek Vossen
Local Organizing Chair:
        Karel Pala
Program Committee:
Pushpak Bhattacharya (IIT Mumbai, India)
Orhan Bilgin (Sabanci University, Istanbul, Turkey)
Paul Buitelaar (DFKI Saarbruecken, Germany)
Dan Cristea (University of Iasi, Romania)
Bento Carlos Dias da Silva (UNESP, Soa Paolo, Brasil)
Dominique Dutoit (University of Caen and Memodata, France)
Ales Horak (Masaryk University, Brno, Czech Republic)
Chu-Ren Huang (Academica Sinica, Taipei, Republic of China)
Adam Kilgarriff (University of Brighton, England)
Karin Kipper (University of Pennsylvania, USA)
Claudia Kunze (Tuebingen University, Germany)
Bernardo Magnini (IRST, Trento, Italy)
Palmira Marrafa (University of Lisbon, Portugal)
Simonetta Montemagni (ILC-CNR, Pisa, Italy)
Grace Ngai (Polytechnical University, Hong Kong)
Karel Pala (Masaryk University, Brno, Czech Republic)
German Rigau (Basque Country University, Spain)
Pavel Smrz (Masaryk University, Brno, Czech Republic)
Sofia Stamou (University of Patras, Greece)
Felisa Verdejo (U.N.E.D. Madrid, Spain)
Michael Zock (LIMSI-CNRS, Orsay, France)
back to top

                Speech Communications Call for Papers: 

Special Issue on

                Error Handling in Spoken Dialogue Systems

 Editors: Rolf Carlson, KTH    
Julia Hirschberg, Columbia University
Marc Swerts, University of Antwerp and Tilburg University

Spoken dialogue systems in real applications as well as research have attracted increased attention in recent years.  Given the limitations of current speech technologies, both in recognition and understanding and in generation, this interest in `real' systems has led to an increased awareness of the problems raised by system errors.  These errors may lead to increased confusion for both users and the system in the rest of the dialogue.  The need to devise better strategies for detecting and dealing with problems in human-machine dialogues has become critical for spoken dialogue systems.  After a workshop held in August 2003 on this topic (, we are now soliciting journal papers not only from workshop participants but also from other researchers for a special issue on "Error Handling in Spoken Dialogue Systems."
Submissions are invited on the following broad topic areas:
What can we learn from errors in human-human and wizard-of-Oz systems that will help us to handle error in human-machine dialogue systems?
How do systems detect when a dialogue is `going wrong'?  How do they define such conditions? What factors are the key contributors to and indicators of `bad' dialogues?
How do systems identify their own errors?  What are the most important causes of such errors, from the user side (e.g. out-of-vocabulary words, non-native accent or dialect, disfluencies, hyperarticulated speaking style, gender, age, lack of experience with the system) and from the system side (e.g. inappropriate prompts, poor confidence modeling, dialog modeling failures)?  How difficult is it to determine the causes of particular errors?
How can we predict which dialogues will be successful?  How should we define `success'?  What features can best predict it?  How can we evaluate system success?  How can we compare different error-handling strategies?
What mechanisms can be devised to allow systems to recover from error gracefully?  Can we develop adaptive strategies to identify patterns of error and respond accordingly?
What sorts of behavior do users exhibit when faced with system errors? Can these be taken into account in error handling?
What measures (better prompts, anticipation of likely error, better help information) can be taken to minimize potential errors?

Important Dates:
Submissions due: February 1, 2004
First Notification of Decisions: May 1, 2004
Submission requirements:
Papers should follow the submissions requirements for Speech
Communications submissions, as specified at
back to top

 Call for Papers

The 8th World Multi-Conference on


SCI 2004,
July 18 - 21, 2004, Orlando, Florida(USA)
The Rosen Plaza Hotel
 Program Committee Chair: William Lesso
General Chair: Nagib Callaos
Organizing Committee Chair: Belkis Sanchez
PROGRAM COMMITTEE: Integrated by (320) prestigious scholars/researchers
from 54 countries:
* Information Systems, Technologies and Applications
* Communication and Network Systems, Technologies and Applications
* Control Systems, Technologies and Applications
* Computer Science and Engineering
* Optical Systems, Technologies and Applications
* Image, Acoustic, Speech and Signal Processing
* Applications of Informatics and Cybernetics in Science and Engineering
* Systemics
Participation of both, researchers and practitioners is strongly
encouraged. Papers may be submitted on: research in science and
engineering, case studies drawn on professional practice and consulting,
and position papers based on large and rich experience gained through
executive/managerial practices and decision-making. For this reason, the
Program Committee is conformed according to the criteria given above.
Extended abstracts or paper drafts should be sent taking into account the
following Format:
1.  Major theme of the paper should be related to at least one of the major
themes given above.
2.  Paper title.
3.  Extended abstract of 500 to 1500 words and/or paper drafts of 2000 to
5000 words, in English.
4.  Author(s) and/or co-author(s) with names, addresses, telephone and fax
numbers, and e-mail addresses.
Extended abstracts or paper drafts should be sent via the conference web
site (, filling the respective form and
uploading the respective paper or extended abstract. If the conference web
site is not accessible for you, you can also make your submission by
e-mail, attaching it to the following e-mail addresses:, and
December 10th, 2003: Submission of extended abstracts (500-1500 words)
or paper drafts (2000-5000 words).
December 10th, 2003: Invited Sessions proposals. Acceptation of invited
session proposals will be done in about one week of its registration via
the respective conference web form, and final approval will be done after
the registration of at least five papers in the respective session.
January 30th, 2004: Acceptance notifications.
March 31st, 2004: Submission of camera-ready papers: hard copies and
electronic versions. 
Submitted papers will be sent to reviewers. Accepted papers, which should
not exceed six single-spaced typed pages, will be published by means of
paper and electronic proceedings.  SCI Journal will publish, at least, the best 10% of the papers presented at
the conference.

Based on past conferences experience, we suggest the following steps in
order to organize an invited session:
1)  Identify a special topic in the scope of SCI 2004, and the invited
session title.
2)  Fill the invited session organization form, provided in the conference
web page, and fill the respective form. If
by any reasons you are not able to access the page mentioned above, please,
try the following page:  If you don't have
access to the web, contact us via e-mail.
Invited sessions and symposia organizers with the best performance will be
co-editors of the proceedings volume where their session or symposia paper
were included.
Best Invited sessions and symposia organizers are candidates for invited
editors or co-editors of the SCI Journal special issue related to their
field of research interest.
[back to top]

Links to Upcoming Conferences and Workshops

(Organized by Date)

2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Mohonk Mountain House, New Paltz, New York, October 19-22, 2003

ASRU2003 Workshop on Automatic Speech Recognition and Understanding
St. Thomas, U.S. Virgin Islands, November, 2003

ITU Workshop on Standardization in Telecommunications for Motor Vehicles
Geneva, U.S. Switzerland, November 24-25, 2003

Workshop on Multimodal User Authentication
Santa Barbara, CA,  December 11-12, 2003

International Conference on Models and Analysis of Vocal Emissions for Biomedical Applications
Firenze, Italy,  December 10-12, 2003

SWIM: Special Workshop in Maui Lectures by Masters in Speech Processing
Maui, Hawaii, January 12-14, 2004

2nd International Conference of the Global WordNet Association
Brno, Czech Republic, January 20 -23, 2004

International Conference on Speech Prosody
Nara, Japan, March 23-26, 2004
mail to:

ICA2004 18th International Congress on Acoustics
Kyoto, Japan, April 4-9, 2004

ITCC04 - International Conference on Information Technology Coding and Computing
Las Vegas, Nevada, April 5-7, 2004

Boston, MA, May 2-7, 2004

Montreal, Canada, May 17-21, 2004

Odyssey2004 - ISCA Workshop on Speaker and Language Recognition
Toledo, Spain, May 31 - June 1, 2004

SCI2004 - 8th World Conference on Systemics, Cybernetics, and Informatics
Orlando, Florida, July 18 - 21, 2004

Vienna, Austria, Sept. 7-10, 2004

ICSLP2004 - INTERSPEECH 8th Biennial International Conference on Spoken Language Processing
Jeju Island, Korea, October 4-8, 2004

Philadelphia, Pennsylvania, May, 2005

EUROSPEECH 2005 9th European Conference on Speech Communication and Technology
Lisbon, Portugal, September 4-8, 2005

back to top