IEEE SPEECH TECHNICAL COMMITTEE NEWSLETTER

June 9, 2005

INTRODUCTION:

Welcome to the IEEE Signal Processing Society Speech Technical Committee (STC) newsletter.  As always, contributions of events, publications, workshops, and career information to the newsletter are welcome.  Please send to Rick Rose (rose@ece.mcgill.ca).   Archives of recent STC Newsletters can be found on the STC website


STC NEWS: 
Minutes of the STC ICASSP2005 Meeting  (S. Parthasarathy)
Election of At-Large Members to the SPS Board of Govenors   (Alex Acero)

NEW INSTITUTE:
Saras Intitute - History of Speech and Language Technology (Patri Pugliese and Janet Baker)

SPECIAL ISSUES OF TRANSACTIONS:
Call for Papers for a Special Issue of the IEEE Transactions on SAP: Objective Quality Assessment of Speech and Audio
Call for Papers for a Special Issue of the IEEE Transactions on SAP: Blind Signal Processing for Speech and Audio Applications

NEW WORKSHOP / EVALUATION ANNOUNCEMENTS:
2006 Odyssey Speaker and Language Recognition Workshop
IWSLT2005 - International Workshop on Spoken Language Translation
Call for Papers Reminder - ASRU2005 - 2005 Automatic Speech Recognition and Understanding Workshop
Call for Demonstrations - ASRU2005

CAREERS:
Postdoctoral Fellowship Position at McGill University
Sidney Burrus Retires from Rice University

LINKS TO WORKSHOPS AND CONFERENCES:
Links to conferences and workshops organized by date  (Rick Rose)


Minutes of the Speech Technical Committee Meeting

Held at ICASS2005,

Tuesday, March 22, 2005


Note: Meetings of the IEEE SPS Speech Technical Committee take place twice each year.   There is a fall meeting whose main order of business is to organize sessions in the speech area for the upcoming ICASSP conference and a spring meeting which is usually held at the ICASSP conference and covers a wider set of topics.    The attendees of both meetings include both the STC members and the associate editors of the Speech and Audio Transactions.    This meeting took place at the ICASSP2005 conference in Philadelphia and was presided over by the  STC Chairman, Mazin Rahim.   The following is an editted version of the minutes from this meeting recorded by S. Parthasarathy.

Chair's Introduction - Mazin Rahim:
 
  1. Thanks to retiring STC members and welcome to new members
  2. All STC members belong to a sub-committee and they have been very effective. The Awards committee has done an excellent job and their active role has resulted in a number of speech awards.
  3. The review process worked very well with the help of area chairs, the other STC members, and external reviewers.
  4. The special sessions in the Speech area at ICASSP2005 were a great success.

Report by the Chief Editor of the Transactions on Speech and Audio Processing - Isabel Trancoso


Report on STC Policies and Procedures - ChirstopherWellekens


Report on STC Newsletter - Rick Rose
Report  by the Awards Subciommittee - Ananth Sankar
Report on the SPS Conference Board Meeting - Helen Meng
Report on the ASRU2005 Workshop - Rick Rose and Jim Glass
1. Wireless Internet access: Should we have wireless access in the hotel  lobby, terrace, etc. and how much should it cost. The hotel wants to charge $30 a day.
2. Registration Limit: How in practice do we limit attendees to under about 200 (220) without denying requests from registrants with accepted papers?
3. Session Organization: Thinking of having somewhat structured oral presentations with some guidance given to the authors; contributed papers will be posters.

Proposal for Focussed Workshops - Mazin Rahim
IEEE TTS and Coding Workshops - Michael Picheny
Special sessions for ICASSP 2006 - Roberto Pieracinni
Representation of the Speech Community on the SPS Board of Govenors (BOG) - Alex Acero

back to top

Election of At-Large Members to the IEEE Signal Processing Society Board of Govenors

The Board of Governors (BoG) makes most decisions about the Society, such as creating new journals or technical committees, voting for awards, or changing the Bylaws and rules of governance. The BoG is composed of the Executive committee (President, Past-President, President-Elect, VP Conferences, VP Publications, VP Awards and Membership, VP Finance) and 9 members-at-large. The term for all positions is 3 years. Positions in the executive committee are elected by the BoG, whereas members-at-large are elected by all members of the IEEE Signal Processing Society.

In 2004, there were 7 people in the BoG active in the speech area (Alex Acero, Joe Campbell, Mark Clements, Rich Cox, Shigeru Katagiri, Manfred Lang, and Doug O’Shaughnessy) and I feel like we've made some progress in areas like awards (candidates active in speech won two of the three Paper Awards, and two of the four Major Awards: Technical Achievement Award, Meritorious Service Award, Young Author Best Paper Award, and Best Paper Award) and the Transactions on Speech and Audio Processing (the BoG approved a 75% increase in page budget for 2006 plus the electronic pre-publication of accepted papers on Xplore, which will help reduce the publication delay) among others. I’d like to thank Joe Campbell and Doug O’Shaughnessy, whose term expired in 2004, for their contributions. None of the 3 new members-at-large elected for 2005 were active in speech, and the terms of the remaining BoG members active in speech processing will expire at the end of 2005. In 2006, there will be no members active in speech at the BoG unless some of the 2006 members-at-large elected in this election represent the speech field.

Now it’s time that time of the year to elect 3 new members-at-large for 2006. As a member of the Society you may not have voted in the past because you do not know the candidates, or because it's not clear to you what difference each candidate will make in your professional career. A lot of the decisions the IEEE Signal Processing makes are passed for a vote in the BoG, so if you vote for somebody working in your field (and if you're reading this newsletter chances are that field is speech processing) your field will be better represented in the Society. This year we have in the ballot two people active in the speech area: Mazin Gilbert, formerly Rahim, (Chair of IEEE Speech Technical Committee) and Isabel Trancoso (Editor-in-Chief Transactions on Speech and Audio Processing). In 2004, the society mailed 12,878 ballots and only 1,166 ballots were returned (the candidate with most votes only got 492). This is a great opportunity to elect your representatives in the BoG. Your vote can make a difference!

top of page


Saras Institute
History of Speech and Language Technology
 

http://di-130c.mit.edu/

 The History of Speech and Language Technology Project is sponsored by the Saras Institute in affiliation with the Dibner Institute for the History of Science and Technology, located at the Massachusetts Institute of Technology, Cambridge, MA. The overall mission is to collect, preserve and make readily available information about significant research discoveries, technical achievements and business developments in speech technology (speech recognition, speech synthesis, speaker ID & verification, etc., and their practical applications). They have, at present, a substantial collection of documents and artifacts from various institutions dealing with advances in speech technology (see the Sampler Page for examples). They are interested in identifying and preserving additional materials along these lines, especially if they might otherwise be lost or discarded. Longer term goals include making these materials readily available (including via the Internet) to historians of science and technology and anyone else interested in the history of speech technology. A particular effort is being made to record interviews with seminal contributors in this field so that future generations can better appreciate the insights and perspectives that created this technology. A limited number of interviews have already been conducted, but not yet transcribed. An overview of the history of speech and language technology can be obtained by consulting their Timeline (which, however, has not yet been posted).

The Saras Institute is named for Saraswati, the Hindu goddess of learning, knowledge, and wisdom, including the invention of speech and writing.

The Dibner Institute for the History of Science and Technology is an international center for advanced research in the history of science and technology located on the campus of MIT.

top of page

Call for Papers for Special Issue of
The IEEE Transactions on Speech and Audio Processing
Objective Quality Assessment of Speech and Audio

Objective Quality Assessment of Speech and Audio is an interdisciplinary research area to build computational models that aim to achieve human performance in quality estimation of speech and audio. The estimation of quality is becoming more important especially in telecommunication applications, where Quality of Service is one of the key considerations.

The goal of this special issue is to present recent progress and advances in this area as well as remaining challenges. We invite original, previously unpublished research works in all areas relevant to the field. In particular, paper submissions are encouraged on the following topics:

Submission procedure:

Prospective authors should prepare manuscripts according to the Information for Authors as published in any recent issue of the Transactions and as available on the web at http://www.ieee.org/organizations/society/sp/infotsa.html. Note that all rules will apply with regard to submission lengths, mandatory overlength page charges, and color charges.

Manuscripts should be submitted electronically through the online IEEE manuscript submission system at http://sps-ieee.manuscriptcentral.com/. When selecting a manuscript type, authors must click on "Special Issue of T-SA on Objective Quality Assessment of Speech and Audio." Authors should follow the instructions for the IEEE Transactions on Speech and Audio Processing and indicate in the Comments to the Editor-in-Chief that the manuscript is submitted for publication in the Special Issue on Objective Quality Assessment of Speech and Audio. We require a completed copyright form to be signed and faxed to 1-732-562-8905 at the time of submission. Please indicate the manuscript number on the top of the page.

Schedule:
Submission deadline: February 1, 2006
Notification of acceptance: July 31, 2006
Final manuscript due: September 30, 2006
Tentative publication date: January 2007

Guest Editors:
Dr. Doh-Suk Kim Lucent Technologies, Whippany, USA dsk@lucent.com
Dr. John Beerends TNO Telecom, Delft, The Netherlands j.g.beerends@telecom.tno.nl
Dr. Oded Ghitza Sensimetrics Corporation, Somerville, MA, USA oded@sens.com
Dr. Peter Kroon Agere Systems, Allentown, PA, USA kroon@agere.com
top of page


Call for Papers for Special Issue of
The IEEE Transactions on Speech and Audio Processing
Blind Signal Processing for Speech and Audio Applications

A special issue of the IEEE Transactions on Speech and Audio Processing will be dedicated to recent advances in blind signal processing for speech and audio applications. The special issue will represent a vehicle whereby researchers can present new studies of blind signal processing techniques for speech and audio applications, thus paving the way for future developments in the field.

Prospective papers should be unpublished and present solid research work offering innovative contributions either from a methodological or application point of view. In particular, submissions are encouraged on theory and methods related to the following areas:

 

Submission procedure:

Prospective authors should prepare manuscripts according to the Information for Authors as published in any recent issue of the Transactions and as available on the web at http://www.ieee.org/organizations/society/sp/infotsa.html. Note that all rules will apply with regard to submission lengths, mandatory overlength page charges, and color charges.

Manuscripts should be submitted electronically through the online IEEE manuscript submission system at http://sps-ieee.manuscriptcentral.com/. When selecting a manuscript type, authors must click on "Special Issue of T-SA on Blind Signal Processing for Speech and Audio Applications." Authors should follow the instructions for the IEEE Transactions on Speech and Audio Processing and indicate in the Comments to the Editor-in-Chief that the manuscript is submitted for publication in the Special Issue on Blind Signal Processing for Speech and Audio Applications. We require a completed copyright form to be signed and faxed to 1-732-562-8905 at the time of submission. Please indicate the manuscript number on the top of the page.

Schedule:
Submission deadline: 1 July, 2006
Notification of acceptance: 31 January, 2007
Final manuscript due: 15 March, 2007
Tentative publication date: July 2007

Guest Editors:
Dr. Shoji Makino NTT Communication Science Laboratories, Japan maki@cslab.kecl.ntt.co.jp
Dr. Te-Won Lee University of California, San Diego, USA tewon@salk.edu
Dr. Guy Brown University of Sheffield, UK g.brown@dcs.shef.ac.uk
top of page


2006 Odyssey Speaker Recognition Workshop


San Juan Puerto Rico
June 28-30, 2006


CALL FOR PAPERS

We invite you to Odyssey 2006, an ISCA Tutorial and Research Workshop on speaker and language recognition held at the scenic Ritz Carlton Hotel in San Juan, Puerto Rico. In cooperation with the ISCA Speaker and Language Characterization SIG, this workshop is hosted by The Polytechnic University of Puerto Rico. 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), 1998 RLA2C Workshop (Avignon), 2001: A Speaker Odyssey (Crete), and 2004 The Speaker and Language Recognition Workshop(Toledo).

Feature Tracks and Topics

Feature tracks cover newtechniques 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 ‘06 Workshop Evaluation Track

<>The NIST Speaker Recognition Evaluation 2006 Workshop will be held during this week before 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: http://www.nist.gov/speech

Paper Submission

Prospective authors are invited to submit papers written in English. Papers will be submitted via the Odyssey web site atwww.speakerodyssey.com. The document style, templates, and submission form can be downloaded from the Odyssey web site. Two members of the Scientific Committee will review each paper. At least one author of each paper is required to register. The workshop proceedings will be published on CD-ROM.

Schedule

Proposal due

15 January 2006

Notification of acceptance

27 February 2006

Final papers due

30 March 2006

Preliminary program

21 April 2006

Workshop

28 –30 June 2006


top of page


International Workshop on Spoken Language Translation 2005

Pittsburgh, PA
October 24 - 25, 2005

http://www.is.cs.cmu.edu/iwslt2005/

 

The Consortium for Speech Translation Advanced Research (C-STAR), an international partnership of research laboratories engaged in automatic translation of spoken language, organizes The International Workshop on Spoken Language Translation (IWSLT) from Oct. 24th to 25th.  Speech translation systems combine speech recognition (ASR) systems with machine translation (MT) systems.  This year, IWSLT will focus on dealing with the integration of speech, and how to achieve more robust translations in the face of recognition errors.  An evaluation campaign will be held, using the multilingual BTEC corpus from the IWSLT-2004 evaluation, but extended by using ASR output.  In addition, multiple language tracks and integration modalities will be compared.

Two types of submissions are invited: 1) participants in the evaluation campaign of spoken language translation technologies, and 2) technical papers on related speech translation activities, including reports on work from other programs worldwide.  Each participant in the evaluation campaign is requested to submit a paper describing the translation system.

Evaluation campaign

The evaluation of spoken language translation systems will be done using the Basic Travel Expression Corpus (BTEC).  Participants choose at least on of the following conditions:

Translation directions:

    Chinese-English
English-Chinese<>
Japanese-English
Korean-English
Arabic-English

<>

Data tracks:

·     Supplied data: 20,000 sentence pairs for each translation direction

·     Unrestricted data:  supplied data, LDC data, WWW

<>·     C-STAR track:  Unrestricted data (including full BTEC corpus or proprietary data.)
 

Translation conditions:

·     Manual transcription (plain sentences in BTEC)

·     ASR output (1-best, N-best, lattices) of spoken BTEC sentences

Evaluation Methodology:

·     Subjective Evaluation (most popular track)

·     Automatic Evaluation (BLEU, NIST, WER, etc)

Important Dates:
Registration:                                         open
Training Corpus Release:                   May 20, 2005
Test Corpus Release:                          Aug 16, 2005
Result Submission Due:                      Aug 18, 2005
Camera-ready Paper:                            Sept 25, 2005

Technical Papers

To accomplish speech translation, we have to solve problems in MT for speech, especially for spontaneous speech and handle recognition errors in the ASR output.  Technical papers are invited on all matters related to speech translation.  Potential topics for general speech translation session include, but are not limited to:

·     Spontaneous speech translation

·     Domain-limited and unlimited speech translation

·     Tight coupling of MT with ASR

·     Word / Phrase Alignment

·     MT Decoding Algorithms

·     Multilingual ASR

·     Multilingual Parsing

·     Using comparable and non-parallel data

·     Domain and Language Portability

·     MT Evaluation Measures

Important Dates:
Submission of Draft (8 pages):       July 12, 2005
Notification of Acceptance:            Aug 9, 2005
Camera-ready Paper:                         Sept 25, 2005
Workshop:                                         Oct 24-25, 2005

Organizers:

<>Alex Waibel (CMU, USA / UKA, Germany; Chair)
Chiori Hori (CMU, USA, Co-Chair)
Stephan Vogel (CMU, USA, Program Chair)
Tanja Schultz (CMU, USA, Program Co-Chair)
Christian Boitet (CLIPS, France)
Gianni Lazzari (ITC-irst, Italy)
Youngjik Lee (ETRI, Korea)
Seiichi Yamamoto (ATR, Japan)
Chengqing Zong (CAS, China)  <>
Local Arrangements: Celine Carraux (CMU, USA)

top of page



CALL FOR PAPERS REMINDER

IEEE ASRU 2005

Automatic Speech Recognition and Understanding Workshop

Tulum ruins

Fiesta Americana Grand Coral Beach Resort 

Cancun, Mexico

November 27 – December 1, 2005


The Ninth biannual IEEE workshop on Automatic Speech Recognition and  Understanding (ASRU) will be held November 27-December 1, 2005.   The ASRU Workshops have a tradition of bringing together researchers from academia and industry in an intimate and collegial setting to discuss problems of common interest in automatic speech recognition and understanding. Papers in all areas of human language technology are encouraged to be submitted, with emphasis placed on automatic speech recognition and understanding technology, speech to text systems, spoken dialog systems, multilingual language processing, robustness in ASR, spoken document retrieval, and speech-to-speech translation.
 
The workshop program will consist of invited lectures, oral and poster presentations, panel discussions, and technology demonstrations. Ample time will be allowed for informal discussions and to enjoy the impressive tropical setting.  

PAPER SUBMISSION:
Prospective authors are invited to submit full-length, 4-6 page papers, including figures and references, to www.asru2005.org . All papers will be handled and reviewed electronically. The deadline for paper submission is July 1, 2005.  Instructions for submitting a paper can be found at http://www.asru2005.org .

IMPORTANT DATES


May 1, 2005
Workshop registration opens
July 1, 2005
Camera-ready paper submission deadline
August 15, 2005
Paper Acceptance/Rejection notices emailed
September 15, 2005

Revised papers due/Author registration deadline

October 1, 2005
Workshop early registration deadline
October 27, 2005
Hotel reservation deadline

Nov. 27 - Dec. 1, 2005

Workshop



back to top



CALL FOR DEMONSTRATIONS

IEEE ASRU 2005

Automatic Speech Recognition and Understanding Workshop

Tulum ruins

Fiesta Americana Grand Coral Beach Resort 

Cancun, Mexico

November 27 – December 1, 2005


Prospective demonstrators are invited to submit 1-2 page proposals via the workshop website for demonstrating leading edge technology within the broad scope of the workshop. Proposals in all areas of human language technology are encouraged to be submitted with emphasis placed on: All demo proposals will be handled and reviewed electronically. Please identify any special audio-visual needs in your proposal.

IMPORTANT DATES

May 1, 2005
Workshop registration opens
Aug. 15, 2005
Demo submission deadline
September 1, 2005
Demo decision notices emailed
September 15, 2005
Author registration deadline
October 1, 2005
Workshop early registration deadline
October 27, 2005
Hotel reservation deadline
 Nov 27 - Dec. 1, 2005
Workshop


back to top

Sidney Burrus Retires from Rice University

 
This June, Sidney Burrus will be stepping down as the Dean of the George R. Brown School of Engineering and retiring from the Electrical and Computer Engineering Faculty at Rice University.

To view a brief biography of Sidney Burrus, visit: http://www-ece.rice.edu/~csb/.
To view the program of a recent workshop honoring Prof. Burrus' 70th birthday and 40 years of research and leadership in ditital signal processing, visit:  http://csb70.rice.edu/.

Burrus holds the Maxfield and Oshman Professor of Electrical and Computer Engineering chair.  He earned his bachelor's and master's degrees in electrical engineering from Rice in 1958 and 1960 at Rice, respectively, and returned to join the faculty in 1965 after earning his doctorate at Stanford. Burrus has served as chair of the Department of Electrical and Computer Engineering, director of the Computer and Information Technology Institute and master of Lovett College.

From 1984 to 1992 he served as chair of the Electrical and Computer Engineering Department. He was named Dean of the School of Engineering in 1998.  In 1975 and again in 1979 he was a guest professor at the Universitaet Erlangen-Nürnberg, Germany. During the summer of 1984 he was a visiting fellow at Trinity College, Cambridge University, England, and during the academic year 1989-90, he was a visiting professor at MIT, Cambridge, Mass.

Throughout his career, Burrus has been honored for his work in the classroom and in research laboratories. He received teaching awards throughout his tenure as a faculty member at Rice. He earned a Humboldt Award in 1975, a Senior Fulbright Fellowship in 1985, was a distinguished lecturer for the Signal Processing Society and for the Circuits and Systems Society from 1989 through 1992, and received the Signal Processing Society Award in 1995.

In addition to his teaching and research work load, Burrus is a member of the university's Ad Hoc Committee on General Education.  He has served on advisory and review panels for the National Science Foundation, the Office of Naval Research and various universities.

"Sidney Burrus helped found Rice's DSP group in 1968 and build it into one of the world's premier DSP research programs," said Richard Baraniuk, professor of electrical and computer engineering. "It is difficult to overestimate his contributions in this field. He wrote some of the foundational texts in DSP, and his work with Texas Instruments in the early 1970s set off a chain reaction that eventually caused the company to rethink its entire business model."

Sidney brought an intimate knowledge of the challenges and the strengths of Rice and the engineering school. He is an outstanding scholar, has terrific people skills, and is very familiar with where we've been and where we needed to go.

Rice held a two-day celebration in February 2005 titled "csb@70" recoginizing Sidney's leadership in the field of DSP - as well as his 40th anniversary on the faculty and his 70th birthday. The celebration began with an invitation-only dinner and concluded with a daylong DSP workshop, featuring such DSP luminaries as John Treichler '69, founder, director and chief technology officer of Applied Signal Tech; Ronald Schafer, distinguished technologist at Hewlett-Packard Laboratories; James McClellan '72, a professor at Georgia Institute of Technology; Sanjit Mitra, a professor at the University of California-Santa Barbara; David C. Munson, a professor at the University of Michigan; and Fred Mintzer, current president of the IEEE Signal Processing Society and of IBM Thomas Watson Research Laboratories.

back to top


Postdoctoral Fellowship Position in Speech Recognition

and Speech Modeling at McGill University


We are seeking a postdoctoral fellow to perform basic research as part of a three year project in the general area automatic speech recognition.  The position will be in the Electrical and Computer Engineering Department at McGill University in Montreal, Canada.   The candidate should have hands-on experience with  speech processing systems and should have a strong background in statistical modeling, signal processing, and/or speech analysis.   The candidate should also have facility with the use of high level programming languages for developing protoype systems and simulations.  Fluency in English is required and the ability to work in a small team is also important.

The position is in support of a Canadian funded NSERC project that is being conducted in association with the European 6th Frame Project DIVINES.  The overall goal of the project is to overcome deficiencies in existing acoustic feature analysis and phonetic and lexical modeling techiques.  This will be accomplished through a methodology  involving the diagnosis and modeling of instrinsic variabilities in ASR under a variety of conditions.   

McGill University is located in Montreal, an exciting cosmopolitan city in the Province of Quebec. Montreal is the home of a number of speech recognition Research and Development Laboratories including Centre Recherche  Informatique Montreal (CRIM), ScanSoft Canada, Nuance Canada, Nu Echo, and others.  Montreal is composed of a bilingual population with a blend of European and North American culture. Qualified applicants are invited to submit a resume together with the names and addresses of two references by email to:

McGill University
Richard Rose   
McGill University
Department of Electrical and Computer Engineering
McConnell Engineering Building, Room 813
3480 University Street
Montreal, Quebec
H3A 2A7

email: 
phone: 514-398-1749
fax: 514-398-4470 tment of Electrical & Computer Engineering

back to top

Links to Upcoming Conferences and Workshops (Organized by Date)

ICME2005 IEEE International Conference on Multimedia and Expo
Amsterdam, The Netherlands, July 6-8, 2005.
http://www.icme2005.org

Auditory-Visual Speech Processing (AVSP 2005)
Vancouver Island, British Columbia, Canada, July24-27
http://marcs.uws.edu.au/links/avisa/avsp05

SIGdial Workshop on Discourse and Dialog
Lisbon, Portugal , September 2-3, 2005
http://www.sigdial.org/workshops/workshop6

ITRW 2005 Workshop on DSP for IN-VEHICLE and MOBILE SYSTEMS
Sesimbra, Portugal, September 3, 2005
http://dspincars.sdsu.edu/

EUROSPEECH 2005 9th European Conference on Speech Communication and Technology
Lisbon, Portugal, September 4-8, 2005
http://www.interspeech2005.org/

Disfluency in Spontaneous Speech
Aix-en-Provence, September 10-12, 2005
http://www.up.univ-mrs.fr/delic/Diss05

IEEE WASPAA2005 Workshop on Applications of Signal Processing to Audio and Acoustics
New Paltz, New York, October 16-19, 2005
http://www.LNT.de/~WASPAA05/

SPECOM 2005 - 10th International Conf. on Speech and Computers
Patras, Greece, October 17-19, 2005
http://www.wcl.ee.upatras.gr/specom2005.htm

MMSP-2005 IEEE International Workshop on Multimedia Signal Processing
Shanghai, China, October 30- November 1, 2005
http://www.mmsp05.missouri.edu/

IEEE ASRU2005 Automatic Speech Recognition and Understanding Workshop
Cancun, Mexico, November 27 - December 1, 2005
http://www.asru2005.org

ICASSP2006
Toulouse, France May 15-19, 2006
http://www.icassp2006.org

2006 Odyssey Speaker Recognition Workshop
San Juan, Puerto Rico, June 28 - 30, 2006
www.speakerodyssey.com

ICME2006 IEEE International Conference on Multimedia and Expo
Toronto, Ontario, Canada, July 9 - 12.
http://www.icme2006.org

ICPR2006 International Conference on Pattern Recognition
Hong Kong, August 20-24, 2006.
http://www.comp.hkbu.edu.hk/~icpr06/

HCI2005 Human Animated Character Interaction Workshop
Edinburgh, UK, September 6, 2005.
http://www.dcs.shef.ac.uk/cogsys/workshop/

INTERSPEECH 2006 - ICSLP  
Pittsburgh, PA, USA September 17-21, 2006
http://www.interspeech2006.org/

ICASSP2007
Honolulu, Hawaii, USA, 2007, April 17-20

INTERSPEECH 2007
Antwerp, Belgium, August 27-31, 2007
http://www.interspeech2007.org/

back to top