IEEE SPEECH TECHNICAL COMMITTEE NEWSLETTER

January 24, 2004

INTRODUCTION:

Welcome to the eighth  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.   Please note the change in address of the  newsletter editor (rose@ece.mcgill.ca) when submitting contributions.  Topics for issue number eight ...

SPECIAL ISSUES:
IEEE Trans on SAP Special Issue on Data Mining of Speech, Audio, and Dialog (Mazin Rahim)
IEEE Trans on SAP Special Issue on Speech-to-Speech Machine Translation (G. Riccardi)


NEW WORKSHOP ANNOUNCEMENTS:
3rd Inter. Conf on Measurement of Speech and Audio Quality in Neworks - MESAQIN 2004
IEEE 2004 Workshop on Signal Processing Advances in Wireless Communications
2004 HLT/NAACL Workshop on Spoken Language Understanding for Conversational Systems (G. Tur)
NIST Rich Transcription 2004 Meeting Recognition Workshop (John Garofolo)

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

Call for Papers

IEEE Transactions on Speech and Audio Processing

Special Issue on Data Mining of Speech, Audio and Dialog


Data mining methods are used to discover patterns and extract potentially useful or interesting information automatically or semi-automatically from data. As a result of the recent advances in machine learning and data mining algorithms, along with the availability of inexpensive storage space and faster processing, data mining has become practical in new areas including speech, audio and spoken language dialog. Data mining research in these areas is growing rapidly given the influx of speech, audio and dialog data that are becoming more widely available. Fundamental research in areas of prediction, explanation, learning and language understanding of speech and audio data are becoming increasingly important in revolutionizing business processes by providing essential sales and marketing information about the service, customers and product offerings. This research is also enabling a new class of learning conversational systems to be created that can infer knowledge and trends automatically from data, analyze and report application performance, and adapt and improve over time with minimal or zero human involvement.


The purpose of this special issue is to present recent advances in Data Mining Research for Speech, Audio, and Spoken Language Dialog. Original, previously unpublished submissions for the following areas are encouraged:


Guest Editors:

Dr. Mazin Rahim, AT&T Research, Florham Park, USA. mazin@research.att.com

Dr. Usama M. Fayyad, DMX Group, Seattle, USA. fayyad@dmxgroup.com

Dr. Roger Moore, 20/20 Speech Ltd., Malvern, U.K. r.moore@2020speech.com

Dr. Geoff Zweig, IBM Research, Yorktown Heights, USA. gzweig@us.ibm.com


Schedule:

Submission deadline: 1 July 2004 (early submission is encouraged)

Notification of acceptance: 1 January 2005

Final manuscript due: 31 March 2005

Tentative publication date: 1 July 2005


Submission Procedure:

Prospective authors should follow the regular guidelines of the IEEE Transactions on Speech and Audio Processing for electronic submission via Manuscript Central (http://sps-ieee.manuscriptcentral.com). Authors must enter the title of the special issue into the field labeled “Please enter any additional keywords related to this submitted manuscript in order for the paper to be properly assigned to a Guest Editor.” In addition, the title of the special issue should be referenced again in the field marked “Comments to Editor-in-Chief” along with any other pertinent information. You are required to provide a properly executed copyright form to be faxed to the IEEE Signal Processing Society Publications Office (via +1 732-562-8905) at the time of submission. An 8-page limit will be enforced on papers published in the special issue and all papers are subject to the published policy for overlength page charges and color charges.

[top of page]

Call for Papers

Special Issue of

The IEEE Transactions on Speech and Audio Processing

On

Speech-to-Speech Machine Translation

Speech-to-Speech Machine Translation (SSMT) is a multidisciplinary research area that addresses one of the most complex problems in speech and language processing. The challenges posed by SSMT have been the subject of several collaborative research projects across universities and laboratories around the world. Over the last decade SSMT has benefited from advances in speech and language processing as well as from the availability of large multilingual databases. These advances have spurred research on statistical machine translation and on exploiting machine translation for cross-lingual information retrieval. There have also been substantial efforts towards automating and evaluating a variety of metrics that are relevant to SSMT systems.


The purpose of this special issue is to present recent advances in Speech-to-Speech Machine Translation. Original, previously unpublished research is sought in all areas relevant to the field. In particular, submissions on theory and methods for the following areas are encouraged:


Guest Editors:

Dr. Giuseppe Riccardi AT&T Research Labs, Florham Park, USA beppe@att.com

Dr. Yuqing Gao IBM TJ Watson Research, Yorktown Heights, USA yuqing@us.ibm.com

Prof. Helen Meng Chinese University of Honk Kong, Hong Kong, China hmmeng@se.cuhk.edu.hk

Dr. Satoshi Nakamura ATR Research Labs, Kyoto, Japan satoshi.nakamura@slt.atr.co.jp

Prof. Alex Waibel Carnegie Mellon University, Pittsburgh, USA waibel@cs.cmu.edu


Submission procedure:

Prospective authors should follow the regular guidelines of the IEEE Transactions on Speech and Audio Processing for electronic submission via Manuscript Central (http://sps-ieee.manuscriptcentral.com). Authors must enter the title of the special issue into the field labeled “Please enter any additional keywords related to this submitted manuscript in order for the paper to be properly assigned to a Guest Editor.” In addition, the title of the special issue should be referenced again in the field marked “Comments to Editor-in-Chief” along with any other pertinent information. You are required to provide a properly executed copyright form to be faxed to the IEEE Signal Processing Society Publications Office (via +1 732-562-8905) at the time of submission. An 8-page limit will be enforced on papers published in the special issue and all papers are subject to the published policy for overlength page charges and color charges.


Schedule:

Submission deadline: 1 June 2004

Notification of acceptance: 1 November 2004

Final manuscript due: 31 January 2005

Tentative publication date: June 2005

[top of page]

       CALL FOR PAPERS

3rd International Conference MESAQIN 2004

Measurement of Speech and Audio Quality in Networks
on-line: May 17, 2004
conference meeting: Prague, June 10 - June 11, 2004
Deadline for extended abstract submission: February 28, 2004
www: http://wireless.feld.cvut.cz/mesaqin

Topics:

Extended abstracts/fulltexts should be sent before February 28, 2004, to the e-mail address:
mesaqin@wireless.feld.cvut.cz
Info for authors is available on the conference web page.

The papers will be reviewed by the International Program Committee
and notification of acceptance will be sent by e-mail before April 1, 2004.

Organized and co-sponsored by:

Czech Technical University
IMEKO - International Confederation of Measurements - Czech National Committee
Institute of Radio Engineering and Electronics - Academy of Science of the Czech Republic
Grant Agency of the Czech Republic

Concept of Arrangement

Obtained contributions will be converted into Adobe PDF Format
and published on WWW. On these WWW pages an on-line discussion concerning these contributions will be held. After two weeks the discussion will be closed. Conference meeting enabling personal contact establishment and maintenance will be held in Prague and will be accompanied by social events. Printed proceedings will be published.

Deadline for extended abstract/fulltext submission: February 28, 2004
Notification of paper acceptance: April 1, 2004
Full text submission/enhancement: May 10, 2004
Publication on WWW, on-line discussion start: May 17, 2004
Conference Meeting: June 10 - June 11, 2004

[top of page]

CALL FOR PAPERS

The 2004 IEEE Workshop on

SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS

July 11-14, 2004

Lisbon, Portugal


SPAWC-2004, the fifth IEEE International Workshop on Signal Processing Advances for Wireless Communications, is devoted to recent advances in signal processing for wireless and mobile communications. This workshop brings together members of the signal processing, communications and information theory communities, working in universities, research
centers and telecommunications companies. The meeting will feature keynote addresses by leading researchers, as well as invited and contributed papers.

SPAWC-2004 will be held at Hotel Tivoli - Tejo, in Lisbon, Portugal, more precisely at the Parque das Nações. This site offers some of the most daring examples of contemporary architecture, Europe's largest Oceanarium, delightful thematic gardens, exhibition centres, theatres and event halls, all located along a breathtaking 5 km stretch of the Tagus riverfront, in the heart of Lisbon, benefiting from a wide array of shops, restaurants and bars. Only five minutes from Lisbon International Airport, Parque das Nações builds on the heritage of EXPO'98 - the last world exposition of the twentieth century.  Prospective authors are invited to submit contributions in the following areas:


Prospective authors should submit the full camera ready version of the paper (up to five pages) using the template provided at the workshop URL.  Submissions should include affiliations, addresses, tel/fax numbers, and e-mail addresses, and keywords identifying one of the above topics.  All submissions will be electronic in PDF format.

IMPORTANT DATES
Paper submissions deadline: January 16, 2004
Notification of acceptance: March 19, 2004
Final papers due: April 16, 2004

Please visit the conference web site for paper submission procedures and further details about the conference:
http://spawc2004.isr.ist.utl.pt

General Chair
Victor Barroso
Instituto Superior Técnico
ISR, Torre Norte, Piso 7
Av. Rovisco Pais
1049-001 Lisboa Portugal
vab@isr.ist.utl.pt
Fax: (351) 21 8418291

Honorary Chair
José Moura
Carnegie Mellon University

Technical Committee Chair
José Leitão
Instituto Superior Técnico

Technical Committee
A. J. van der Veen
A. Swami
Ali H. Sayed
Anna Scaglione
B. Ottersten
Chong-Y. Chi
Nat. Tsing Hua
D. Slock
F. Nunes
G. Vazquez
G.T. Zhou
Geert Leus
H. Boelcskei
J. Gomes
J. Xavier
L. Tong
N. Al Dhahir
N. Sidiropoulos
P. Loubaton
S. Barbarossa
Xiang-Gen Xia

Publicity and Local Arrangements
F. Garcia, IST, Portugal

Treasurer
J. Gomes, IST, Portugal

Publications
P. Aguiar, IST, Portugal

International Liaison
Anna Scaglione,
Cornell U., USA (North America)
Chong-Y. Chi and Nat. Tsing Hua,
U., Taiwan (Asia and Australia)
M. Alencar,
U.F. Campina Grande, Brasil
(Central and South America)

SPAWC 2004 Secretariat:
Instituto Superior Técnico
ISR, Torre Norte, Piso 7
Av. Rovisco Pais
1049-001 Lisboa Portugal
E-mail: spawc2004@isr.ist.utl.pt
Ph: (351) 21 8418289
Fax: (351) 21 8418291
[top of page]

Call for Workshop Papers

HLT/NAACL 2004 Workshop
on
Spoken Language Understanding for Conversational Systems
http://www.research.att.com/~dtur/NAACL04-Workshop/

The Park Plaza Hotel, Boston, Massachusetts
May 7, 2004

The success of a conversational system depends on a synergistic integration of technologies such as speech recognition, spoken language understanding (SLU), dialog modeling, natural language generation, speech synthesis and user interface design. In this workshop, we will address the SLU component of a conversational system and its relation to the speech recognizer and the dialog model. In particular, we aim to bring together techniques that address the issue of robustness of SLU to speech recognition errors, language variability and dysfluencies in speech with issues of representation that provide greater flexibility to the dialog model.

The topic of robust SLU has received much attention during the DARPA funded ATIS program of the 1990s and more recently the DARPA Communicator program. In parallel to that research, a number of real-world conversational systems have been deployed to date. However, the techniques for robust SLU have branched out in many different directions. They have been influenced by many recent areas such as information extraction, question answering and machine learning. Data driven approaches to understanding are rapidly gaining prominence.

The objective of this workshop is to provide the speech and language processing community with a timely update of recent advances, perspectives and research directions in SLU for conversational systems.

The workshop will address related topics such as:

In the past few years, there has been substantial increase in interest in information extraction from the NLP community, question-answering in the information retrieval community, and spoken dialog systems in the speech processing community. Spoken language understanding is an especially attractive topic for cross-fertilization of ideas between speech, IR and NLP communities. This workshop follows on IEEE Automatic Speech Recognition and Understanding (ASRU) Workshop (http://www.asru2003.org) series and previous ACL workshops on related subjects, such as: Workshop on Spoken Dialog Systems (1997) (http://www1.cs.columbia.edu/~radev/acl/ACL97/interactive-spoken.html).

IMPORTANT DATES:
Paper submission deadline: January 26, 2004
Notification of acceptance for papers: February 25,
2004 Camera ready papers due: March 8, 2004
Workshop date: May 7, 2004

SUBMISSION PROCEDURE Authors should submit full papers of maximum 8 pages, including references and figures, following the main conference ACL style format (as specified in http://www1.cs.columbia.edu/~pablo/hlt-naacl04/format.html). Note that reviewing will NOT be blind, the paper submissions may include the authors' names and affiliations. Submissions should be sent to gtur@research.att.com.

ORGANIZING COMMITTEE
Srinivas Bangalore, AT&T Labs - Research, USA
Dilek Hakkani-Tür, AT&T Labs - Research, USA
Gokhan Tur, AT&T Labs - Research, USA

PROGRAM COMMITTEE
Frederic Bechet, Univ. of Avignon, France
Ciprian Chelba, Microsoft, USA
Stephen Cox, Univ. of East Anglia, UK
Sadaoki Furui, Tokyo Institute of Technology, Japan
Allen Gorin, AT&T Labs - Research, USA
Roberto Gretter, ITC-IRST, Italy
Helen Meng, CUHK, Hong Kong
Prem Natarajan, BBN, USA
Hermann Ney, RWTH Aachen, Germany
Roberto Pieraccini, IBM, USA
Manny Rayner, NASA, USA
Brian Roark, AT&T Labs - Research, USA
Stephanie Seneff, MIT, USA
Elizabeth Shriberg, SRI, USA
Amanda Stent, Stony Brook Univ., USA
[top of page]

Rich Transcription 2004 Meeting Recognition Workshop

ICASSP 2004 in Montreal

May 17, 2004


NIST is conducting a community-wide evaluation of speech-based meeting recognition technologies in March and a 1-day workshop,  "Rich Transcription 2004 Meeting Recognition Workshop", on May 17 at ICASSP 2004 in Montreal.  The evaluation is part of the NIST Rich Transcription Evaluation series and will include both speaker segmentation and speech-to-text transcription tasks in the meeting domain.   The test set will be approximately 90 minutes in length and will be comprised of 8 ~11-minutes meeting exerpts collected at CMU, ICSI, the LDC, and NIST.  Evaluation participants will have automatic slots in the workshop.  Others working in related areas (speech technologies, vision technologies, behavioral sciences, etc.) in the meeting domain  may submit abstracts for invited workshop slots.  While a portion of the workshop will be devoted to discussion of the results of the evaluation, the goal of the workshop is to provide an overview of the state-of-the-art in meeting recognition technologies and discuss plans for future work and collaborations. Contact john.garofolo@nist.gov for further information.
 
Evaluation
A great deal of information regarding the evaluation would be provided in an evaluation specification document released prior to the evaluation.  However, here is what we plan to do in brief: 
 
The evaluation would be implemented using an approximately 90-minute multi-site test set of 11-minute excerpts of meetings recorded using both  1) 1 or more distantly-placed microphones,  and 2) separate close-talking microphones for each meeting participant.  Both Speech-to-Text Transcription (STT) and Speaker Segmentation (SPKR) tasks would be included.  The tasks would be similar, although not identical, to the tasks implemented in the 2003 Spring Rich Transcription Evaluation for news broadcasts and telephone conversations
(http://www.nist.gov/speech/tests/rt/rt2003/spring/index.htm).  The following test conditions would be supported:
 
STT using 1 or more distant mikes (primary)
        [multiple mikes would be provided as available]
STT using 1 distant mike (optional contrast)
STT using separate close-talking mikes (required contrast)
 
SPKR using 1 or more distant mikes (primary)
        [multiple mikes would be provided as available]
SPKR using 1 distant mike (optional contrast)
 
Minimally, evaluation participants would be required to implement either the STT or SPKR task primary condition and required contrasts for the selected task.  Training data (10 hours or more) would be made available through the LDC prior to the evaluation.
 
Schedule
Here is our tentative schedule:
 
Training Data available: February 2
Evaluation Spec available: February 13 
Abstracts for non-evaluation papers due: February 23
Notification of acceptance of non-evaluation papers: March 15
Committment to participate in evaluation: March 1
Evaluation begins: March 8
Evaluation system output due: March 22
Scored results available: March 26
Non-evaluation papers due: April 19
Evaluation papers due: April 27
[top of page]

Links to Upcoming Conferences and Workshops

(Organized by Date)

Workshop on Multimodal User Authentication
Santa Barbara, CA,  December 11-12, 2003
http://mmua.cs.ucsb.edu

International Conference on Models and Analysis of Vocal Emissions for Biomedical Applications
Firenze, Italy,  December 10-12, 2003
http://www.maveba.org

SWIM: Special Workshop in Maui Lectures by Masters in Speech Processing
Maui, Hawaii, January 12-14, 2004
http://dspincars.sdsu.edu/swim

2nd International Conference of the Global WordNet Association
Brno, Czech Republic, January 20 -23, 2004
http://www.fi.muni.cz/gwc2004

International Conference on Speech Prosody
Nara, Japan, March 23-26, 2004
http://www.gavo.t.u-tokyo.ac.jp/sp2004/sp2004_fm.html#

ICA2004 18th International Congress on Acoustics
Kyoto, Japan, April 4-9, 2004
http://www.ica2004.or.jp

ITCC04 - International Conference on Information Technology Coding and Computing
Las Vegas, Nevada, April 5-7, 2004
http://www.itcc.info

HLT/NAACL 2004
Boston, MA, May 2-7, 2004
http://www.hlt-naacl04.org/

HLT/NAACL 2004 Workshop on Spoken Language Understanding for Conversational Systems
Boston, MA, May 7, 2004
http://www.research.att.com/~dtur/NAACL04-Workshop/

NIST Rich Transcription 2004 Meeting Recognition Workshop 
Montreal, Canada, May 17, 2004
john.garofolo@nist.gov

ICASSP2004
Montreal, Canada, May 17-21, 2004
http://www.icassp2004.com

Odyssey2004 - ISCA Workshop on Speaker and Language Recognition
Toledo, Spain, May 31 - June 1, 2004
http://www.odyssey04.org/

3rd International Conference MESAQIN 2004
Czech Republic, June 10-11, 2004
http://wireless.feld.cvut.cz/mesaqin/

IEEE2004 Workshop on Signal Processing Advances in Wireless Communications
Lisbon Portugal, July 11 - 14, 2004
http://spawc2004.isr.ist.utl.pt

SCI2004 - 8th World Conference on Systemics, Cybernetics, and Informatics
Orlando, Florida, July 18 - 21, 2004
http://www.iisci.org/sci2004

EUSIPCO2004
Vienna, Austria, Sept. 7-10, 2004
http://www.nt.tuwien.ac.at/eusipco2004/

ICSLP2004 - INTERSPEECH 8th Biennial International Conference on Spoken Language Processing
Jeju Island, Korea, October 4-8, 2004
http://www.icslp2004.org

ICASSP2005
Philadelphia, Pennsylvania, May, 2005
http://www.icassp2005.org/

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

back to top