[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

VOQUAL: A workshop on voice perceptual attributes

Dear List,

    A workshop on the perceptual attributes of voice
("voice quality") is being organized at the University
of Geneva in August 2003. One of its most interesting
features is that a common voice material is proposed to
all the participants, in order to compare approaches
and tools. See below the complete announcement.

Jean-Sylvain Liénard
    BP 133  91403 Orsay Cedex
    tél      33 1 69 85 81 13
    fax      33 1 69 85 80 88
    E-mail   jean-sylvain.lienard@limsi.fr



GENEVA - AUGUST 27-29, 2003

ISCA Tutorial and Research Workshop
International Speech Communication Association



University of Geneva, Department of Psychology
27-29 August 2003 (week before EUROSPEECH'03)

Submissions due: May 2, 2003
Notification of Acceptance: June 16, 2003
Deadline for Final Papers: June 30, 2003
Deadline for Regular Registration: June 30, 2003
Workshop: August 27-29, 2003


Until recently, voice quality and its functions in
speech communication has been only marginally
considered in the speech communication community.
However, there is today some evidence that voice
quality settings and voice quality modulations are
playing a central role in human voice-based
communication, i.e. speech, singing and other kinds of
expressive vocalizations.

Voice quality: a prosodic feature ?
A challenging problem is the relationship between voice
quality and prosody. Prosodic parameters are usually
restricted to pitch, duration, pauses and some sort of
intensity parameter. Voice quality is not usually
considered in the prosodic field, which is more focused
on intonation, accentuation and rhythm. However,
synthesis of expressive speech has demonstrated that
convincing natural sounding results are impossible to
obtain without dealing with voice quality parameters.

Voice quality: a support for emotions ?
Vocal expression of emotions and attitudes is one of
the main domains of interest for this workshop.
Although it has been studied for a long time in
psychology, it can be considered as an emerging
research domain not only for speech recognition and
synthesis, but also for speech coding and other areas
of speech communication.

What definition for voice quality ?

Voice quality is still a rather fuzzy concept: what is
the timbre of a voice? How to measure and quantify
vocal effort? What are the domains of variation of
everyday speech? What are the physical and perceptive
correlates of voice quality? What are the relationships
between voice quality and others aspects of prosody?
These matters and others will be addressed in the
workshop, which aims at gathering together people
involved in voice quality research in the fields
including (but not limited to) speech communication,
psychology, voice physiology and pathology, voice and
singing pedagogy.

Test your approach on a common voice material. !

An active approach to the workshop will be encouraged.
Therefore, a common voice material (speech and singing
voice) will be provided on the workshop website

Tentative participants will be asked to take this
material into account when preparing their
contributions to the workshop and their paper
proposals. We hope that this common material will help
us for presentation and discussion of our methods for
voice quality analysis and synthesis, of our models of
voice quality perception and voice quality description,
of our analyses of voice quality functions in human


* Analysis of voice quality
* synthesis of voice quality
* signal processing of voice quality
* physical modeling of voice quality
* automatic recognition of voice quality
* voice quality aspects of prosody
* prosodic aspects of voice quality
* expressive speech
* singing and other kinds of non-speech expressive
* vocal correlates of emotions and attitudes
* acoustics and phonetics of vocal effort and everyday
* perception of voice quality
* physiology and pathology of voice quality
* other topics related to voice quality functions,
analysis and synthesis


The first day of the workshop will be a Tutorials Day.
Four tutorials will be given by renowned experts of the
domain and discussed by the audience on the following

Signal processing for voice quality processing
Paavo Alku, Helsinki University, Finland:  "Different
parameterization methods of the glottal flow estimated
by inverse filtering"

Voice quality and the singing voice
Janice Chapman, London, UK

Physical modeling of voice and voice quality
Brad Story, University of Arizona, USA

Phonetics and measurements of voice quality
Adrian Fourcin, University College, London, UK


Submission requirements
Full papers of 4-6 pages in length are to be submitted
by May 2nd, 03. Authors will be allowed to make changes
based on reviewers suggestions before submitting the
final versions of the papers for publication.

Workshop proceedings will be available upon
registration at the conference center and subsequently
on the workshop web site.

The official language of the workshop will be English.

A small number of grants covering registration and
possibly cheap accommodation costs will be offered to
students and young scientists to attend the workshop.
The International Speech Communication Association
(ISCA) is a non-profit organization for promoting
Speech Communication Science and Technology
internationally. For membership and other information,
please contact the ISCA secretariat at:

c/o Institut fuer Kommunikationsforschung und Phonetik
Universitaet Bonn
Poppelsdorfer Allee 47
D-53115 Bonn, Germany
Fax: (+49) 228-735639
Email: info@isca-speech.org


Organizing Committee
* Christophe d'ALESSANDRO, LIMSI-CNRS, Orsay, France
* Klaus SCHERER, University of Geneva , Switzerland
* Nick CAMPBELL, ATR, Kyoto, Japan
* Boris DOVAL, LIMSI-CNRS, Orsay, France
* Nathalie HENRICH, LAM, Paris, France
* David SANDER, University of Geneva , Switzerland
* Blandine MOURON, University of Geneva , Switzerland

International Scientific Committee
* Paavo Alku, Helsinki University, Finland
* Veronique Auberge, ICP, Grenoble, France
* Gerrit Bloothooft, Utrecht University, The
* Noel Chateau, France Telecom, Lannion, France
* Maria-Gabriella Di Benedetto, Roma University, Italy
* Thierry Dutoit, Faculte Polytechnique, Mons, Belgium
* Adrian Fourcin, University College, London, UK
* Daniel Hirst, LPL, Aix-en-Provence, France
* Hideki Kasuya, Utsunomiya University, Japan
* Hideki Kawahara, Wakayama University, Japan
* Jody Kreiman, University of California at Los
Angeles, USA
* Jean-Sylvain Lienard, LIMSI-CNRS, Orsay, France
* Parham Mokhtari, JST-CREST, HIS-ATR, Tokyo, Japan
* Ailbhe NED Chasaide, CLCS, Trinity College, Dublin,
* Peter Pabon, Utrecht University, The Nederlands
* Kenneth Stevens, MIT, Cambridge, USA
* Jan Svec, The Denver Center for the Performing Arts,
Denver, USA
* Sten Ternstrom, KTH, Sweden

Supported by
* SynSIG
* SFA (Societe Francaise d'Acoustique)
* AFCP (Association Francophone de la Communication
* other societies forthcoming


Registration will be opened in April 2003.

Workshop fee

Regular fee (until June 30)        200 EUROS
Late registration (after June 30)  250 EUROS
Student fee (until June 30)        100 EUROS
Late student fee (after June 30)   150 EUROS

The workshop fee includes admission to the sessions,
CD-ROM, coffees, lunches, and a banquet dinner. Paper
proceedings will be available at an extra cost of 30
Euros per copy.

Students must present a verification of their
university affiliation and student status at the
workshop in order to be entitled to the reduced
conference fee.

The fees do not include personal Insurance:
participants are advised to make their own arrangements
regarding travel insurance and medical assistance
during the Workshop.

Participants are asked to manage their own
accommodation in Geneva. A limited number of rooms for
student accomodation are available at the "Cite
universitaire" :

Please contact directly the "Cite universitaire" by
Email for reservation.
Email : cite-uni@unige.ch

A list of hotels in the vicinity of the University will
be provided soon. For hotel information and on-line
reservation, please contact directly the  Geneva
tourist office http://www.geneve-tourisme.ch.

Cancellation of Registration
Notification of cancellation must be made in writing
and sent to the organizers. Registration cancellations
will be accepted until 14 July 2003, up to which date
the total amount will be refunded less 50 euro for
administrative expenses. For cancellations made after
14 July, 2003 we regret that no refunds can be made.


The following speech and singing databases are at your
disposal on the web site of the workshop for any
analysis you might find interesting for the workshop.
There are 5 databases built to study the great
diversity of voice quality that the human voice is able

to produce in the case of speech and singing.

Speech database 1 (American english)
* 1 male
* Sentence : "She has left for a great party today."
* Author : Christophe d'ALESSANDRO, (c)03, LIMSI-CNRS,

Speech database 2 (Japanese)
* 1 female
* Sentences : spontaneous speech, various sentences
* Author : Parham MOKHTARI, (c)00-03, ATR, Japan

Speech database 3 (French)
* 1 female
* Sentence : "Il est sorti avant le jour."
* Author : Blas PAYRI, (c)1999, LIMSI-CNRS, France

Singing database 1 (English)
* 1 male / 2 females, professional singers
* Phrase : short extract of the musicals "cats",
"belting" technique.
* Author : Nathalie HENRICH, (c)02, KTH, Stockholm,

Singing database 2 (French)
* 1 counter-tenor
* Sentence : "Vos mepris chaque jour."
* Author : Nathalie HENRICH, (c)01, LIMSI-CNRS/LAM,