INTERSPEECH 2012

Portland, U.S., 09-13 September 2012
Chair: Jan van Santen, Richard Sproat 
13th INTERSPEECH event

Top

Interspeech 2013 Lyon, France 23-29 August 2013 General Chair: Frédéric Bimbot

Top

 Interspeech 2014 will be held in Singapore, the Garden City, on 7-11 September 2014.

Conference Chair: Haizhou Li, Institute for Infocomm Research.

Top

ASRU 2011
Automatic Speech Recognition and Understanding Workshop
Big Island, Hawaii
December 11-15, 2011
http://www.asru2011.org
Demonstration Call for Proposals
> Deadline: September 15, 2011 <

The program committee for the 12th biannual IEEE workshop on Automatic Speech Recognition and
Understanding is accepting proposals for the Show & Tell demonstration session event that will be held
during the conference. The Demonstration session has become an exciting highlight of the ASRU
workshops. The event will include demonstrations of latest innovations by research groups in industry,
academia and government. Demonstrations can be related to any of the topics defined by ASRU:
• ASR / LV CSR Systems
• Language Modeling
• Acoustic Modeling
• Decoder Search
• Spoken Language Understanding
• Spoken Dialog Systems
• Multilingual Speech & Language Processing
• Robustness in ASR
• Spoken Document Retrieval
• Speech-to-Speech Translation
• Text-to-Speech Systems
• Speech Summarization
• New Applications of ASR
• Speech Signal Processing
The deadline for submission of Show & Tell demos proposals is September 15, 2011 with notification
of acceptance by September 29, 2011. Submissions will be mailed to the Demonstration Chairs.
Proposals should include the demonstration title, list of authors, and an abstract of no more than one
page. The abstract should clearly explain what is novel and innovative in the proposed demonstration.
Show & Tell demonstrations should have an interactive component (i.e., should be more than a simple
computer simulation or graph).
Each demonstration will be allotted one table, space for a poster, and a power outlet. Presenters are
responsible for all other equipment and shipping to and from the conference. At request wireless
Internet connection will also be available and, if you have special requirements, please contact the
Demonstration Chairs.
ASRU 2011
the Demonstration Chairs
Patrick Nguyen (e-mail: drpng@google.com)
Olivier Siohan(e-mail: siohan@google.com) 

Top

 ASRU 2011
            Automatic Speech Recognition and Understanding Workshop
                               Big Island, Hawaii
                              December 11-15, 2011
                            http://www.asru2011.org/

The deadline for submitting papers is 1 July 2011. The website will not accept any submissions after July 1st 11:59PM Hawaiian time. Please be sure to submit your papers by:

** Workshop overview and topics **
The twelfth IEEE workshop on Automatic Speech Recognition and Understanding (ASRU) will be held on December 11-15, 2011. The ASRU workshop meets every two years and has 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.

Submission of papers in all areas of human language technology is encouraged, with emphasis placed on:
- Automatic speech recognition and understanding
- Human speech recognition and understanding
- Speech-to-text systems
- Spoken dialog systems
- Multilingual language processing
- Robustness in ASR
- Spoken document retrieval
- Speech-to-speech translation
- Text-to-speech systems
- Spontaneous speech processing
- Speech summarization
- New applications of ASR

** Schedule **
Paper submission deadline: 1 July 2011
Paper acceptance/rejection: 20 August 2011
Early registration deadline: 15 October 2011
Workshop: 11-15 December 2011

** Technical Program **
The workshop program will consist of oral and poster presentations, including invited overview lectures covering major areas of the field.  In addition, there will be four keynote addresses by well-known experts on such related topics as machine learning and pattern classification.

** Submission Procedure **
Prospective authors are invited to submit full-length, 4-6 page papers, including figures and references, to the ASRU 2011 website (http://www.asru2011.org). All papers will be handled and reviewed electronically. The website will provide you with further details.  Please note that the submission dates for papers are strict deadlines.

** Registration and information **
Please note that the number of attendees will be limited and priority will be given to paper presenters. Registration will be handled via the ASRU 2011 website, http://www.asru2011.org/, where more information on the workshop will be available. 

Top

SemDial 2011 (Los Angelogue)

The 15th Workshop on the Semantics and Pragmatics of Dialogue

Los Angeles, September 21-23, 2011

http://projects.ict.usc.edu/nld/semdial2011

The SemDial series of workshops aims to bring together researchers working on the semantics and pragmatics of dialogue in fields such as artificial intelligence, computational linguistics, formal semantics/pragmatics, philosophy, psychology, and neuroscience. In 2011 the workshop will leave Europe for the first time, to be held at the Institute for Creative Technologies of the University of Southern California in Los Angeles. The SemDial workshops are always stimulating and fun, and L.A. is a great place to visit.

Invited Speakers:

Jerry Hobbs

David Schlangen

Additional invited speakers to be announced later

Call for Papers:

Submission is now open.

We invite papers on all topics related to the semantics and pragmatics of dialogues, including, but not limited to:

- Models of common ground/mutual belief in communication

- Modelling agents' information states and how they get updated

- Multi-agent models and turn-taking

- Goals, intentions and commitments in communication

- Semantic interpretation in dialogues

- Reference in dialogues

- Ellipsis resolution in dialogues

- Dialogue and discourse structure

- Interpretation of questions and answers

- Nonlinguistic interaction in communication

- Natural language understanding and reasoning in spoken dialogue systems

- Multimodal dialogue systems

- Dialogue management in practical implementations

- Categorisation of dialogue moves or speech acts in corpora

- Designing and evaluating dialogue systems

Submission is through Easychair:

http://www.easychair.org/conferences/?conf=semdial2011

On the submission site, choose the category that is the closest fit to your paper; categories are used for assigning papers to area chairs, who follow each paper through its review process (we may reassign papers to distribute the load among the chairs).

Submitted papers should be in the following format:

- Anonymous PDF file

- 8 pages total (including data, tables, figures, and references)

- US letter paper size

- 11pt Times font

- 1 inch (2.5 cm) margins

- 2-column format

Include a one-paragraph abstract of the entire work (about 200 words). We strongly recommend using the style files provided by ACL-HLT 2011.

Multiple submissions by the same author or group of authors are allowed, but each person may only give one oral presentation at the workshop.

Deadline for receipt of papers is June 5, 2011, at 23:59 UTC-11.

Posters and Demos:

We will have a separate submission of late-breaking system demonstrations and ongoing project descriptions, to be presented in a poster session during the workshop. Late-breaking submissions will be two pages long; they will not be refereed, but evaluated for relevance only by the area chairs. Submission of late-breaking abstracts will be allowed only after review of the main session papers has concluded. The deadline for late-breaking submissions is August 7, 2011.

Proceedings:

Final, 8-page versions of the accepted papers, together with the 2-page accepted late-breaking abstracts, will be compiled in a proceedings volume and distributed (online or in print) at the workshop.

Important Dates:

Paper submissions due: June 5, 2011 (Sunday)

Author notification for full papers: July 29, 2011 (Friday)

Poster and demo submissions due: August 7, 2011 (Sunday)

Author notification for posters and demos: August 12, 2011 (Friday)

Camera-ready copies due: August 24, 2011 (Wednesday)

SemDial 2011 workshop: September 21-23, 2011 (Wednesday--Friday)

Organizers:

Ron Artstein: Area chair Theoretical Linguistics, Logic, and Conversation Analysis

David DeVault: Area chair Natural Language Processing

Kallirroi Georgila: Area chair Natural Language Processing

Elsi Kaiser: Area chair Psycholinguistics

Amanda Stent: Area chair

David Traum: Internal coordinator

Sudeep Gandhe: Sponsorship and fundraising

Mark Core: Demos and posters

Anton Leuski: Web site

Program Committee:

Hua Ai, Jennifer Arnold, Srinivas Bangalore, Luciana Benotti, Nate Blaylock, Johan Bos, Harry Bunt, Donna Byron, Herb Clark, Paul Dekker, Myroslava Dzikovska, Raquel Fern‡ndez, Victor Ferreira, Simon Garrod, Jonathan Ginzburg, Amy Isard, Andrew Kehler, Alistair Knott, Kazunori Komatani, Staffan Larsson, Gary Lee, Oliver Lemon, Colin Matheson, Gregory Mills, Yukiko Nakano, Stanley Peters, Martin Pickering, Chris Potts, Matthew Purver, Antoine Raux, Hannes Rieser, David Schlangen, Elizabeth Shriberg, Gabriel Skantze, Ronnie Smith, Matthew Stone, Nigel Ward, Michael White

If you have any questions, please write to one of the organizers. We do not have a dedicated email address.

SemDial 2011 homepage: http://projects.ict.usc.edu/nld/semdial2011

SemDial series homepage: http://www.illc.uva.nl/semdial

Top

AISV - STELARIS (late)Summer School 2011, September 25^th-30^th

Software Tools and Methods for Advanced Research in Phonetics

http://www.aisv.it/summerschools/

The next AISV summer school, organized by AISV in collaboration with the Stelaris network, will take place at S. Marco di Castellabate (Salerno, Italy) on September 25th-30th 2011.

Confirmed teachers are Paul Boersma, Franco Cutugno, Sarah Hawkins, Mietta Lennes.

The maximum number of participants will be fixed at 30 (min to guarantee the budget 22). They will pay a fixed fee (600,00 €) inclusive of lodging, meals and scientific activities.

Themes:

1.     Advanced use of Tools for Phonetic Research (TBA)

2.     Scripting and/or complex procedures (Paul Boersma)

3.     Perceptual experiments, methods and tools (Sven Mattys)

4.     Data Modeling, querying and Information Retrieval (Francesco Cutugno)

5.     Methodology clinics: small groups discuss students' own research questions (Sarah Hawkins (coordination) together with all lecturers)

6.     Annotation, Labeling, Descriptive Systems (Mietta Lennes)

Please visit the website for more information.

Dott.ssa Rosita Lio

L@bphon - Laboratorio di Fonetica
c/o Dipartimento di Linguistica
Via P.Bucci - Cubo 20/A
87036 Arcavacata di Rende (CS)
Tel. (+39) 0984/494078
Fax (+39) 0984/494114
E-mail: labfonuc@unical.it
Home Page: http://www.linguistica.unical.it/labfon/Home.htm

Top

L'Ecole de Recherche Multimodale d'Information - Techniques & Sciences
[ERMITES],  édition VI,
se tient les 27, 28 et 29 septembre 2011, sur  Porquerolles la perle
des Iles D’Or - Var

Thème

' Décomposition parcimonieuse, abstraction et structuration
           pour l'analyse de scène acoustique complexe '

Orateurs confirmés :
Adam O. ; Bengio Y. ; Glotin H. ; Halkias X. ; Haton J.-P. ; Kowlaski
S. ; MALLAT S. : Razik J. ; Stylianou Y.

Organisée par le projet DYNI de l'UMR LSIS.
Soutenue par l'INRIA, CNRS LSIS, GDRI3-ARIA, AFCP, USTV.
Sous le patronage de la Fédération de Recherche en Informatique et
Interactions d’Aix-Marseille (FRIIAM)
et du PEPS IN2SI DYNI 'Indexation robuste à l’échelle'.

Les participants peuvent soumettre un résumé de leurs travaux, qui si
accepté sera présenté durant ERMITES et publié dans les actes.

-- PROGRAMME --
Ouverture dès 10h le 27 septembre, centre IGESA Porquerolles

*
J.-P. Haton  - Pr univ. Nancy - LORIA & IUF - http://www.loria.fr/~jph/

'Analyse de scène et reconnaissance stochastique de la parole'

Les difficultés spécifiques pour la reconnaissance de la parole sont
nombreuses: nombre variable de locuteurs connus ou inconnus,
microphones distants, bruit ambiant, effets liés aux locaux (écho,
réverbération).
Cet exposé rappelle les principes de la reconnaissance automatique de
la parole et présentera les niveaux fonctionnels d'un système : prise
de son, paramétrisation, analyses syntaxiques et sémantiques. Nous
insisterons sur les modèles stochastiques actuellement les plus
performants pour la reconnaissance de la parole.


*
Y. Stylianou – Pr univ. de Crête – ICS -
http://www.ics.forth.gr/netlab/stylianou.html

'Adaptive AM-FM decomposition of signals with applications to speech'

I will present an adaptive AM-FM decomposition of signals and will
comment its application to speech analysis, synthesis, and
modifications.
As an introduction, I will present the classic Sinusoidal model
showing its limitations in modeling non-stationary signals like
speech.
Then the iterative adaptive AM-FM decomposition algorithm will be
presented in the context of time-varying multi-component signals and
robustness issues against wrong initial conditions/hypotheses and
additive noise will be discussed on synthetic signals. Focusing in
speech, it will be shown that this decomposition results in a
high-resolution
time frequency representation of speech. Comparisons with Gauss-Newton
and Reassigned Spectrogram approaches will be presented.
Finally, possible applications on signals other than speech, like in
vocalizations from marine mammals will be shortly discussed.


*
M. Kowlaski - MC univ. Paris XI - L2S -
http://web1.lss.supelec.fr/perso/kowalski/

'Parcimonie et structures pour les décompositions des signaux dans des
dictionnaires temps-fréquence'

Les décompositions parcimonieuses et structurées des signaux dans des
dictionnaires de formes d'ondes peuvent s'obtenir par un modèle
explicite dans le domaine des coefficients.
On s'intéresse dans une première partie aux approches variationnelles,
où les normes mixtes permettent d'introduire des couplages sur les
coefficients préalablement organisés en groupes. L'optimisation des
fonctionnelles s'effectue alors par des algorithmes de seuillage
itératifs. En modifiant directement les opérateurs de seuillage, on
peut introduire plus de flexibilité sur le couplage des coefficients,
en particulier grâce à un Group-Lasso fenêtré.
Dans une seconde partie, on regardera des modèles de type
Bernoulli-Gaussien, éventuellement multi-varié, pour la décomposition
hybrides des signaux (aussi appelée décomposition en composantes
morphologiques). Une telle approche à l'avantage de fournir un
seuillage adaptatif des coefficients, et ainsi de s'affranchir des
réglages parfois fastidieux d'hyper-paramètres intervenant dans les
approches variationnelles.


*
Y. Bengio - Pr univ. Montréal - LISA -
http://www.iro.umontreal.ca/~bengioy/yoshua_en/

'Deep Unsupervised Learning of Representations'

Deep Unsupervised Learning of Representations et ferait un survol de
découvertes récentes dans le domaine de l'apprentissage non-supervisé
de représentations (surtout pour les images, transposable à
l'acoustique).
Nous montrerons en particulier cette approche dans le but d'apprendre
des abstractions de plus en plus haut niveau, et de découvrir les
facteurs explicatifs des variations présentes dans les données.


*
S. Mallat - Ecole X, CMAP - http://www.cmap.polytechnique.fr/~mallat/

'Scattering & Matching Pursuit for Acoustic Sources Separation'

Signal classes are usually invariant to groups of operators such as
translations or scalings, and to larger Lie groups of deformations.
Invariants and dimensionality reduction play major roles for
classification, as opposed to sparse complete representations.
Constructing invariants while keeping discriminant information deeply
constraints the representation. We introduce a non-linear invariant
representation, that reminds quantum scattering. It is implemented
through the architecture of a deep neural network, but learning is
needed at a single layer, and computed with O(N) operations. State of
the art results are shown for object classification of deformed
patterns and random textures. Part of this work is described in
http://arxiv.org/abs/1011.3023 .


*
J. Razik - MC univ. USTV LSIS - http://razik.univ-tln.fr/

'Apprentissage de dictionnaire : de la parole humaine au chant de baleine'

L'utilisation des méthodes de dictionary learning non supervisé a
montré dans le domaine de l'image être la méthode de l'état de l'art
pour des tâches de classification. Dans le domaine de la parole, nous
avons montré que ces méthodes permettent également de dépasser les
classiques modèles GMM en reconnaissance de phonèmes, tout en restant
non supervisé. Nous avons également étudié l'apprentissage non
supervisé par dictionary learning dans le cadre de l'analyse et la
découverte d'un lexique associé au chant des baleines. L'objectif est
d'obtenir des descripteurs plus génériques et plus efficaces que ceux
habituellement extraits. Ceci permet également de déterminer des
formes récurrentes dans la structure des chants entre les différents
individus d'une population et sur plusieurs années. Ces travaux menés
en collaboration avec S. Paris et H. Glotin sont illustrés de
démonstrations.


*
X. Halkias - Columbia univ., Rosa Lab & post-doc DYNI Univ. Sud-Toulon Var

'Detection and Tracking of Dolphin Vocalizations'

Audio processing has widely affected the field of animal bioacoustics.
Many audio engineers are now using their knowledge to advance ou r
understanding of the world that surrounds us and especially that of
animals. This work falls into that category, where the principles of
signal processing, communication theory and machine learning are used
to analyze the clandestine world of marine mammals and specif ically
dolphins.
In this talk, several algorithms are proposed for the successful
detection of dolphin calls in long recordings. Starting with the
simple and widely used thresholding detectors, several advancements
are proposed, based on the data, leading to more intricate classifiers
like Support Vector Machines (SVM) that are known for their
robustness.
Lastly, two systems for pitch extraction are provided. The first
system is based on a probabilistic framework and deals with the
extraction of dolphin whistle calls while providing a first attempt on
resolving simple overlaps. The second system assumes that the desired
calls have already been detected and proceeds to identify the pitch
for both whistle and burst calls using hierarchically driven Hidden
Markov Models (HMM).


*
O. Adam - Pr univ. Paris6 - LAM (Equipe Lutherie Acoustique Musicale)
et CNPS (Centre de Neuroscience de Paris-Sud) -
http://www.cb.upsud.fr/Olivier.htm

'Estimation de densité de population de baleine par analyse de leurs chants'

L’étude des cétacés passe par leurs observations. Plusieurs méthodes
sont possibles et récemment le recours à l’acoustique passive a montré
un grand intérêt, soit pour des observations d’espèces discrètes et/ou
pour des observations à distance et/ou pour des observations
continues.
Les techniques développées, relevant de l’acoustique sous-marine,
l’instrumentation, du traitement du signal, de la reconnaissance des
formes, ont pour but de détecter les sons émis par ces mammifères
marins, de les classer, et de localiser lorsque cela est possible.
Nous présenterons une nouvelle activité dans ce domaine qui consiste à
estimer la taille du groupe de cétacés à partir de leurs émissions
sonores et des extrapolations statistiques. Plusieurs exemples sur
différentes espèces seront présentés comme illustrations.


*
H. Glotin - Pr univ. USTV - LSIS & IUF - http://glotin.univ-tln.fr

'Suivi de cachalot par acoustique passive'

Nous posons la problématique de l'analyse de scène acoustique au
travers de la structuration de signaux bioacoustiques acquis dans des
conditions variables. Nous nous intéresserons essentiellement au plus
grand des odontocètes, le cachalot (45 tonnes, 18 mètres de long). Cet
extraordinaire plongeur, qui sonde plus d'une heure à moins 2000
mètres, possède le biosonar le plus puissant.
Avec plusieurs canaux (ici 4 hydrophones), nous montrons qu'il est
possible de reconstruire la trajectoire de ses plongées écoutées à
plusieurs kilomètres (voir démonstrations 3D
http://glotin.univ-tln.fr/PIMC/DEMO et
http://lsis.univ-tln.fr/tcan/pimc/ ).
Nous montrons aussi que d'autres informations sont mesurables sur un
seul canal, comme la taille de l’animal, son comportement. Des
démonstrations sont faites sur des signaux que nous avons enregistrés
au large de Porquerolles cette année, et sur des bases de référence de
la communauté bioacoustique enregistrés au large des Bahamas par
l'AUTEC

==

Inscription :

Les pré-inscriptions sont ouvertes dès maintenant par simple email à
ermites@univ-tln.fr renseignant le type d'inscription, votre
téléphone, email et affiliation.
Les places seront limitées aux trente premiers à avoir validé leur
inscription par paiement à l'AFCP avant le 26 août (détails :
http://glotin.univ-tln.fr/ERMITES11 ).

==

Tarifs :

A/  Formule pension complète (incluant 2 nuitées, 5 repas, 2 pts déj,
pauses café / boissons, actes papier, en chambre studio 2 lits / salle
de bain) :
A1/ Doctorant, Postdoc, Master = 280 euros,
A2/ Autre = 410 euros.

B/  Formule journée avec repas midi, actes, pauses café / boisson :
B1/ Doctorant, Postdoc, Master = 70 euros,
B2/ Autres = 100 euros.

==

Comité de Programme :
H. Glotin (prés.), Pr univ. Sud-Toulon Var & IUF, LSIS DYNI
S. Paris, MC univ. Aix-Marseille, LSIS DYNI
J. Razik, MC univ. Sud-Toulon Var, LSIS DYNI
Y. Bengio, Pr univ. Montréal, LISA
S. Mallat, Ecole Polytechnique
O. Adam, Pr univ. Paris VI, LAM
Y. Stylianou, Pr univ. de Crête
J.-P. Haton, univ. Nancy & IUF, LORIA

Comité d’Organisation :
S. Paris (prés.)
J. Razik
H. Glotin
F. Chamroukhi, MC USTV, LSIS DYNI
R. Abeille, doctorant USTV, LSIS DYNI
M. Chouchane, doctorant, LSIS DYNI
R. Delaye, ingénieur du son,
P. Machart, doctorant LSIS DYNI & LIF
F. Bénard, doctorant LSIS DYNI
Y. Doh, master, LSIS DYNI

==

Contexte général d'ERMITES :
L’Ecole Recherche Multimodale d’Information : Technologies et Sciences
fait intervenir, sur 3 jours, devant des chercheurs et ingénieurs en
devenir, une dizaine de spécialistes qui travaillent sur les analyses
conjointes de textes, images, sons et vidéos pour en extraire de
l’information. La recherche d’information est de plus en plus complexe
et hasardeuse compte tenu du volume sans cesse croissant des
informations disponibles et de leur nature multimodale (images, sons,
musique, parole, bio-acoustique, vidéos…). Nous avons décidé
d’organiser ERMITES 2011 avec l'USTV, le support de l'UMR Laboratoire
des Sciences de l’Information et des Systèmes (LSIS), du CNRS, de
l'INRIA, du GDRI3-ARIA, du CNRS et LSIS, afin :
- d’analyser les dernières avancées théoriques, et pratiques, des
systèmes robustes de recherche d’information multimodale de grande
dimension et sur des masses de données,
- de montrer que ces nouveaux outils forment une base pour une domaine
plus vaste que celui  d’origine pour lequel ils ont été développés
(plus particulièrement leur application au domaine audio et
audio-vidéo),
- de sensibiliser les jeunes scientifiques au vaste champ scientifique
mis en jeu par ces nouvelles avancées aux problèmes de fiabilité,
robustesse, apprentissage, sous contrainte du passage à l'échelle.
Chaque spécialiste présentera un condensé de son savoir. L'esprit
d’ERMITES étant de mettre l'accent sur les analyses jointes
(transversales sur diverses modalités), ceci étant un défi majeur et
encore peu pris en compte par la majorité des équipes qui restent
plutôt dans le pré carré de leur spécialité de départ.

Site web de l'édition 2010 avec actes audiovisuels :
http://glotin.univ-tln.fr/ERMITES10

SITE WEB 2011 : http://glotin.univ-tln.fr/ERMITES11

Top

Le Laboratoire de Phonétique et Phonologie, dans le cadre de l'ANR SLBL-08-JCJC-0127 et des séminaires de recherche SRPP, a le plaisir de vous convier à un workshop autour de la syllable le mercredi 28 septembre 2011.

La demi-journée se déroulera au LPP, 19 rue des Bernardins, 75005 Paris (plan d'accès sur http://lpp.univ-paris3.fr/), salle Rousselot (1er étage) :

10h: Accueil autour d'un café

10h30 : Nathalie Vallée (Gipsa-lab, Grenoble) : Phonetic and Phonological Asymetries in Syllable

11h30 : Louis Goldstein (Haskins Laboratories &University of Southern California) : Coupling graph model of syllable structure

12h30 : Discussion générale

Top

1ere annonce : 4eme JEFP le 29 septembre à Paris sur « Le développement de la perception: du signal aux unités phonologiques » **

**Attention: le nombre de place limité, merci de vous inscrire avant le 19 septembre**

Bonjour,

L'année universitaire commence avec une nouvelle édition des Journées d'Etude et de Formation sur la Parole, dès septembre.

Cette année, les 3 volets des JEFP auront un thème commun 'la perception de la parole', et ils se dérouleront lors de 3 journées exceptionnelles durant l'année 2011-2012.

Ces journées, soutenues par l'Association Française de Communication Parlée, ont pour objectif de permettre aux doctorants d'avoir l'occasion de se familiariser aux habitudes, objets, méthodes et questionnements des disciplines ayant pour étude la parole.

La quatrième édition des JEFP aura lieu le jeudi 29 septembre de 10h à 17h45 au Laboratoire de Phonétique et Phonologie situé 19 rue des Bernardins 75005 PARIS. (accueil à partir de 9h15)

Le thème de cette journée sera 'le développement de la perception: du signal aux unités phonologiques'.

La journée sera animée par Pierre Hallé (chercheur au Laboratoire de Phonétique et de Phonologie) et Willy Serniclaes (chercheur au Laboratoire Psychologie de la Perception) qui reviendront sur des éléments théoriques relatifs à la perception inter-langues, au développement de la perception et sur des notions de psychoacoustique.

Lors de travaux dirigés, Coralie Vincent (Ingénieure à Paris 8) abordera les diverses distorsions que peut subir un signal ou comment avoir de bon stimuli pour ses recherches et Erwan Pépiot (doctorant à Paris) montrera comment développer un test sur la perception de la syllabation avec le logiciel Perceval.

Ces journées sont entièrement gratuites. Pour pouvoir y participer il suffit de s'inscrire à l'adresse suivante:

http://jefp.univ-avignon.fr/inscription.php

ou d'envoyer un mail à

laurianne.georgeton@univ-paris3.fr

en précisant vos nom, prénom, statut (doctorant, chercheur, autre) et institution à laquelle vous êtes rattachés.

Un nombre conséquent de bourses AFCP sont disponibles pour le remboursement (total ou partiel) de vos frais de transport, le remboursement se fera sur pièces justificatives après la journée. Merci de nous prévenir lors de votre inscription si vous souhaitez bénéficier d’une bourse de transport et de nous donner une idée du montant.

Bonne rentrée à tous.

Laurianne Georgeton pour l'organisation des JEFP

Laurianne Georgeton Doctorante contractuelle avec mission d'enseignement Laboratoire de Phonétique et de Phonologie 19 rue des bernardins, 75005 Paris 0680175770

Top

SiPS 2011
IEEE Workshop on Signal Processing Systems
October 4-7, 2011, Beirut, Lebanon
Preliminary Call for Papers
http://www.sips11.org/

The objective of this workshop is to provide a forum for discussion of new developments, recent progress, and innovations in the design and implementation of digital signal processing systems. It addresses all aspects of architecture and design methods of these systems. Emphasis is on current and future challenges in research and development in both academia and industry. Hard-bound proceedings of the workshop will be published. Original and unpublished papers are solicited in the following areas, but not limited to:

VLSI Based Design and Implementation of Signal Processing Systems
-Low-power signal processing circuits and applications
-High performance VLSI systems
-FPGA and reconfigurable architecture based systems
-System-on-chip and network-on-chip
-VLSI Systems for Wireless Sensor Network and RF Identification Systems
 
Software Based Design and Implementation of Signal Processing Systems
-Programmable digital signal processor architecture and systems
-Application specific instruction-set processor (ASIP) architecture and systems
-SIMD, VLIW and multi-core CPU architecture
-Graphic processing unit (GPU) based massively parallel implementation

Design Methods of Signal Processing Algorithms and Architectures 
-Optimization of signal processing algorithms
-Compilers and tools for signal processing system design
-Algorithm transformation and algorithm-to-architecture mapping

Signal Processing Application Systems
-Audio, speech and language processing
-Biomedical signal processing and bioinformatics
-Image, video and multimedia signal processing
-Information forensics, security and cryptography
-Machine learning for signal processing
-Sensing and sensor signal processing
-Wireless communications and networking
-Coding and Compression
-Multiple-Input-Multiple-Output (MIMO) and Communication Systems
-Software Defined Radio

Emerging Technologies
-Vehicular ad hoc networks (VANET)
-Cognitive radio networks
-Bio-inspired networks
-Context-aware mobile networking
-Wireless body area networks (WBANs)
-Tele-medicine/e-health networks

Important Dates
Paper submission          April 9
Acceptance notification   June 27
Final version due         July 25

Best Student Paper Contest: The finalist papers will be presented in a poster session during an evening reception on Tuesday October 4th. The papers will be judged based on both manuscript and presentation. The finalist papers will have free student registration and certificate. The top three winning papers will be announced during lunch on Thursday October 6th.

Special Issue: Selected papers will be considered for publication in a Special Issue of the Journal of VLSI on Signal Processing Systems for Signal, Image and Video Technology, Springer Publisher.

Details on author schedules, submission, program and venue are available on the workshop website: http://www.sips11.org/

General Chairs:
Magdy Bayoumi
University of Louisiana at Lafayette

Ibrahim Hajj
American University of Beiru

Technical Program Chairs:
Mohammad Mansour
American University of Beirut

Brian L. Evans
University of Texas at Austin

Industry Liaison Chair:
Khaled El-Maleh
Qualcomm

Administration Committee:
Ahmed Abdelgawad
University of Louisiana at Lafayette

Sponsored by:
IEEE Signal Processing Society
IEEE Circuits and Systems Society

Top

2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
                   Mohonk Mountain House
                    New Paltz, New York
                    October 16-19, 2011

                   http://www.waspaa.com

The 2011 IEEE Workshop on Applications of Signal Processing to Audio
and Acoustics (WASPAA'11) will be held at the Mohonk Mountain House in
New Paltz, New York, and is sponsored by the Audio and Acoustic Signal
Processing committee of the IEEE Signal Processing Society. The
objective of this workshop is to provide an informal environment for
the discussion of problems in audio and acoustics and signal
processing techniques leading to novel solutions. Technical sessions
will be scheduled throughout the day. Afternoons will be left free for
informal meetings among workshop participants.

Papers describing original research and new concepts are solicited for
technical sessions on, but not limited to, the following topics:

Acoustic scenes
 * Source separation and localization
 * Signal enhancement: Echo cancellation, dereverberation,
    noise reduction, restoration
 * Microphone arrays
 * Multichannel audio acquisition and reproduction
 * Room acoustics

Music and environmental audio
 * Musical signal analysis: Segmentation, classification, transcription
 * Creation of musical sounds: Waveforms, instrument models, singing
 * Audio matching and retrieval

Audio coding
 * Waveform coding and parameter coding
 * Spatial audio coding
 * Sparse representations
 * Mobile devices
 * Digital rights

Hearing and perception
 * Auditory perception
 * Spatial hearing
 * Quality assessment
 * Hearing aids


Important Dates:

Submission of four page paper:     May 13, 2011
Notification of acceptance:        July 15, 2011
Early registration open until:     August 31, 2011


Organizing Committee:

General Chair             Dan Ellis, Columbia University
Technical Program Chair   Paris Smaragdis, UIUC & Adobe Systems Inc
Finance Chair             Michael Brandstein, MIT Lincoln Labs
Publications Chair        John McDonough, Disney Research
Publicity Chair           Michael Mandel, Audience, Inc
Local Arrangements Chair  Bhiksha Raj, Carnegie Mellon University
Far East Liaison          Shigeki Sagayama, University of Tokyo

Top

CALL FOR PAPERS
 
Oriental COCOSDA 2011
 
October 26-28, 2011, National Chiao Tung University, Hsinchu, Taiwan
http://ococosda2011.cm.nctu.edu.tw

===========================================================

        The oriental chapter of COCOSDA (The International Committee for the
Co-ordination and Standardization of Speech Databases and Assessment
Techniques) is pleased to announce that the 14th Oriental COCOSDA Conference
will be held on Oct. 26-28, in Hsinchu, Taiwan hosted by the National Chiao
Tung University, Taiwan. Oriental COCOSDA is an international conference
held annually by the oriental chapter of COCOSDA. The first preparatory
meeting was held in Hong Kong in 1997 and then the past thirteen workshops
were held in Japan, Taiwan, China, Korea, Thailand, Singapore, India,
Indonesia, Malaysia, Vietnam, Japan, China and Nepal.
 
        Oriental COCOSDA conference in Taiwan will help in boosting the
research and development in the field of Speech Technology and will help in
enthusing the interest towards Speech Technology in East and Southeast Asia.
 
        Papers are invited on substantial, original and unpublished research
on all aspects of speech databases, assessments and speech I/O, including,
but not limited to:

Topics

• Speech databases and text corpora
• Assessment of speech input and output technologies
• Phonetic/phonological systems for Oriental languages
• Romanization of Non-Roman Characters
• Segmentation and labeling
• Speech Prosody and Labeling
• Speech processing models and systems
• Multilingual speech corpora
• Special topics on speech databases and assessments
• Standardization
• Any other relevant topics
 
Important Dates

•Full Paper Submission                     July, 1,  2011
•Notification of acceptance of paper          Aug. 5, 2011
•Final Manuscript                         Aug. 26, 2011

Top

2011 INTERNATIONAL FALL SCHOOL IN FORMAL LANGUAGES
AND APPLICATIONS

FSFLA 2011

(formerly International PhD School in Formal Languages and Applications)

Tarragona, Spain

October 31 – November 4, 2011

Organized by:
Research Group on Mathematical Linguistics
Rovira i Virgili University

http://grammars.grlmc.com/fsfla2011/

*********************************************************************

ADDRESSED TO:

Undergraduate and graduate students from around the world. Most appropriate degrees include: Computer Science and Mathematics. Other students (for instance, from Linguistics, Electrical Engineering, Molecular Biology or Logic) are welcome too provided they have a good background in discrete mathematics.

The School is appropriate also for people more advanced in their career who want to keep themselves updated on developments in the field.

There will be no overlap in the schedule of the courses.

The previous event was SSFLA 2011 (http://grammars.grlmc.com/ssfla2011/).

COURSES AND PROFESSORS:

- Franz Baader (Technische Dresden), Reasoning in Description Logics [intermediate, 6 hours]
- Manfred Droste (Leipzig), Weighted Automata and Weighted Logic [introductory/advanced, 8 hours]
- Max H. Garzon (Memphis), DNA Codeword Design and DNA Languages [introductory/intermediate, 10 hours]
- Venkatesan Guruswami (Carnegie Mellon), The Complexity of Approximate Constraint Satisfaction [intermediate, 6 hours]
- Tao Jiang (California Riverside), Average-case Analysis and Lower Bounds by the Incompressibility Method [intermediate, 6 hours]
- Michael Moortgat (Utrecht), Type-logical Grammars: Expressivity, Parsing Complexity [introductory/advanced, 8 hours]
- Helmut Seidl (Technische München), Macro Treetransducers for XML Processing [intermediate, 6 hours]
- Alan Selman (Buffalo), Probabilistic Complexity Classes [intermediate, 10 hours]
- Jeffrey Shallit (Waterloo), Automatic Sequences, Decidability, and Enumeration [intermediate, 6 hours]

SCHOOL PAPER:

On a voluntary basis, within 6 months after the end of the School, students will be expected to draft an individual or jointly-authored research paper on a topic covered during the classes under the guidance of the lecturing staff.

REGISTRATION:

It has to be done on line at

http://grammars.grlmc.com/fsfla2011/Registration.php

FEES:

They are variable, depending on the number of courses each student takes. The rule is:

1 hour = 

- 10 euros (for payments until July 31, 2011), 
- 15 euros (for payments after July 31, 2011). 

The fees must be paid to the School's bank account: 

Uno-e Bank (Julian Camarillo 4 C, 28037 Madrid, Spain): IBAN: ES3902270001820201823142 – Swift/BIC code: UNOEESM1 (account holder: Carlos Martin-Vide GRLMC; account holder's address: Av. Catalunya, 35, 43002 Tarragona, Spain)

Please mention FSFLA 2011 and your full name in the subject. A receipt will be provided on site. Bank transfers should not involve any expense for the School.

For early reduced rates, please notice that the date that counts is the date of the arrival of the fees to the School’s account.

People registering on site at the beginning of the School must pay in cash. For the sake of local organization, however, it is much recommended to complete the registration and the payment earlier.

ACCOMMODATION:

Information about accommodation is available on the website of the School.

CERTIFICATES:

Students will be delivered a certificate stating the courses attended, their contents, and their duration. Those participants who will choose to be involved in a research paper will receive an additional certificate at the completion of the task, independently on whether the paper will finally get published or not.

IMPORTANT DATES:

Announcement of the programme: June 4, 2011
Starting of the registration: June 4, 2011
Early registration deadline: July 31, 2011
Starting of the School: October 31, 2011
End of the School: November 4, 2011 

QUESTIONS AND FURTHER INFORMATION:

Lilica Voicu: florentinalilica.voicu@urv.cat 

WEBSITE:

http://grammars.grlmc.com/fsfla2011/ 

POSTAL ADDRESS:

FSFLA 2011
Research Group on Mathematical Linguistics
Rovira i Virgili University
Av. Catalunya, 35
43002 Tarragona, Spain

Phone: +34-977-559543
Fax: +34-977-558386

ACKNOWLEDGEMENTS:

Diputació de Tarragona
Universitat Rovira i Virgili

Top

Deadline extended to August 9

The 5th Language and Technology Conference (LTC 2011), November 25-27, 2011, Poznań, Poland

CALL FOR PAPERS The 5th Language and Technology Conference (LTC'11), a meeting organized by the Faculty of Mathematics and Computer Science of Adam Mickiewicz University, Poznań, Poland in cooperation with the Adam Mickiewicz University Foundation, will take place on November 25-27, 2011. Since very beginning the meetings of the LTC series continue to address Human Language Technologies (HLT) as a challenge for computer science, linguistics and related fields. Fostering language technologies and resources remains an important mission in the dynamically changing information-saturated world. We aim at contributing to this mission and we invite you to join us in that at LTC'11 in November 2011, traditionally held in Poznań, Poland.

CONFERENCE TOPICS The conference topics include the following (the ordering is not significative): * electronic language resources and tools * formalization of natural languages * parsing and other forms of NL processing * computer modeling of language competence * NL user modeling * NL understanding by computers * knowledge representation * man-machine NL interfaces * Logic Programming in Natural Language Processing * speech processing * NL applications in robotics * text-based information retrieval and extraction * question answering * tools and methodologies for developing multilingual systems * translation enhancement tools * corpora-based methods in language engineering * WordNet-like ontologies * methodological issues in HLT * language-specific computational challenges for HLTs (especially for languages other than English) * validation in all areas of HLTs * HLT standards and best practices * HLTs as a support for foreign language teaching * HLTs as support for e-learning * communicative intelligence * legal issues connected with HLTs (problems and challenges) * contribution of HLTs to the Homeland Security problems (technology applications and legal aspects) * visionary papers in the field of HLT * HLT related policies * system prototype presentations This list is by no means closed and we are open to further proposals. Please do not hesitate to contact us in order to feed us with your suggestions and ideas of how to satisfy your expectations concerning the program. The Program Committee is also open to suggestions concerning accompanying events (workshops, exhibits, panels, etc). Suggestions, ideas and observations may be addressed directly to the LTC Chair by email (vetulani@amu.edu.pl ). Language: The conference language is English Contact: ltc@amu.edu.pl Paper submission The conference accepts papers in English. Papers (5 formatted pages in the conference format) are due by June 20, 2011 (midnight, any time zone) and should not identify the author(s) in any manner. In order to facilitate submission we have decided to reduce the formatting requirements as much as possible at this stage. Please, however, do observe the following: 1. Accepted fonts for texts are Times Roman, Times New Roman. Courier is recommended for program listings. Character size for the main text should be 10 points, with 11 points leading (line spacing). 2. Text should be presented in 2 columns, 8,42 cm each with 0,95 cm between columns (gutter). 3. The document size is 5 pages formatted according to (1) and (2) above. 4. The use of PDF format is strongly recommended, although MS Word will also be accepted. (Please no latex and other formats) You may also use the templates (ELRA/LREC based format), to be found at http://www.ltc.amu.edu.pl (soon). Detailed guidelines for the final submission of accepted papers will be published on the conference web site before September 12, 2011. All submissions are to be made electronically via the LTC'11 web submission system (EasyChair). Acceptance/rejection notification will be sent by September 12, 2011.

PUBLICATION POLICY Acceptance will be based on the reviewers' assessments (anonymous submission model). The accepted papers will be published in the conference proceedings (hard copy, with ISBN number) and on CD-ROM. The abstracts of the accepted contributions will also be made available via the conference page (during its lifetime). Publication requires full electronic registration and payment of the conference fee (full registration) by at least one of the co-authors before October 12, 2011. A post-conference volume with extended versions of selected papers is planned to be published. As this was the case for post-LTC'07 (v. 5603) and LTC'09 (v. 6562), it is planned to publish them in the Springer series Lecture Notes in Artificial Intelligence.

IMPORTANT DATES/DEADLINES * Deadline for submission of papers for review: June 20, 2011 * Acceptance/Rejection notification: September 12, 2011 * Deadline for submission of final versions of accepted papers: October 12, 2011 * Conference: November 25-27, 2011

REGISTRATION Only electronic registration will be possible. Details will be published at www.ltc.amu.edu.pl.

CONFERENCE FEES Non-student participants: Regular registration fee (payment before October 13, 2011) 190 EURO Late registration fee (payment after October 12, 2011) 240 EURO Student participants: Regular registration fee (payment before October 13, 2011) 120 EURO Late registration fee (payment after October 12, 2011) 160 EURO To be entitled to student rates the participant must present a student identity card (or equivalent document)valid on June 20, 2011. The conference fee covers: * participation in the scientific program * conference materials * proceedings on CD and paper * social events (banquet,...) * coffee breaks

EXHIBITIONS AND SPECIAL EVENTS *Poster forum* Although all accepted papers will be presented by the authors in the traditional, standard way (oral presentation + discussion), the organizers will offer to the authors an additional opportunity to present (mini) posters containing the abstract and the key ideas of the paper. Posters will be presented by the organizers during the LTC in the conference area. No extra fee will be charged for this form of presentation. The poster size will be A1, horizontal. (Notice. The Poster forum should not be confused with traditional poster sessions. In particular, there will be no limited presentation time and the posters do not have to be accompanied by the authors) *Hyde park corner* We intend to arrange 'A Hyde Park Corner' for non-reviewed presentations and positions. Limited number of presentations (depending on the available space) will be accepted. The content must meet the conference scope and aims. Both form and content must conform to the Polish and International Law. Texts will be presented on the sole responsibility of the authors/presenters and will not be published or reproduced in the Conference documents. *A book exhibition* is intended (call for exhibitors in preparation). Also, registered participants are invited to bring hard copies of their papers and books. We plan to make special presentations of the achievements of the conference participants, irrespective of whether they are directly related to the conference topic. *Tutorials* A tutorial program is under construction. *Special events.* Besides the standard conference presentation of papers, the Organizers are open to various kinds of initiatives (expos, demos, satellite workshops, panels, awards). A program of special events is now under construction. You are welcome to contact us with your suggestions.

AWARDS FOR BEST STUDENT PAPERS As at the 2nd, 3rd and 4th Language and Technology Conferences (2005, 2007, 2009) special awards will be granted to the best student papers. The regular or PhD students (on the date of paper submission) are concerned. Co-authored papers will be considered provided that the students' contributions exceeds 60% and that the main author(s) is (are) student(s)(this fact must be documented by a written declaration signed by all co-authors). In 2005 the Jury, composed of the Program Committee members present at the conference, awarded this distinction to: Ronny Melz (University of Leipzig, Germany), Hartwig Holzapfel (University of Karlsruhe, Germany), Marcin Woliński (IPI PAN, Warsaw, Poland). In 2007 this distinction went to Daria Fišer (University of Ljubljana) In 2009 two awards were granted: to Mahmoud EL-Haj (University of Essex, UK) and Alexander Pak (LIMSI-CNRS, Orsay, France). VISAS Participants from some non-EC countries may need visas to enter the Polish territory. Visa delivery is exclusively in competence of the Visa Authorities of the Schengen Convention countries. If you have any doubts, we recommend you to check your situation with the nearest Polish Consulate in your residence country. If you are author (co-author) of an accepted paper, we can confirm - if necessary - that we expect your presence at the conference for paper presentation. Upon request, we may also write a confirmation letter (in Polish) directly to the Polish Consulate indicated by you. To do this we will need a request letter (e-mail) from you in which you will provide us with the address of the Consulate you wish us to contact. To get information about countries whose citizens are not required to have a visa when entering Poland and to find important telephone numbers you may also visit the web site of the Polish Ministry of Foreign Affairs (see Consular Information ) Conference location: Poznań, Poland. Further details will be announced soon at http://ltc.amu.edu.pl.

ACCOMODATION There are several large scale events in Poznań at the LTC 2009 time (November 25-27, 2011). Therefore, we strongly recommend you to make hotel reservation in advance. There are several standard possibilities to book via Internet. Also, a special offer for Conference participants has been prepared by the travel agency Zimny (zimny@zimny.pl ). OTHER MANY important information will is provided at http://ltc.amu.edu.pl. Please check it from time to time and do not hesitate to ask questions at ltc@amu.edu.pl.

Top

International Symposium on Audiovisual Detection of Errors in
Pronunciation Training (IS ADEPT)
Cairo University, Egypt
4-6 December 20011

www.speech.kth.se/isadept

The aim of this symposium is to bring together academia and industry
within the field of Computer Assisted Pronunciation Training in order
to reach a common understanding of the current state-of-the-art in
pronunciation error analysis and identifying needs and paths for
future research.

Keynote speakers
Lewis Johnson, Chief scientist at Alelo Inc.
Horacio Franco, Speech Technology & Research Laboratory SRI International
Gary Pelton, VP Carnegie Speech
Helmer Strik, Radboud University Nijmegen
Silke Witt-Ehsani, Vice President, TuVox Design Center
Florian Hoenig, University of Erlangen

Invited speakers will give presentations focusing on overviews of
automatic pronunciation detection methods in commercial applications
and research projects, ongoing development of pronunciation analysis
algorithms, and the pedagogical or pragmatic needs in future
development.

Paper submissions
Prospective participants should submit a full 4 or 6 page paper, or a
1 page demo proposal. Please refer to www.speech.kth.se/isadept for
the list of topics.

Important Dates
Paper Submission 10 September 2011
Notification of Acceptance 10 October 2011
Camera-Ready Paper 4 November 2011
Registration Deadline 4 November 2011

Social program
The program includes a symposium river cruise dinner on the Nile, an
excursion to the nearby pyramids in Giza and common lunches during the
symposium.

www.speech.kth.se/isadept
isadept2011@speech.kth.se


********************************
International Symposium on Audiovisual Detection of Errors in
Pronunciation Training (IS ADEPT)
Cairo University, Egypt
4-6 December 20011

www.speech.kth.se/isadept

Call for Papers
IS ADEPT is a symposium jointly organized by the Centre for Speech
Technology, KTH, Stockholm, Sweden and the Faculty of Computers and
Information (FCI), Cairo University, Egypt with the support of the
Arabic Language Technology Center (ALTEC).

Scope
The aim of this symposium is to bring together academia and industry
within the field of Computer Assisted Pronunciation Training. That is,
on the one hand, researchers working on methods to create and evaluate
algorithms for automatic detection and analysis of language learners'
pronunciation errors and, on the other, representatives from companies
marketing language learning software. The goal is to reach a common
understanding of the current state-of-the-art in pronunciation error
analysis and identifying needs and paths for future research.

Keynote speakers
Lewis Johnson, Chief scientist at Alelo Inc.
Horacio Franco, Speech Technology & Research Laboratory SRI International
Gary Pelton, VP Carnegie Speech
Helmer Strik, Radboud University Nijmegen
Silke Witt-Ehsani, Vice President, TuVox Design Center
Florian Hoenig, University of Erlangen

Invited speakers will give presentations focusing on overviews of
automatic pronunciation detection methods in commercial applications
and research projects, ongoing development of pronunciation analysis
algorithms, and the pedagogical or pragmatic needs in future
development.

Paper submissions
Prospective participants should submit a full 4 or 6 page paper, or a
1 page demo proposal. Both types of submissions will be reviewed by
members of the scientific committee.

Important Dates
Paper Submission 10 September 2011
Notification of Acceptance 10 October 2011
Camera-Ready Paper 4 November 2011
Registration Deadline 4 November 2011
Symposium Dates 4-6 December 2011

Topics (non-exhaustive)
Automatic pronunciation scoring
Automatic pronunciation error detection and analysis
Audiovisual methods for pronunciation analysis
Articulation-based pronunciation analysis
Evaluation of pronunciation analysis algorithms
Evaluation of commercial products
Technology vs. pedagogy: match and misses
Feedback based on automatic pronunciation analysis
Robustness and portability of analysis methods (exercises, speakers,
dialects, languages)
Effect of intonation/stress on pronunciation errors

Social program
One aim of the symposium is to promote future exchange between the
participants and a social program will be organized in order to allow
for more informal discussions and exchanges of ideas. The program
includes a symposium river cruise dinner on the Nile, an excursion to
the nearby pyramids in Giza and common lunches during the symposium.

Registration fees
$250, $150 for students

www.speech.kth.se/isadept
isadept2011@speech.kth.se

Top

     8th International Workshop on Spoken Language Translation

             (IWSLT 2011)

 

First Call for Participation

 

December 8-9, 2011

    San Francisco, CA, USA

 

      http://www.iwslt2011.org 
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

 

The International Workshop on Spoken Language Translation (IWSLT) is a yearly scientific workshop, associated with an open evaluation campaign on spoken language translation, where both scientific papers and system descriptions are presented. The 8th International Workshop on Spoken Language Translation will take place in downtown San Francisco, 8-9 December 2011.

 

=== Scientific Papers ===

 
The IWSLT invites submissions of scientific papers to be published in the workshop proceedings and presented at the workshop, either in oral or poster form. The workshop welcomes high quality contributions covering theoretical and practical issues in the field of machine translation (MT), in general, and spoken language translation (SLT), Automatic Speech Recognition (ASR), and Text-to-Speech Synthesis (TTS), in particular. Possible topics include, but are not limited to:

-       MT and SLT approaches and evaluation

-       Integration of ASR and MT

-       Language resources for MT and SLT

-       Open source software for MT and SLT

-       Adaptation in MT

-       Simultaneous speech translation

-       Speech translation of lectures

-       Efficiency in MT

-       Stream-based algorithms for MT

-       Multilingual ASR and TTS

-       Rich transcription of speech for MT

-       Translation of on-verbal events

 
Important dates:

 - Paper submission due                 30 September 2011

 - Notification of acceptance                       31 October 2011

 - Camera-ready paper due                       11 November 2011


========================
=== Evaluation Campaign ===
========================


The IWSLT 2011 Evaluation Campaign will focus on the translation of TED Talks, a collection of public speeches on a variety of topics. Four tracks are organized addressing different research tasks:

·      ASR track: automatic transcription of talks from audio to text (in English)

·      SLT track: speech translation of talks from audio (or ASR output) to text (from English to French)

·      MT track: text translation of talks (from English to French, Arabic to English, and Chinese to English)

·      SC track: system combination of ASR outputs (in English) and MT outputs (in English and French)


Training of MT systems and language models for ASR is constrained to data supplied by the organizers. Supplied training, development, and test data will be available under the workshop’s webpage.
 

Important dates: 

-       01 Sep 2011 - Release of ASR test data

-       11 Sep 2011 - Submission of ASR runs

-       13 Sep 2011 - Release of ASR-SC test data

-       18 Sep 2011 - Submission of ASR System Combination runs

-       20 Sep 2011 - Release of SLT and MT test data

-       25 Sep 2011 - Submission of SLT and MT runs

-       27 Sep 2011 - Release of MT System Combination test data

-       30 Sep 2011 - Submission of MT System Combination runs

-       15 Oct 2011 - Submission of system paper

-       31 Oct 2011 - Notification of acceptance

-       11 Nov 2011 - Camera ready version

 

=== Organizers===

- Alex Waibel (CMU, USA / KIT Germany; Workshop Chair)

- Marcello Federico (FBK-irst, Italy; Evaluation Campaign Chair)

- Mei-Yuh Hwang (Microsoft Research, USA; Program Committee Co-Chair)

- Sebastian Stüker (KIT, Germany; Program Committee Co-Chair)

 
=========================================================================================
=== All information as it becomes available can be found at the workshop’s webpage: http://www.iwslt2011.org ===

Top

                       ASRU 2011
Automatic Speech Recognition and Understanding Workshop
                   Big Island, Hawaii
                  December 11-15, 2011
                http://www.asru2011.org

           DEMONSTRATION CALL FOR PROPOSALS

           > Deadline: September 15, 2011 <

The program committee for the 12th biannual IEEE workshop on Automatic Speech Recognition and Understanding is accepting proposals for the Show & Tell demonstration session event that will be held during the workshop. The Demonstration session has become an exciting highlight of the ASRU workshops. The event will include demonstrations of latest innovations by research groups in industry, academia and government. Demonstrations can be related to any of the topics defined by ASRU:

- ASR / LV CSR Systems
- Language Modeling
- Acoustic Modeling
- Decoder Search
- Spoken Language Understanding
- Spoken Dialog Systems
- Multilingual Speech & Language Processing
- Robustness in ASR
- Spoken Document Retrieval
- Speech-to-Speech Translation
- Text-to-Speech Systems
- Speech Summarization
- New Applications of ASR
- Speech Signal Processing

The deadline for submission of Show & Tell demos proposals is September 15, 2011 with notification of acceptance by September 29, 2011. Submissions will be mailed to the Demonstration Chairs. Proposals should include the demonstration title, list of authors, and an abstract of no more than one page. The abstract should clearly explain what is novel and innovative in the proposed demonstration. Show & Tell demonstrations should have an interactive component (i.e., should be more than a simple computer simulation or graph).

Each demonstration will be allotted one table, space for a poster, and a power outlet. Presenters are responsible for all other equipment and shipping to and from the workshop.  Wireless Internet will also be available by request.  If you have any special requirements, please contact the Demonstration Chairs.

ASRU 2011
the Demonstration Chairs
Patrick Nguyen (e-mail: drpng@google.com)
Olivier Siohan(e-mail: siohan@google.com)

Top

Show&Tell Demonstrations  (www.ieee-espa.org)

[Download the PDF Show&Tell Call for Papers]

We are delighted to host Show&Tell at the first IEEE International Conference on Emerging Signal Processing Applications. Show&Tell will provide researchers, technologists and practitioners from academia, industry and government the opportunity to demonstrate their latest systems and interact with the attendees in an informal setting. Demonstrations in the following or other related areas are encouraged:

• 3D technology for gaming, telepresence
• Gesture recognition for games and natural user interfaces
• Digital photography
• 4G wireless
• Robotics
• Multimedia tablets
• SP in automobiles: speech interfaces, cameras
• Voice search
• SP with multicore processors
• IPTV

Demonstrations will be peer-reviewed by members of the ESPA Program Committee, who will judge the significance, quality, and clarity of each submission. At least one author of each accepted submission must register for and attend the conference, and demonstrate the system during the Show&Tell sessions.

Submission guidelines

• All manuscripts must be in English.
• One page to describe the demonstration.
• All submitted proposals must adhere to the format and style specified in the ESPA 2012 authors’ kit.
• Authors are invited to submit supporting data files, such as demonstration videos, to be included on the Proceedings CD-ROM if their Show&Tell paper is accepted.
• Show and Tell events will be held tentatively on January 12th and 13th. Authors will be provided with a poster board and a table. Wireless access will be available.

Papers should be submitted through the standard procedure at www.ieee-espa.org. Send any questions to showandtell@ieee-espa.org.

Chair

Mazin Gilbert (AT&T Labs Research, USA)

Important dates

• Full submission deadline: October 1st, 2011
• Acceptance notification: October 10th, 2011

Top

ICPRAM (1st International Conference on Pattern Recognition Applications and Methods - http://www.icpram.org/) has an open call for papers, whose deadline is set for July 26, 2011. We hope you can participate in this conference by submitting a paper reflecting your current research in any of the following tracks:
- Theory and Methods
- Applications

ICPRAM 2012 will be held in Vilamoura, Algarve, Portugal next year, on February 6-8, 2012. 
The conference will be sponsored by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC) in cooperation with the Association for the Advancement of Artificial Intelligence (AAAI) and Pattern Analysis, Statistical Modelling and Computational Learning (PASCAL2), and technically co-sponsored by IEEE Signal Processing Society, Machine Learning for Signal Processing (MLSP) Technical Committee of IEEE, AERFAI (Asociacion Espanola de Reconocimiento de Formas y Analisis de Imagenes) and APRP (Associacao Portuguesa de Reconhecimento de Padroes). INSTICC is member of the Workflow Management Coalition (WfMC).

ICPRAM would like to become a major point of contact between researchers, engineers and practitioners on the areas of Pattern Recognition, both from theoretical and application perspectives.
Contributions describing applications of Pattern Recognition techniques to real-world problems, interdisciplinary research, experimental and/or theoretical studies yielding new insights that advance Pattern Recognition methods are especially encouraged.

The conference program features a number of Keynote Lectures to be delivered by distinguished world-class researchers, including those listed below.

The proceedings of ICPRAM will be submitted for indexation by Thomson Reuters Conference Proceedings Citation Index, INSPEC, DBLP and EI.
All accepted papers (full, short and posters) will be published in the conference proceedings, under an ISBN reference, on paper and on CD-ROM support. BWRB
A short list of presented papers will be selected so that revised and extended versions of these papers will be published by Springer-Verlag in a AISC Series book.
Top selected papers in specific areas of interest will be published as a special issue in the Neurocomputing Journal.

Best paper awards will be distributed during the conference closing session. Please check the website for further information (http://www.icpram.org/best_paper_awards.asp).

All papers presented at the conference venue will be available at the SciTePress Digital Library (http://www.scitepress.org/DigitalLibrary/).

Workshops and special sessions are also invited. If you wish to propose a workshop or a special session, for example based on the results of a specific research project, please contact the secretariat. Workshop chairs and Special Session chairs will benefit from logistics support and other types of support, including secretariat and financial support, to facilitate the development of a valid idea.

Please check further details at the ICPRAM's conference website (http://www.icpram.org). 
Should you have any question please don't hesitate contacting me.

ICPRAM 2012 will be held in conjunction with ICAART 2012 (http://www.icaart.org/home.asp) in Vilamoura, Algarve, Portugal next year, on February 6-8, 2012. Registration to ICPRAM will enable free access to the ICAART conference (as a non-speaker).

We hope to welcome you in Vilamoura, Algarve next February 2012!


Kind regards,
Patricia Alves
ICPRAM Secretariat

Av. D.Manuel I, 27A 2.Esq.
2910-595 Setubal, Portugal
Tel.: +351 265 100033
Fax: +44 203 014 8556
Email: icpram.secretariat@insticc.org




ICPRAM website: http://www.icpram.org

IMPORTANT DATES:
Conference date: 6-8 February, 2012

Regular Paper Submission: July 26, 2011
Authors Notification: October 6, 2011
Final Regular Paper Submission and Registration: October 26, 2011


TECHNICALLY CO-SPONSORED BY
- IEEE
- Machine Learning for Signal Processing (MLSP) Technical Committee of IEEE 
- AERFAI 
- APRP 


IN COOPERATION WITH
- AAAI 
- PASCAL2


CONFERENCE TRACKS:
TRACK 1: THEORY AND METHODS
- Exact and Approximate Inference
- Density Estimation
- Bayesian Models
- Gaussian Processes
- Model Selection
- Graphical and Graph-based Models
- Missing Data
- Ensemble Methods
- Neural Networks
- Kernel Methods
- Large Margin Methods
- Classification
- Regression
- Sparsity
- Feature Selection and Extraction
- Spectral Methods
- Embedding and Manifold Learning
- Similarity and Distance Learning
- Matrix Factorization
- Clustering
- ICA, PCA, CCA and other Linear Models
- Fuzzy Logic
- Active Learning
- Cost-sensitive Learning
- Incremental Learning
- On-line Learning
- Structured Learning
- Multi-agent Learning
- Multi-instance Learning
- Reinforcement Learning
- Instance-based Learning
- Knowledge Acquisition and Representation
- Meta Learning
- Multi-strategy Learning
- Case-based Reasoning
- Inductive Learning
- Computational Learning Theory
- Cooperative Learning
- Evolutionary Computation
- Information Retrieval and Learning
- Hybrid Learning Algorithms
- Planning and Learning
- Convex Optimization
- Stochastic Methods
- Combinatorial Optimization


TRACK 2: APPLICATIONS
- Natural Language Processing
- Information Retrieval
- Ranking
- Web Applications
- Economics, Business and Forecasting Applications
- Bioinformatics and Systems Biology
- Audio and Speech Processing
- Signal Processing
- Image Understanding
- Sensors and Early Vision
- Motion and Tracking
- Image-based Modelling
- Shape Representation
- Object Recognition
- Video Analysis
- Medical Imaging
- Learning and Adaptive Control
- Perception
- Learning in Process Automation
- Learning of Action Patterns
- Virtual Environments
- Robotics


KEYNOTE SPEAKERS:
Ludmila Kuncheva, Bangor University, U.K.
Tiberio Caetano, NICTA, Australia
Francis Bach, INRIA, France 
Jose C. Principe, University of Florida, U.S.A.
Joachim M. Buhmann, ETH Zurich, Switzerland 
(list not yet complete)


CONFERENCE CHAIR:
Ana Fred, Technical University of Lisbon / IT, Portugal


PROGRAM CO-CHAIRS:
J. Salvador Sanchez, Jaume I University, Spain
Pedro Latorre Carmona, Jaume I University, Spain


PAPER SUBMISSION:
Authors should submit an original paper in English, carefully checked for correct grammar and spelling, using the on-line submission procedure. The initial submission must have between 3 to 13 pages otherwise it will be rejected without review. Each paper should clearly indicate the nature of its technical/scientific contribution, and the problems, domains or environments to which it is applicable.

A 'double-blind' paper evaluation method will be used. To facilitate that, the authors are kindly requested to produce and provide the paper, WITHOUT any reference to any of the authors. This means that is necessary to remove the authors personal details, the acknowledgements section and any reference that may disclose the authors identity.

Submission types:

A) Regular Paper Submission
A regular paper presents a work where the research is completed or almost finished. It does not necessary means that the acceptance is as a full paper. It may be accepted as a 'full paper' (30 min. oral presentation), a 'short paper' (20 min. oral presentation) or a 'poster'.

B) Position Paper Submission
A position paper presents an arguable opinion about an issue. The goal of a position paper is to convince the audience that your opinion is valid and worth listening to, without the need to present completed research work and/or validated results. It is, nevertheless, important to support your argument with evidence to ensure the validity of your claims. A position paper may be a short report and discussion of ideas, facts, situations, methods, procedures or results of scientific research (bibliographic, experimental, theoretical, or other) focused on one of the conference topic areas. The acceptance of a position paper is restricted to the categories of 'short paper' or 'poster', i.e. a position paper is not a candidate to acceptance as 'full paper'.


PROGRAM COMMITTEE:
Please check the program committee members at http://www.icpram.org/program_committee.asp

Top

***********************************************************************
                            IEEE ICASSP 2012
  International Conference on Acoustics, Speech, and Signal Processing
                           March 25 - 30, 2012
               Kyoto International Conference Center, Kyoto JAPAN
                        http://www.icassp2012.org/
***********************************************************************
We are very glad to announce that paper submission will be open soon at 
the IEEE ICASSP 2012 web site (http://www.icassp2012.org/).  

Important Deadlines
Special Session & Tutorial Proposals Due
     August 11, 2011
Notification of Special Session & Tutorial Acceptance
     September 15, 2011
Submission of Regular Papers
     September 27, 2011
Notification of Paper Acceptance
     December 22, 2011
Revised Paper Upload Deadline
     January 19, 2012
Author's Registration Deadline
     January 26, 2012


CALL FOR PAPERS

The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) will be held at the Kyoto International Conference Center in Kyoto, Japan, on March 25 - 30, 2012. 

The ICASSP meeting is the world's largest and most comprehensive technical conference focused on signal processing and its applications. The conference will feature world-class speakers, tutorials, exhibits, and over 50 lecture and poster sessions on:

 * Audio and acoustic signal processing
 * Bio imaging and signal processing
 * Design and implementation of signal processing systems
 * Image, video and multidimensional signal processing
 * Industry technology tracks
 * Information forensics and security
 * Machine learning for signal processing
 * Multimedia signal processing
 * Sensor array and multichannel signal processing
 * Signal processing education
 * Signal processing for communications and networking
 * Signal processing theory and methods
 * Speech processing
 * Spoken language processing

Welcome to Kyoto: The Cultural Heart of Japan. Kyoto is special because it reigned as the national capital of Japan for more than 1000 years. Seventeen UNESCO World Cultural Heritage Sites are situated in a cityscape dominated by 2000 temples and shrines. The rich heritage is also reflected in modern technical advances of Japanese frontier and leading industries. You and your family will be welcomed with all the hospitality of the cultural heart of Japan.

Submission of Papers: Prospective authors are invited to submit full-length, four-page papers, including figures and references, to the ICASSP Technical Committee. All ICASSP papers will be handled and reviewed electronically. The ICASSP 2012 website (http://www.icassp2012.org/) will provide you with further details. Please note that the submission dates for papers are strict deadlines.

Tutorial and Special Session Proposals: Tutorials will be held on March 25 and 26, 2012. Brief proposals must include title, outline, contact information, biography and selected publications for the presenter, a description of the tutorial, and material to be distributed to participants. Special sessions proposals must include a topical title, rationale, session outline, contact information, and a list of invited speakers. Tutorial and special session authors are referred to the ICASSP 2012 website for additional information regarding submissions.

For more detailed information, please visit the ICASSP 2012 official website, http://www.icassp2012.org/.

The ICASSP 2012 Organizing Committee

================================================================================
You have received this mailing because you are a member of IEEE Signal Processing Society .

To unsubscribe, please go to http://ewh.ieee.org/enotice/options.php?SN=Wellekens&LN=CONF and be certain to include your IEEE member number. 

If you need assistance with your E-Notice subscription, please contact Khanh Luu.

Top

EACL 2012, 2nd CALL FOR TUTORIAL PROPOSALS

** Deadline: September 30th, 2011

Proposals are invited for the Tutorial Program of the 13th Conference
of the European Chapter of the Association for Computational
Linguistics (EACL 2012), to be held in Avignon, France, from April 23
to April 27, 2012. The selected tutorials will be given on the Monday
and Tuesday preceding the main conference (April 23 and 24).

EACL 2012 seeks proposals for tutorials in all areas of computational
linguistics, broadly conceived to include disciplines such as
linguistics (including phycholinguistics and other subfields), speech,
information retrieval and multimodal processing.

We particularly welcome (1) tutorials which cover advances in newly
emerging areas not previously covered in an (E)ACL related tutorial,
or (2) tutorials which provide introductions into related fields which
are potentially relevant for the CL community (e.g. bioinformatics,
social media, human language processing, machine learning
techniques). In order to gather a widespread audience, the interest of
the tutorial and the quality of the instructors will also be taken
into account.

REMUNERATION

Remuneration for tutorials is regulated by ACL policies:
http://aclweb.org/adminwiki/index.php?title=Policy_on_tutorial_teacher_payment

The conversion to euros will be done as follows: €550 for up to 20
people, plus €25 per person for registrants between 21 to 50, plus €18
per person for registrants greater than 50.

Please NOTE: Remuneration for Tutorial presenters is fixed according
   to the above policy and does not cover registration fees for the
   main conference.

SUBMISSION DETAILS

Proposals for tutorials should contain:

1. A title and brief description of the tutorial content and its
   relevance to the ACL community (not more than 2 pages).

2. A brief outline of the tutorial structure showing that the
   tutorial's core content can be covered in a three-hour slot
   (excluding a coffee break). In exceptional cases six-hour tutorial
   slots are available as well.

3. The names, postal addresses, phone numbers, and email addresses of
   the tutorial instructors, including a one-paragraph statement of
   their research interests and areas of expertise.

4. A list of previous venues and approximate audience sizes, if the
   same or a similar tutorial has been given elsewhere; otherwise an
   estimate of the audience size.

5. A description of special requirements for technical equipment
   (e.g. internet access).  Proposals should be submitted by
   electronic mail, in plain ASCII text, to tutorials at eacl2012 dot
   org, no later than September 30th 2011.

   The subject line should be: 'EACL 2012 TUTORIAL PROPOSASeptember 30th, 2011L'.

PLEASE NOTE:

- only proposals submitted by e-mail will be taken into account.

- you will receive email confirmation from us that your prSeptember 30th, 2011oposal has
  been received. If you do not receive this confirmation 24 hours
  after sending the proposal, please contact us personally using both
  e.agirre at ehu dot es and lieve.macken at hogent dot be


TUTORIAL SPEAKER RESPONSIBILITIES

Accepted tutorial speakers will be notified by November 3rd, 2011,
and must then provide abstracts of their tutorials for inclusion in
the conference registration material by December 16th, 2011. The
description should be in two formats: an ASCII version that can be
included in email announcements and published on the conference web
site, and a PDF version for inclusion in the electronic proceedings
(detailed instructions to follow).

Tutorial speakers must provide tutorial materials, at least containing
copies of the course slides as well as a bibliography for the material
covered in the tutorial, by February 1st, 2012.

IMPORTANT DATES

Submission deadline for tutorial proposals: September 30th, 2011
Notification of acceptance: November 3rd, 2011
Tutorial descriptions due: December 16th, 2011
Tutorial course material due: February 1st, 2012
Tutorial dates: April 23-24, 2012


TUTORIAL CHAIRS

Eneko Agirre, University of the Basque Country, Spain
Lieve Macken, University College Ghent, Belgium

Please send inquiries concerning EACL 2012 tutorials to:
tutorials at eacl2012 dot org

Top

EACL 2012
Thirteenth Conference of the European Chapter of the Association for 
Computational Linguistics
Avignon, France
April 23-27, 2012
http://eacl2012.org
========================================================================
First Call For Papers
========================================================================

>>> Submission deadline: November 4, 2011 <<<

EACL 2012 is the 13th Conference of the European Chapter of the
Association for Computational Linguistics. The conference invites the
submission of papers on substantial, original, and unpublished
research on all areas of computational linguistics, broadly conceived
to include disciplines such as psycholinguistics, speech, information
retrieval, multimodal language processing. The conference welcomes
theoretical, empirical, and application-orientated papers as well as
papers targeting emerging domains such as bioinformatics and social
media.  

The list of topics includes, but is not limited to:

  - phonetics, phonology, and morphology
  - word segmentation, tagging and chunking
  - syntax, parsing, grammar formalisms, and grammar induction
  - semantics
  - pragmatics, discourse, and dialogue
  - generation and summarization
  - information retrieval and  question answering
  - information extraction
  - sentiment analysis and opinion mining
  - machine translation and multilingual systems
  - spoken language processing and language modeling
  - dialogue systems and multimodal systems
  - language resources and tools
  - psychological and mathematical models of language and language
acquisition
  - machine learning and algorithms for natural language
  - natural language processing applications
  - evaluation methodology


Important Dates
---------------

Paper submission deadline: November 4, 2011 
Author response period: December 27-30, 2011
Notification of acceptance: January 13, 2012
Camera-ready papers due: March 9, 2012
Papers available on-line: April 19, 2012
EACL 2012 Conference: April 23 - 27, 2012

All deadlines refer to 11:59pm Samoa time (UTC/GMT -11 hours) 


Requirements
------------

Papers should describe original work; they should emphasize completed
work rather than intended work, and should indicate clearly the state
of completion of the reported results. A paper accepted for
presentation 
at EACL 2012 cannot be presented at any other meeting with publicly
available published proceedings. Papers that are being submitted to
other conferences or workshops must indicate this on the submission
page. If the paper is accepted by both EACL 2012 and another meeting
or publication, it must be withdrawn from one of them. Furthermore,
its authors must notify the program chairs, within a week of receiving
the EACL 2012 acceptance notification, whether or not they have chosen
EACL 2012 for presentation of their work.


Review and Selection
--------------------

Reviewing of papers will be double-blind, and all submissions will
receive 
three independent reviews. Final decisions on the program will be made
by 
the Program Committee, consisting of the Program Co-Chairs and Area
Chairs.  
Submissions will be assessed with respect to appropriateness, clarity, 
soundness/correctness, meaningful comparison,
originality/innovativeness, 
and impact of ideas or results. 


Publication and Presentation
----------------------------

All papers that are accepted will be published in the proceedings of
the conference, and will be presented orally or as a poster
presentation 
as determined by the program committee. The decisions as to which
papers 
will be presented orally and which as poster presentations will be
based 
on the nature rather than on the quality of the work. Authors will be
also 
asked on submission to state their preferred mode of presentation. 
EACL 2012 will continue aiming to give poster presentations a high
status. 
There will be no distinction in the conference proceedings between
papers 
that are assigned different presentation modes.


Submission Information
----------------------

All submissions must be submitted electronically as PDF and must
follow the two-column format of EACL proceedings. Authors are strongly
recommended to use the style files available on the conference web
site. Papers may consist of up to nine (9) pages of content and any
number of additional pages containing references only.

EACL 2012 will also accept papers accompanied by the resource(s)
(software or data) described in the paper. In addition to the regular
review of the research quality of the paper, these papers will also be
reviewed for the quality of the resource that is being made
available. Acceptance or rejection decision will be made based on the
quality of both the research and the software/data component.

As reviewing will be double-blind, the paper should not include the
authors' names and affiliations. Furthermore, self-references that
reveal the author's identity, e.g., 'We previously showed (Smith,
1991) ...', should be avoided. Instead, use citations such as 'Smith
previously showed (Smith, 1991) ...'. Authors should not use anonymous
citations and should not include any acknowledgments. Papers that do
not conform to these requirements will be rejected without review.

The deadline for submission is 11:59pm Samoa Time (UTC/GMT -11 hours)
on November 4, 2011.  Additional instructions for electronic submission 
will be posted on the conference website at http://eacl2012.org


Mentoring service
-----------------

EACL is providing a mentoring (coaching) service for authors from
regions of the world where English is less emphasized as a language of
scientific exchange. Many authors from these regions, although able to
read the scientific literature in English, have little or no
experience in writing papers in English for conferences such as the
E/ACL meetings. If you would like to take advantage of the service,
please upload your paper in PDF format by September 23, 2011 using the
paper submission software for the mentoring service which will be
available at the conference website. Questions about the mentoring
service should be referred to 


Invited speakers
----------------

TBA


Best paper awards
-----------------

TBA


Organization
------------

General Chair:          Walter Daelemans (University of Antwerp,
Belgium)

Program Co-Chairs:      Mirella Lapata (University of Edinburgh, UK)
                        Lluis Marquez (Universitat Politcnica de
Catalunya, Spain)

Area Chairs:            TBA

Mentoring Chairs:       Caroline Sporleder (Saarland University,Germany)
                        Gertjan van Noord (University of Groningen, The
Netherlands)
                        
Publications Chairs:    Adri de Gispert (University of Cambridge, UK)
                        Fabrice Lefevre (University of Cambridge, UK)

Local Chair:            Marc El-Beze (University of Avignon, France)
Local Co-Chair:         Tania Jimenez (University of Avignon, France)

Top

1st Call for Papers

6th INTERNATIONAL CONFERENCE ON LANGUAGE AND AUTOMATA
THEORY AND APPLICATIONS

LATA 2012

A Coruña, Spain

March 5-9, 2012

http://grammars.grlmc.com/LATA2012/

*********************************************************************

AIMS:

LATA is a yearly conference in theoretical computer science and its applications. Following the tradition of the International Schools in Formal Languages and Applications developed at Rovira i Virgili University in Tarragona since 2002, LATA 2012 will reserve significant room for young scholars at the beginning of their career. It will aim at attracting contributions from both classical theory fields and application areas (bioinformatics, systems biology, language technology, artificial intelligence, etc.).

VENUE:

LATA 2012 will take place in A Coruña, at the northwest of Spain. The venue will be the Faculty of Computer Science, University of A Coruña.

SCOPE:

Topics of either theoretical or applied interest include, but are not limited to:

- algebraic language theory
- algorithms for semi-structured data mining
- algorithms on automata and words
- automata and logic
- automata for system analysis and programme verification
- automata, concurrency and Petri nets
- automatic structures
- cellular automata
- combinatorics on words
- computability
- computational complexity
- computational linguistics
- data and image compression
- decidability questions on words and languages
- descriptional complexity
- DNA and other models of bio-inspired computing
- document engineering
- foundations of finite state technology
- foundations of XML
- fuzzy and rough languages
- grammars (Chomsky hierarchy, contextual, multidimensional, unification, categorial, etc.)
- grammars and automata architectures
- grammatical inference and algorithmic learning
- graphs and graph transformation
- language varieties and semigroups
- language-based cryptography
- language-theoretic foundations of artificial intelligence and artificial life
- parallel and regulated rewriting
- parsing
- pattern recognition
- patterns and codes
- power series
- quantum, chemical and optical computing
- semantics
- string and combinatorial issues in computational biology and bioinformatics
- string processing algorithms
- symbolic dynamics
- symbolic neural networks
- term rewriting
- transducers
- trees, tree languages and tree automata
- weighted automata

STRUCTURE:

LATA 2012 will consist of:

- 3 invited talks
- 2 invited tutorials
- peer-reviewed contributions

INVITED SPEAKERS:

To be announced

PROGRAMME COMMITTEE:

Eric Allender (Rutgers)
Miguel Á. Alonso (A Coruña)
Amihood Amir (Bar-Ilan)
Dana Angluin (Yale)
Franz Baader (Dresden)
Patricia Bouyer (Cachan)
John Case (Delaware)
Volker Diekert (Stuttgart)
Paul Gastin (Cachan)
Reiko Heckel (Leicester)
Sanjay Jain (Singapore)
Janusz Kacprzyk (Warsaw)
Victor Khomenko (Newcastle)
Bakhadyr Khoussainov (Auckland)
Claude Kirchner (Paris)
Maciej Koutny (Newcastle)
Salvador Lucas (Valencia)
Sebastian Maneth (Sydney)
Carlos Martín-Vide (Tarragona, chair)
Giancarlo Mauri (Milano Bicocca)
Aart Middeldorp (Innsbruck)
Faron Moller (Swansea)
Angelo Montanari (Udine)
Joachim Niehren (Lille)
Mitsunori Ogihara (Miami)
Enno Ohlebusch (Ulm)
Dominique Perrin (Marne-la-Vallée)
Alberto Policriti (Udine)
Alexander Rabinovich (Tel Aviv)
Mathieu Raffinot (Paris)
Jörg Rothe (Düsseldorf)
Olivier H. Roux (Nantes)
Yasubumi Sakakibara (Keio)
Eljas Soisalon-Soininen (Aalto)
Frank Stephan (Singapore)
Jens Stoye (Bielefeld)
Howard Straubing (Boston)
Masayuki Takeda (Kyushu)
Wolfgang Thomas (Aachen)
Sophie Tison (Lille)
Jacobo Torán (Ulm)
Tayssir Touili (Paris)
Esko Ukkonen (Helsinki)
Frits Vaandrager (Nijmegen)
Manuel Vilares (Vigo)
Todd Wareham (Newfoundland)
Pierre Wolper (Liège)
Hans Zantema (Eindhoven)
Thomas Zeugmann (Sapporo)

ORGANIZING COMMITTEE:

Miguel Á. Alonso (A Coruña, co-chair)
Adrian Horia Dediu (Tarragona)
Carlos Gómez Rodríguez (A Coruña)
Jorge Graña (A Coruña)
Carlos Martín-Vide (Tarragona, co-chair) 
Bianca Truthe (Magdeburg)
Jesús Vilares (A Coruña)
Florentina Lilica Voicu (Tarragona)

SUBMISSIONS:

Authors are invited to submit papers presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (including eventual appendices) and should be formatted according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs/lncs+authors?SGWID=0-40209-0-0-0). Submissions have to be uploaded at:

http://www.easychair.org/conferences/?conf=lata2012

PUBLICATIONS:

A volume of proceedings published by Springer in the LNCS series will be available by the time of the conference.

A special issue of a major journal will be later published containing peer-reviewed extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation.

REGISTRATION:

The period for registration will be open since July 16, 2011 until March 5, 2012. The registration form can be found at the website of the conference: http://grammars.grlmc.com/LATA2012/

Early registration fees: 500 Euro
Early registration fees (PhD students): 400 Euro
Late registration fees: 540 Euro
Late registration fees (PhD students): 440 Euro
On-site registration fees: 580 Euro
On-site registration fees (PhD students): 480 Euro

At least one author per paper should register. Papers that do not have a registered author who paid the fees by December 5, 2011 will be excluded from the proceedings.

Fees comprise access to all sessions, one copy of the proceedings volume, coffee breaks and lunches.

PhD students will need to prove their status on site.

PAYMENT:

Early (resp. late) registration fees must be paid by bank transfer before December 5, 2011 (resp. February 24, 2012) to the conference series account at Uno-e Bank (Julián Camarillo 4 C, 28037 Madrid, Spain):

IBAN: ES3902270001820201823142 – Swift/BIC code: UNOEESM1 (account holder: Carlos Martin-Vide – LATA 2012; address: Av. Catalunya, 35, 43002 Tarragona, Spain).

Please write the participant’s name in the subject of the bank form. Transfers should not involve any expense for the conference. People claiming early registration will be requested to prove that they gave the transfer order to the bank by the deadline.

On-site registration fees can be paid only in cash. A receipt for payments will be provided on site.

Besides paying the registration fees, it is required to fill in the registration form at the website of the conference.

IMPORTANT DATES:

Paper submission: October 7, 2011 (23:59h, CET)
Notification of paper acceptance or rejection: November 18, 2011
Final version of the paper for the LNCS proceedings: November 27, 2011
Early registration: December 5, 2011
Late registration: February 24, 2012
Starting of the conference: March 5, 2012
Submission to the post-conference special issue: June 9, 2012

FURTHER INFORMATION:

florentinalilica.voicu@urv.cat

POSTAL ADDRESS:

LATA 2012
Research Group on Mathematical Linguistics
Rovira i Virgili University
Av. Catalunya, 35
43002 Tarragona, Spain

Phone: +34-977-559543
Fax: +34-977-558386

Top

The 8th edition of the Language Resources and Evaluation Conference will take place in Istanbul (Turkey) on May 21-27, 2012.
More information will be available soon on: http://www.lrec-conf.org/lrec2012/lrec2012.htm

Helene Mazo
on behalf of LREC 2012 Programme Committee

Top

Call for papers

LabPhon 13
The 13th Conference on Laboratory Phonology
Stuttgart, Germany, July 27-29, 2012

Deadline for abstract submission: 15 January 2012

Notification of acceptance: 31 March 2012

Conference website:
http://www.labphon13.labphon.org/

Abstracts are solicited for contributed papers for presentation as 20-minute oral contributions or as posters. Contributions relating to the conference themes are especially encouraged; there will also be sessions for non-thematic papers.

The overall theme for the conference is “Phonological and phonetic computations: between grammar and neural activity.” Our goal is to bring together researchers from phonology, phonetics, and adjacent psycho- and neurosciences and to seek to advance these disciplines by encouraging the joint pursuit of interdisciplinary research questions. Specific topics that address this theme are the following:

    Simulation as a research method in Laboratory Phonology.
    Invited speakers: Bruce Hayes (UCLA), Andrew Wedel (Univ. Arizona)
    Invited moderator: Bernd Möbius (Saarland Univ.)

    Computational approaches to sound change: data-driven and model driven.
    Invited speakers: Jonathan Harrington (LMU Munich), Paul Boersma (Univ. Amsterdam)
    Invited moderator: John Coleman (Univ. Oxford)

    Temporal mechanisms in neural processing of sounds and prosodies.
    Invited speakers: Karsten Steinhauer (McGill Univ.), William Idsardi (Univ. Maryland)
    Invited moderator: Carsten Eulitz (Univ. Konstanz)

    Rich memory for rich phonology.
    Invited speakers: Stephen Goldinger (Arizona State Univ.), Robert Port (Indiana Univ.)
    Invited moderator: Holger Mitterer (MPI Nijmegen)

Non-thematic sessions (both oral and poster) will include contributions to other topics of interest to the LabPhon community.

Top

Call for Nominations

                 IEEE Signal Processing Society
   Speech and Language Technical Committee (SLTC) Member Positions

The Member Election Subcommittee of the IEEE SLTC is seeking nominations for new SLTC Members.  Nominations should be submitted to the Chair of the Member Election Subcommittee at geoffrey.chan@queensu.ca, with cc to ney@informatik.rwth-aachen.de and larry.heck@microsoft.com.  Please provide the name, contact information and biography with the nomination.  The nomination deadline is set as 15 September 2011.  New member candidates can be self-nominated or nominated by current SLTC members.  Members will serve a term of two or three years, with the term to be assigned by the SLTC Chair after the election.

Past SLTC members are eligible to be nominated for a second term.  Current SLTC members may also be nominated for a second consecutive term, but would then not be eligible to vote in this new member election.  Additional terms are allowed after leaving the SLTC, but at least a 3-year gap in service is required.

New members must be willing to review papers that are submitted to the Society's conferences within the area of the SLTC, review papers for workshops owned or co-owned by the SLTC, serve in the subcommittees established by the SLTC, and perform other duties as assigned.  SLTC members will be elected by the members of the SLTC itself based on the needs of the SLTC. The election results will be finalized by 15 November 2011.

Please use the nomination form outlined below and submit a completed nomination form no more than one page in length:

- Name of nominee:

- Short Biography (not more than 150 words):

- Affiliation:

- Address and phone number, email:

- Link to web page (optional):

- IEEE SPS membership (yes/no):

- IEEE volunteer work and leadership activities:

- Other professional volunteer work:

- Previous SLTC/AE memberships (list periods of service):

- Confirmation that the member will serve if elected:

- Area of suggested expertise of the nominee (choose ONE from among the following):

1. Speech recognition

2. Speech production

3. Natural language processing

4. Dialogue systems

5. Speaker recognition

6. Speech synthesis

7. Speech analysis

8. Speech enhancement

9. Speech perception

10. Speech coding

The rights and duties of an SLTC member are described here:

http://www.signalprocessingsociety.org/technical-committees/list/sl-tc/

The following are nominee requirements:

* The candidate may not be a current AE of TASLP.

* The candidate must be a member of the IEEE Signal Processing Society.

* The candidate should be willing to serve if elected. This means active participation including prompt paper reviews for 4 ICASSPs (2012-2015), active participation in accomplishing SLTC sub-committee duties, and best efforts to attend meetings and responding appropriately to action items.

--

Top

AFCP, French-speaking regional branch of ISCA, and the partners of the project ETAPE (1) are proud to announce an evaluation campaign on vocal technologies for the French language. The ETAPE 2011 campaign follows the series of ESTER campaigns organized in 2003, 2005 and 2009, targeting a wider variety of speech quality and the more difficult challenge of spontaneous speech. Speech transcription and information extraction (speaker turns, named entities) will be evaluated, focusing on TV material with various level of spontaneous speech and multiple speaker speech.

A corpora of about 30h of radio and TV shows covering various types and topics (news, debates, etc.), including the reference transcription with named entity annotations, will be made available to participants. After completion of the evaluation campaign, the corpus will be complemented with phonetic alignments and syntactic trees that will be available to participants for research purposes. The entire ETAPE data set will also be made availble to non participants via ELRA.

Tentative calendar:
   may 2011     proposal of an evaluation plan for discussion
   june 2011    release of training and development data
   dec. 2011    evaluation campaign (to be defined with participants)
   feb. 2012    workshop

For more information:

  - visit the ETAPE page of the AFCP website (http://www.afcp-parole.org/etape.html)

  - subscribe to the ester-info mailing list: send a mail to sympa@listes.afcp-parole.org with the following line in the mail body

SUBSCRIBE ester-info firstname lastname

  - contact us: guillaume.gravier@irisa.fr, gilles.adda@limsi.fr

(1) ETAPE is a French national project targeting the organisation of evaluation campaigns in the field of automatic speech processing. Partially funded by the French National Research Agency (ANR), the project brings together national experts in the organisation of such campaigns under the scientific leadership of the AFCP, the French-speaking Speech Communication Association, a regional branch of ISCA.

Partners of the ETAPE projects are, in alphabetical order: Association
Francophone de la Communication Parlée, Direction Générale de
l'Armement, ELDA S.A., Laboratoire National d'Essais, Laboratoire de
Linguistique Formelle (Univ. Paris 7), Laboratoire de Phonétique et
Phonologie (Univ. Paris 3).

Top