Appel: SLAM, First Workshop on Speech, Language and Audio in Multimedia

Thierry Hamon thierry.hamon at UNIV-PARIS13.FR
Sat Apr 27 19:59:43 UTC 2013

Date: Fri, 26 Apr 2013 12:20:48 +0200
From: Frederic Bechet <frederic.bechet at>
Message-ID: <517A5500.2080006 at>

[Apologies for multiple postings. Please disseminate widely to 
interested colleagues.]

*Last chance to submit!!!!!! *

We are happy to announce Sam Davies from BBC R&D as an invited speaker,
who will tell us about the BBC's World Service Archive. See for details.

                          Call for papers


                            Organized by
              ISCA SIG on Speech and Language in Multimedia
          IEEE SIG on Audio and Speech Processing for Multimedia

                as a satellite event of Interspeech 2013

                  Aug. 22—23, 2013, Marseille, France


The first Workshop on Speech, Language and Audio in Multimedia (SLAM)
aims at bringing together researchers working in speech, language and
audio processing to analyze, index and access multimedia data.
Multimedia data are now available in very large amounts with a wide
variety of formats and qualities, from professional content to
user-generated ones: Lectures, meetings, interviews, debates,
conversational broadcast, podcasts, social videos on the Web, etc. Such
data, along with the associated use scenarios, raise specific
challenges: Robustness facing the high variability in quality;
Efficiency to handle very large amount of data; Semantics shared across
modalities; Potentially high error rates in transcription; etc.
Worldwide, several national and international research projects are
focusing on audio analysis of multimedia data. Similarly, various
benchmark initiatives have been initiated such as TRECVID MED,
MediaEval, or ETAPE and REPERE in France.

The SLAM workshop intends to bring together players from the field to
share recent research results, discuss ongoing and future projects,
benchmarking initiatives and applications. We expect communications on
research work, project description, evaluation initiative,
demonstrations and applications dealing with speech and/or language
and/or audio on any type of multimedia material. The list of topics of
interest includes (but is not limited to):

     Audio event detection and audio classification
     Speech and speaker recognition on multimedia material
     Audio-aware genre analysis and classification
     Multimodal speaker identification and clustering
     Multimedia spoken term detection and content retrieval
     Speech and audio aware content segmentation and structuring
     Audio indexing and fingerprinting
     Robust feature extraction and processing
     Natural language processing for multimedia
     Metadata extraction : Entity extraction, keyword extraction, etc.
     Summarization and hyperlink generation
     Multimodal fusion and integration involving audio
     Generation of descriptive text for multimedia
     Speech and audio multimedia applications and services
     Databases and benchmarks
     Large scale speech and audio analysis
     Navigation in multimedia audio content

applied to any media such as:

     Professional broadcasts – TV, radio, podcasts, newsfeeds, synopsis,
     Social media – YouTube, Flickr, Facebook, Twitter, Voice Social
     Network, etc.
     Audiovisual archives – Lectures and conferences, meetings, etc.
     Music – Music catalogs, music collections, etc.

The workshop is organized in conjunction with Interspeech 2013 over 1.5
days, starting Thu. 22, 2013 at mid-day and ending Fri. 23, 2013
afternoon, right before the main conference. Marseille is conveniently
connected by high-speed train to Lyon where the Interspeech conference
will take place. The format of the workshop will include an invited
talk, oral presentations of scientific work and a poster session for
project and benchmark presentations.

Prospective authors should submit a manuscript following instructions on
the web site. All submissions will be peer-reviewed by at least two
reviewers. Proceedings will be published online in open access and a
special issue in a dedicated journal is targeted.

*Important dates*
     full paper submission deadline: May 3, 2013 *EXTENDED*
     notification of acceptance: May 31, 2013
     camera ready paper: June 28, 2013
     registration deadline : June 28, 2013
     workshop: August 22-23, 2013
     Interspeech conference: August 25-30, 2013

The first SLAM workshop is jointly organized by the newly created ISCA
SIG on Speech and Language in Multimedia and by the IEEE SIG on Audio
and Speech Processing in Multimedia. This first edition is intended as
the first of a series of workshop.

General Chairs:
     Frédéric Bechet (LIF-CNRS, Aix Marseille Université)
     Guillaume Gravier (IRISA, CNRS)

Scientific committee:
     Xavier Anguera (Telefónica)
     Frédéric Bechet (Aix Marseille Université)
     Delphine Charlet (Orange Labs)
     Gerald Friedland (ICSI)
     Sadaoki Furui (Tokyo Institute of Technology)
     Guillaume Gravier (CNRS)
     Gareth Jones (Dublin City University)
     Martha Larson (TU Delft)
     Lin-Shan Lee (National Taiwan University)
     Georges Linarès (Université d'Avignon)
     Florian Metze (CMU)

Organizing committee:
     Patrice Bellot (LSIS-CNRS, Aix Marseille Université)
     Hervé Bredin (LIMSI, CNRS)
     Benoît Favre (LIF-CNRS, Aix Marseille Université)
     Sylvain Meigner (LIUM, Université du Maine)
     Christian Raymond (IRISA, INSA Rennes)

Message diffuse par la liste Langage Naturel <LN at>
Informations, abonnement :
English version       : 
Archives                 :

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  :

More information about the Ln mailing list