Young Researchers RoundTable on Spoken Dialog Systems (YRRSDS) 2012.

YRRSDS (www.yrrsds.org), is an annual workshop designed for students, post docs, and junior researchers working in research related to spoken dialogue systems in both academia and industry.

 The workshop is meant to provide an interdisciplinary forum for creative thinking about current issues in spoken dialogue systems research, and help create a stronger international network of young researchers working in the field.

YRRSDS has been a satellite event of SIGdial (Special Interest Group on Discourse and Dialogue) since 2005, and will be held on July 3rd and 4th 2012 before SIGdial in Seoul.

The YRRSDS'12 Organizing Committee: Timo Baumann (U Hamburg, Germany) Heather Friedberg (U Pittsburgh, USA) Jana Götze (KTH Stockholm, Sweden) Srini Janarthanam (HWU Edinburgh, UK) Kyungduk Kim (Postech, South Korea) KyukSu Ryu (Seoul National University, South Korea) Pierre Lison (U Oslo, Norway) Alejandra Lorenzo (Loria, France) Raveesh Meena (KTH Stockholm, Sweden) WonSeok Choi (U Sogang, South Korea) Michal Ptaszynski (High-Tech research Center, Japan)

 Contact email: yrrsds2012@gmail.com

Website: www.yrrsds.org

Back

Top

CALL FOR PAPERS
SIGDIAL 2012 CONFERENCE:  13th Annual Meeting of the Special Interest
Group on Discourse and Dialog
Seoul, South Korea
July 5-6, 2012

Deadline for submissions:  March 26, 2012 GMT-11

CALL FOR PAPERS

The SIGDIAL venue provides a regular forum for the presentation of
cutting edge research in discourse and dialog to both academic and
industry researchers. Continuing a series of twelve successful
previous meetings, this conference spans the research interest areas
of discourse and dialog. The conference is sponsored by the SIGDIAL
organization (http://www.sigdial.org/), which serves as the Special
Interest Group on discourse and dialog for both ACL and ISCA.

Topics of Interest

We welcome formal, corpus-based, implementation or analytical work on
discourse and dialog including but not restricted to the following
themes and topics:

1. Discourse Processing and Dialog Systems
2. Corpora, Tools and Methodology
3. Pragmatic and/or Semantic Modeling
4. Dimensions of Interaction
5. Applications of Dialog and Discourse Processing Technology

For a detailed list of topics of interest, see
http://nlp.postech.ac.kr/sigdial2012/topics.htm.

Special Theme

Coherence, whether understood as 'general overall interrelatedness' or
'continuity in meaning and context' (Louwerse and Graesser, 2005) is a
topic that spans research on discourse and on dialog and has strong
connections to research on coreference, discourse structure,
dialog/task modeling, natural language generation, etc.  The special
theme for SIGDIAL 2012 is 'characterizing dialog coherence', where
dialog includes multi-party interaction.  We welcome theoretical,
analytical, computational or interdisciplinary submissions on this
topic.

SUBMISSIONS

The program committee welcomes the submission of long papers, short
papers, and demo descriptions. All accepted submissions will be
published in the conference proceedings.
    * Long papers will be presented in full plenary presentations.
They must be no longer than 8 pages, including title, content, and
examples. Two additional pages are allowed for references and
appendices which may include extended example discourses or dialogs,
algorithms, graphical representations, etc.
    * Short papers will be featured in short plenary presentations,
followed by posters. They should be no longer than 4 pages.  One
additional page is allowed for references and appendices.
    * Demonstrations will be presented in special sessions, separate
from short paper presentations and poster sessions. Demo descriptions
will appear in a dedicated section of the proceedings and should be no
longer than 3 pages, inclusive of references. To encourage late
breaking demos, demo submissions have a later deadline.

Papers that have been or will be submitted to other meetings or
publications must provide this information (see submission format).
SIGDIAL 2012 cannot accept for publication or presentation work that
will be (or has been) published elsewhere, except for demonstrations.
Any questions regarding submissions can be sent to the technical
program co-chairs at program-chairs[at]sigdial.org.

Authors are encouraged to submit additional supportive material such
as video clips or sound clips and examples of available resources for
review purposes.

Submission is electronic using paper submission software at:
https://www.softconf.com/c/sigdial2012/

FORMAT

All long, short, and demo submissions should follow the two-column
ACL-HLT 2012 format. We strongly recommend the use of ACL LaTeX style
files or Microsoft Word style files tailored for ACL-HLT 2012
conference. Submissions must conform to the official ACL-HLT 2012
style guidelines (http://www.acl2012.org/call/sub01.asp), and they
must be electronic in PDF. As in most previous years, submissions will
not be anonymous.

MENTORING SERVICE

The mentoring service offered last year has been very beneficial. We
will follow the same practice this year. Submissions with innovative
core ideas that may need language (English) or organizational
assistance will be flagged for 'mentoring' and conditionally accepted
with recommendation to revise with a mentor. An experienced mentor who
has previously published in the SIGDIAL venue will then help the
authors of these flagged papers prepare their submissions for
publication. Any questions about the mentoring service can be
addressed to the mentoring service chair, Dr. Kallirroi Georgila, at
kgeorgila[at]ict.usc.edu.

BEST PAPER AWARDS

In order to recognize significant advancements in dialog and discourse
science and technology, SIGDIAL will recognize two best paper awards.
A selection committee consisting of prominent researchers in the
fields of interest will select the recipients of the awards.

SPONSORSHIP

SIGDIAL also offers a number of opportunities for sponsors. For more
information, email Jason Williams, Sponsorship Chair, at
jdw[at]research.att.com.

Dialogue and Discourse

SIGDIAL authors are encouraged to submit their research to the journal
Dialogue and Discourse, which is endorsed by SIGDIAL.

IMPORTANT DATES

Long and Short Papers
 Submission Deadline	March 26, 23:59, GMT-11, 2012
 Paper Notification	May 7, 2012
 Final Paper Due	June 4, 2012

Demos
 Submission Deadline	May 14, 2012
 Notification		May 21, 2012
 Final Paper Due	June 4, 2012

Conference   		July 5-6, 2012

ORGANIZING COMMITTEE

For any questions, please contact the appropriate members of the
organizing committee:

General Co-Chairs
Gary Geunbae Lee, POSTECH, South Korea
Jonathan Ginzburg, Universite Paris-Diderot, France

Technical Program Co-Chairs
Claire Gardent, CNRS/LORIA Nancy, France
Amanda Stent, AT&T Labs - Research, USA

Mentoring Chair
Kallirroi Georgila, University of Southern California Institute for
Creative Technologies

Local Chair
Minhwa Chung, Seoul National University

Sponsorships Chair
Jason Williams AT&T Labs - Research, USA

SIGDIAL President
Tim Paek, Microsoft Research, USA

SIGDIAL Vice President
Amanda Stent, AT&T Labs - Research, USA

SIGDIAL Secretary/Treasurer
Kristiina Jokinen, University of Helsinki, Finland

Back

Top

  Special Session at Interspeech 2012

Speech and Audio Analysis of Consumer and Semi-Professional Multimedia

             http://interspeech2012.org/Special.html

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


Consumer-grade and semi-professional multimedia material (video) is becoming abundant on the Internet and other online archives. It is easier than ever to download material of any kind. With cell-phones now featuring video recording capability along with broadband connectivity, multimedia material can be recorded and distributed across the world just as easily as text could just a couple of years ago. The easy availability of vast amounts of text gave a huge boost to the Natural Language Processing and Information Retrieval research communities, The above-mentioned multimedia material is set to do the same for multi-modal audio and video analysis and generation. We argue that the speech and language research community should embrace that trend, as it would profit vastly from the availability of this material, and has significant own know-how and experience to contribute, which will help shape this field.

Consumer-created (as opposed to broadcast news, “professional style”) multimedia material offers a great opportunity for research on all aspects of human-to-human as well as man-machine interaction, which can be processed offline, but on a much larger scale than is possible in online, controlled experiments. Speech is naturally an important part of these interactions, which can link visual objects, people, and other observations across modalities. Research results will inform future research and development directions in interactive settings, e.g. robotics, interactive agents, etc., and give a significant boost to core (offline) analysis techniques such as robust audio and video processing, speech and language understanding, as well as multimodal fusion.

Large-scale multi-modal analysis of audio-visual material is beginning in a number of multi-site research projects across the world, driven by various communities, such as information retrieval, video search, copyright protection, etc. While each of these have slightly different targets, they are facing largely the same challenges: how to robustly and efficiently process large amounts of data, how to represent and then fuse information across modalities, how to train classifiers and segmenters on un-labeled data, how to include human feedback, etc. Speech, language and audio researchers have considerable interest and experience in these areas, and should be at the core and forefront of this research. To make progress at a useful rate, researchers must be connected in a focused way, and be aware of each other’s work, in order to discuss algorithmic approaches, ideas for evaluation and comparisons across corpora and modalities, training methods with various degrees of supervision, available data sets, etc. Sharing software, databases, research results and projects' descriptions are some of the key elements to success which are at the core of the Speech and Language in Multimedia (SLIM) SIG's objectives.

The special session will serve these goals by bringing together researchers from different fields – speech, but also audio, multimedia – to share experience, resources and foster new research directions and initiatives. Contributions are expected on all aspects of speech and audio processing for multimedia contents: research results but also presentation of ongoing research projects or software, multimedia databases and benchmarking initiatives, etc. A special session, as opposed to a regular session, offers unique opportunities to emphasize interaction between participants with the goal of strengthening and growing the SLIM community. The following format will be adopted: a few selected talks targeting a large audience (e.g., project or dataset descriptions, overview) will open the session, followed by a panel and open discussion on how to develop our community along with poster presentations.

Back

Top

Symposium on Machine Learning in Speech and Language Processing (MLSLP) http://ttic.edu/sigml/symposium2012/

This is the second annual meeting of the ISCA Special Interest Group on Machine Learning (SIGML).  

It will include invited talks and general submissions.  The deadline for general submissions is June 15, 2012.  

Please see the web site for up-to-date information.

Call for Participation

The goal of the symposium is to foster communication and collaboration between researchers in these synergistic areas, taking advantage of the nearby location of Interspeech 2012. It is the second annual meeting of the Machine Learning Special Interest Group (SIGML) of the International Speech Communication Association (ISCA). (See last year's symposium here.)

Topics

The workshop will feature both invited talks and general submissions. Submissions focusing on novel research are solicited. In addition, we especially encourage position and review papers addressing topics that are relevant to speech, machine learning, and NLP research. These areas include, but are not limited to, applications to speech/NLP of SVMs, log-linear models, neural networks, kernel methods, discriminative transforms, large-margin training, discriminative training, active/semi-supervised/unsupervised learning, structured prediction, Bayesian modeling, deep learning, and sparse representations.

Paper Submission

Prospective authors are invited to submit papers written in English via the 'Submissions' link to the left. Each paper will be reviewed by at least two reviewers, and each accepted paper must have at least one registered author.

Invited Speakers

Shai Ben-David, Inderjit Dhillon, Mark Gales, Brian Roark, Dirk van Compernolle, additional speakers TBA

Organizing Committee

Back

Top

IWSDS'2012 Workshop on Spoken Dialogue Systems

Towards a Natural Interaction with Robots, Knowbots and Smartphones

http://www.iwsds.org

Following the success of IWSDS’2009 (Irsee, Germany), IWSDS’2010 (Gotemba Kogen Resort, Japan) and IWSDS’2011 (Granada, Spain), the Fourth International Workshop on Spoken Dialog Systems (IWSDS 2012) will be held in Paris (France) on November 28-30, 2012.

The IWSDS Workshop series provides an international forum for the presentation of research and applications and for lively discussions among researchers as well as industrialists, with a special interest to the practical implementation of Spoken Dialog Systems in everyday applications.

Spoken dialog is a matter of research investigations for many years. The first spoken language processing systems aimed at providing such an interaction between humans and machines. It slowly appeared that the problem was much more difficult than it was initially thought, as it involves many different components: speech recognition and understanding, prosody analysis, indirect speech acts, dialog handling, maintenance of the communication with verbal or non verbal events such as backchannels, speech generation and synthesis, multimodal fusion and fission, etc. Social interaction among humans is characterized by a continuous and dynamic exchange of information carrying signals. Producing and understanding these signals allow humans to communicate simultaneously on multiple levels. The ability to understand this information, and for that matter adapt generation to the goal of the communication and the characteristics of particular interlocutors, constitutes a significant aspect of natural interaction. It shows that it is actually very complex to develop simple, natural interaction means.

 Even if the research investigations kept on being conducted, it resulted in a shift of interest to easier tasks, such as voice command, voice dictation, or speech transcription. However, scientific achievements in language processing now results in the development of successful applications such as the IBM Watson, the Evi, Apple SIRI or Google Assistant for access to knowledge and interaction with smartphones, while the coming of domestic robots advocates for the development of powerful communication means with their human users and fellow robots.

We welcome you to the workshop.

Joseph Mariani (LIMSI & IMMI-CNRS) (Chair)
Laurence Devillers (LIMSI-CNRS & University Paris-Sorbonne 4)
Martine Garnier-Rizet (IMMI-CNRS)
Sophie Rosset (LIMSI-CNRS)

IWSDS 2012 Program Committee

Back

Top