ISCA - International Speech
Communication Association

ISCApad Archive  »  2011  »  ISCApad #154  »  Events  »  ISCA Supported Events

ISCApad #154

Friday, April 22, 2011 by Chris Wellekens

3-2 ISCA Supported Events
3-2-1(2011-06-17) SIGDIAL 2011 CONFERENCE: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue,Portland, Oregon


SIGDIAL 2011 CONFERENCE:   12th Annual Meeting of the Special Interest
Group on Discourse and Dialogue
June 17-18, 2011, Oregon Health & Science University in Portland Oregon
(Immediately preceding ACL-HLT 2011)

The  SIGDIAL venue provides  a regular forum  for  the presentation of
cutting edge research  in discourse and  dialogue to both academic and
industry  researchers.  Continuing with  a series of successful eleven
previous meetings, this conference spans the research interest area of
discourse and dialogue.  The conference  is  sponsored by  the SIGDIAL
organization, which serves as the Special  Interest Group in discourse
and dialogue  for both ACL  and ISCA. SIGDIAL  2011 will be co-located
with ACL-HLT 2011 as a satellite event.


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

1. Discourse Processing and Dialogue Systems

Discourse semantic  and pragmatic issues  in NLP  applications such as
text summarization,  question   answering, or information   retrieval,
including topics like:
* Discourse structure, temporal structure, information structure
* Discourse markers, cues and particles and their use
* (Co-)Reference and anaphora resolution, metonymy and bridging resolution
* Subjectivity, opinions and semantic orientation

Spoken, multi-modal, and text/web   based dialogue systems   including
topics such as:
* Dialogue management models
* Coordination of speech, gesture, and eye gaze
* Text and graphics integration
* Strategies for preventing, detecting or handling miscommunication
* Utilizing prosodic information for understanding and for disambiguation
* Embodied conversational agents

2. Corpora, Tools and Methodology

Corpus-based  work on discourse  and spoken, text-based or multi-modal
dialogue including its support, in particular:
* Annotation tools and coding schemes
* Data resources for discourse and dialogue studies
* Corpus-based techniques and analysis (including machine learning)
* Evaluation of systems and components: methodology, metrics and case

3. Pragmatic and/or Semantic Modeling

The pragmatics and/or semantics of discourse and dialogue (i.e. beyond
a single sentence) including the following issues:
* The semantics/pragmatics of dialogue acts (including those which are
   less studied);
* Models of discourse/dialogue structure +/- referential and relational
* Prosody in discourse and dialogue;
* Models of presupposition, accommodation, or conversational implicature.
* Grounded semantics in situated dialogue

4. Dimensions of Interaction

Methods to address how interaction is shaped by specific properties of
users, goals, modalities
* Turn taking within or across modalities
* User modeling
* Models of adaptation, such as entrainment
* Comparison of interactions of distinct types (e.g., task-based versus
* Multiparty interaction

5. Applications

The applications of dialogue and discourse processing technology in:
* Training and education/tutoring systems
* Entertainment and gaming applications
* Online chatting, blog, and social network analysis
* Human robot interaction


There has been   an increasing amount  of  work in   enabling situated
dialogue in both  the virtual world (e.g.,  human agent dialogue in  a
game  environment)  and the physical  environment  (e.g.,  human robot
dialogue). For  example, the GIVE  Initiative  has provided benchmarks
and  evaluations    for instruction     generation   in  3D    virtual
environments. More recently, the AAAI 2010  Fall Symposium on Dialogue
with Robots brought together   researchers from different  disciplines
who  brainstormed challenges and  future  directions in situated human
robot  dialogue.  To  continue  the  momentum  and   encourage broader
participation  in SIGDIAL, this  year we will  have a special theme on
'situated dialogue'.  We invite submissions that address any aspect of
this special topic.


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, examples,
   references, etc. In   addition to this,   two additional  pages  are
   allowed as an appendix which may include extended example discourses
   or dialogues, algorithms, graphical representations, etc.

* Short papers will  be featured in  a short paper spotlight  session,
   followed   by posters. They   should be 4   pages or less (including
   title, examples, references, etc.).

* This year's demonstrations  will be presented  in a special session,
   separated from  short paper presentations  and poster sessions. Demo
   descriptions will appear  in a dedicated  section of the proceedings
   and   should  be 3   pages   or  less   (including title,  examples,
   references,  etc.).   To   encourage  late  breaking    demos,  demo
   submissions have a  much later deadline compared  to long and  short

Papers that  have  been or  will  be submitted  to other  meetings  or
publications  must    provide    this information    (see   submission
format).  SIGDIAL 2011 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]

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

Submission  is  electronic    using  paper  submission  software   at:


All long,  short,  and demo  submissions should  follow the two-column
ACL-HLT 2011format. We strongly  recommend the use  of ACL LaTeX style
files  or Microsoft   Word style  files   tailored  for  ACL-HLT  2011
conference. Submissions  must  conform to  the  official  ACL-HLT 2011
style  guidelines, which are  contained in the  style  files, and they
must be electronic  in PDF.  As  in  most previous years,  submissions
will not be anonymous.

ACL-HLT 2011 Style Files

Latex: -
acl-hlt2011.tex -
acl-hlt2011.sty -
acl-hlt2011.pdf -
acl.bst -

MS Word: -
acl-hlt2011.doc - -
acl-hlt2011.pdf -


Long/Short Paper Submission Deadline:  February 25, 23:59, GMT-11, 2011
Long/Short Paper Notification:  April 15, 2011
Demo Submission Deadline:  April 19, 2011
Demo Notification:  April 26, 2011
Final Paper Submission (all types):  May 15, 2011
Conference:  June 17-18, 2011


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. Ronnie   Smith


In order to recognize significant advancements in dialog and discourse
science and technology, SIGDIAL will recognize a  BEST PAPER AWARD and
a BEST  STUDENT  PAPER AWARD.   A  selection committee   consisting of
prominent  researchers in   the  fields of   interest will  select the
recipients of the awards.


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

General  Co-Chairs (conference[at]
   Johanna Moore, The University of Edinburgh, UK;
   David Traum,  University  of Southern California, USA
Technical Program Co-Chairs (program-chairs[at],
   Joyce Chai, Michigan  State  University, USA;
   Rebecca J. Passonneau, Columbia University, USA
Program Committee: TBA
Mentoring Chair (mentoring[at]
   Ronnie Smith, East Carolina University, USA
Local Chair: Peter Heeman Oregon Health & Science University, USA
Sponsorships Chair (conference[at]
   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,

Back  Top

3-2-2(2011-06-27) CfP Symposium on Machine Learning in Speech and Language Processing, Bellevue, Washington



Call for Participation

 Symposium on Machine Learning in Speech and Language Processing

June 27, 2011

Bellevue, Washington, USA


The symposium will be held in Bellevue, Washington on June 27th, 2011. It will bring together members of the Association for Computational Linguistics ( ), the International Speech Communication Association (, and The International Machine Learning Society ( .  Its goal is to foster communication and collaboration between researchers in these synergistic areas, taking advantage of the nearby locations of ACL-HLT 2011 and ICML 2011.



The workshop will feature a series of invited talks and general submissions. Submissions focusing on novel research are solicited and we especially encourage position and review papers addressing topics that are relevant both to Speech, Machine Learning and NLP. These areas include but are not limited to the use of: SVMs, log-linear models, neural networks, kernel methods, discriminative transforms, large margin training, discriminative training, active, semi-supervised & unsupervised training, structured prediction, Bayesian modeling, deep learning , and sparse representations. Application areas include natural language processing, speech recognition, language modeling, and speaker verification.


Paper Submission

Prospective authors are invited to submit papers written in English via the symposium website. Style guidelines and further submission information will be available from the website. Each paper will be reviewed by at least two reviewers, and each accepted paper must have at least one registered author.


Important Dates

  • April 15 - Papers due
  • May 6 - Notification of acceptance
  • May 27 – Deadline for early registration
  • June 27 - Workshop


Venue, Accommodation and Registration

Venue: SIG-ML will be held at the Hyatt Regency Hotel in Bellevue, Washington, the site of ICML.

Accommodation:  A wide variety of lodging is available in the Bellevue area.

Registration: Please see the website for details.


Organizing Committee

Hal Daume III, University of Maryland; Joseph Keshet, TTI-Chicago;

 Dan Roth, UIUC; Geoffrey Zweig, Microsoft 


Scientific Program Committee

Jeff Bilmes, University of Washington; Brian Kingsbury, IBM; Karen Livescu, TTI-Chicago

Back  Top

3-2-3(2011-07-20)1st Lisbon Machine Learning School - 'Learning For the Web' Lisbon Portugal
1st Lisbon Machine Learning School - 'Learning For the Web'

We invite everyone interested in Machine Learning and Natural Language Processing to attend the 1st Lisbon Machine Learning School - LxMLS 2011.

Important Dates

* Application Deadline: March 31, 2011
* Decision: April 15, 2011
* Early Registration: May 31, 2011
* Summer School: July 20-26, 2011 (right in-between UAI and EMNLP)

Topics and Intended Audience

The school will cover a range of Machine Learning (ML) topics, from theory to practice, that are important in solving
Natural Language Processing (NLP) problems that arise in the analysis and use of Web data.

Our target audience is:

* Researchers and graduate students in the fields of NLP and Computational Linguistics;
* Computer scientists who have interests in statistics and machine learning;
* Industry practitioners who desire a more in depth understanding of these subjects.

Features of LxMLS:

* No deep previous knowledge of ML or NLP is assumed;
* Recommended reading will be provided in advance;
* Includes a strong practical component;
* A day zero is scheduled to review basic concepts and introduce the necessary tools for implementation exercises;
* Days will be divided into tutorials and practical sessions (view schedule);
* Both basic and advanced topics will be covered;
* Instructors are leading researchers in machine learning.

List of Speakers

* MÁRIO FIGUEIREDO - Instituto Superior Técnico | Portugal
* KOBY CRAMMER - Technion, Israel Institute of Technogly | Israel
* SLAV PETROV - Google Inc. | USA
* NOAH SMITH - Carnegie Mellon University | USA
* JASON EISNER - Johns Hopkins University | USA
* XAVIER CARRERAS - Universitat Politècnica de Catalunya | Spain
* MILES OSBORNE - University of Edinburgh | UK
* PHIL BLUNSOM - University of Oxford | UK
* JOÃO GRAÇA - University of Pennsylvania | USA

Please visit our webpage for up to date information:

To apply, please send a brief summary of your research interests (maximum 1 page) along with your CV
mentioning name, country, and affiliation to:

We are looking forward to your participation!

-- The organizers of LxMLS'2011.
Back  Top

3-2-4(2011-08-24) CfP SLaTE-2011 workshop Venice, Italy


We would like to invite you to submit a paper to the SLaTE-2011 workshop
August 24-26, 2011 (before Interspeech-2011 in Florence, Italy)
Ca' Foscari University, Venice, Italy

The ISCA (International Speech Communication Association) Special Interest Group (SIG) on Speech and Language Technology in Education (SLaTE) promotes the use of speech and language technology for educational purposes, and provides a forum for exchanging information (

The workshop will address all topics related to SLaTE, such as:
- Speech technology for education
- Natural language processing for education
- Spoken dialogue systems for education
- Applications using speech and/or natural language processing for education
- Intelligent tutoring systems using speech and natural language
- Development of language resources for SLaTE applications
- Assessment of SLaTE methods and applications

We especially welcome contributions on the future of Speech and Language Technology in Education, e.g. mobile learning, serious gaming, virtual reality, social media (networks), etc.
In addition, we would like to invite demonstrations of systems.

Full 4-page papers should be submitted before April 8, 2011.
Notification of acceptance or rejection of papers will be given by June 10, 2011.
For further information see
If you have questions, you can send an e-mail to SLaTE2011-org (at)

SLaTE-2011 will be organized by Helmer Strik, Catia Cucchiarini (Radboud University Nijmegen, the Netherlands, technical program), Rodolfo Delmonte and Rocco Tripodi (Ca' Foscari University, Venice, Italy, local organizers), within the framework of the ISCA-SIG SLaTE (see

Best regards,
Helmer Strik, Catia Cucchiarini, Rodolfo Delmonte, and Rocco Tripodi
The SLaTE-2011 Organizing Committee

Back  Top

3-2-5(2011-08-31) AVSP 2011 The 11th International Conference on Auditory-Visual Speech Processing

AVSP 2011 The 11th International Conference
on Auditory-Visual Speech Processing

August 31 - September 3, 2011

Volterra, Italy

The 11th international conference on Auditory-Visual Speech
Processing (AVSP) will be held from August 31 to September 3,
2011, directly following the INTERSPEECH2011 conference.

AVSP is a uniquely interdiciplinary conference, being focused on
synergy effects of auditory and visual speech information on
human perception, machine recognition, and human-machine
interaction. AVSP conferences have attracted a lot of researchers
in various fields, such as psychologists, computer engineers,
neuroscientists, linguists, phoneticians, and robot engineers.

The AVSP2011 conference will consist of oral and poster
presentations, a demo session and lectures by invited speakers
(announced later).

Submission of papers or demo proposals are invited in any areas
of auditory-visual speech processing including but not limited
* Audio-visual speech synthesis
* Audio-visual speech recognition by humans and machines
* Models of multimodal integration
* Multimodal processing of spoken events
* Cross-linguistic studies of audio-visual speech processing
* Developmental studies of audio-visual speech processing
* Role of gestures accompanying speech
* Audio-visual prosody
* Modeling, animation and recognition of gestures and expressions
* Neurophysiology and neuropsychology of audition and vision
* Scene analysis using audio and visual information
* Novel techniques for animation of talking faces
* Data collection and corpora for audio-visual speech processing

Important Dates

Paper Submission Deadline      5 May 2011 (Final)
Notification of Acceptance     16 June 2011
Camera-ready Paper             1 July 2011
Early Registration Deadline    27 June 2011
Late Registration Deadline     22 August 2011
Conference                     31 August - 3 September 2011


Prospective participants can submit a contribution in one of two
1. Full 4 or 6 page papers
2. 1 page demo proposals. Accepted proposals will be presented
  during a demo session at the conference

Submission instructions can be found on the conference website Submissions in both formats will be
reviewed by members of the scientific committee.

Organizing Committee

Jonas Beskow
Olov Engwall
Giampiero Salvi
Samer Al Moubayed

(Department of Speech, Music, and Hearing. KTH, Sweden.)

Scientific Committee

Gerard Bailly (GIPSA)
Piero Cosi (U.PADOVA)
Darren Cosker (U. BATH)
Sacha Fagel (ZOOBE)
Gabriele Fanelli (ETZH)
Björn Granström (KTH)
Valerie Hazan (UCL)
David House (KTH)
Carlos Ishi (ATR)
Alexandra Jesse (UMASS AMHERST)
Christian Kroos (MARCS)
Francisco Lacerda (STOCKHOLM U.)
Dominic W. Massaro (UCSC)
Slim Ouni (LORIA)
Catherine Pelachaud (PARIS TECH)
Gerasimos Potamianos (FORTH)
Laurel Riek (CAMBRIDGE)
Kaoru Sekiyama (U. KUMAMOTO)
Barry-John Theobald (UEA)

Registration Fees

Registration for the conference includes accommodation (3 nights),
meals and printed proceedings. Preliminary rates for early
registrants are 500 EUR for single room and 400 EUR for shared
double. Student attendees are encouraged to seek grants for
participation through ISCA.

Conference Website and Contact Info

Back  Top

3-2-6(2011-09-01) IWSDS2011 Workshop on Paralinguistic Information and its Integration in Spoken Dialogue Systems: satellite event of Interspeech 2011


Dear colleagues,

It is our pleasure to invite you to participate in this

IWSDS2011 Workshop on Paralinguistic Information and its Integration in Spoken Dialogue Systems

to be held at Saray hotel in Granada, Spain from September 1 to September 3, 2011.

Following on the success of IWSDS2009 (in Irsee, Germany) and IWSDS2010 (in Gotemba Kogen Resort, Japan) this 3rd International Workshop on Spoken Dialogue Systems (IWSDS2011) will bring together researchers from all over the world working in the field of spoken dialogue systems. It will provide an international forum for the presentation of research and applications and for lively discussions among researchers as well as industrialists.

This year's workshop designates 'Paralinguistic Information and its Integration in Spoken Dialogue Systems' as a special theme of discussion.  We would also like to encourage discussions of common issues of spoken dialogue systems.

The workshop will be held just after INTERSPEECH 2011; Florence, Italy, August 28-31, 2011 and is endorsed by SIGDIAL, a SIG of ISCA, and ACL. It is also supported by the Korean Society of Speech Scientists. The workshop proceedings will be published in a book by Springer.

We welcome you to the workshop.

Ramón López-Cózar - University of Granada (Spain)
Tetsunori Kobayashi - Waseda University (Japan)
Chairs of IWSDS2011

For questions, please contact:

Back  Top

 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2024 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA