[Elsnet-list] CFP, Interspeech 2007: Machine Learning for Spoken Dialogue Systems

Oliver Lemon olemon at gmail.com
Tue Feb 6 11:27:46 CET 2007


Machine Learning for Spoken Dialogue Systems:
Special Session at INTERSPEECH 2007, Antwerp, Belgium

Submission deadline: 23rd March
http://www.interspeech2007.org/

During the last decade, research in the field of Spoken Dialogue
Systems (SDS) has experienced increasing growth. Yet the design and
optimization of SDS does not simply involve combining speech and
language processing systems such as Automatic Speech Recognition
(ASR), parsers, Natural Language Generation (NLG), and Text-to-Speech
(TTS) synthesis. It also requires the development of dialogue
strategies taking into account the performances of these subsystems,
the nature of the dialogue task (e.g. form filling, tutoring, robot
control, or search), and the user's behaviour (e.g. cooperativeness,
expertise). Currently, statistical learning techniques are emerging
for training and optimizing speech recognition, parsing, and
generation in SDS, depending on representations of context. Automatic
learning of optimal dialogue strategies is also a leading research
topic.

Among machine learning techniques for dialogue strategy optimization,
Reinforcement Learning using Markov Decision Processes (MDPs) and
Partially Observable MDP (POMDPs) has become a particular focus. One
concern for such approaches is the development of appropriate dialogue
corpora for training and testing.

Dialogue simulation is often required to expand existing corpora and
so spoken dialogue simulation has  become a research field in its
own right. Other areas of interest are statistical approaches in
context-sensitive speech recognition, trainable NLG, and statistical
parsing for dialogue.

The purpose of this special session is to offer the opportunity to the
international community concerned with these topics to share ideas and
have constructive discussions in a single, focussed, special
conference session.

Submission instructions:

Researchers who are interested in contributing to this special session
are invited to submit a paper according to the regular submission
procedure of INTERSPEECH 2007, and to select "Machine Learning for
Spoken Dialogue Systems" in the special session field of the paper
submission form. The paper submission deadline is March 23, 2007.

The subjects to be covered include, but are not restricted to:

    * Reinforcement Learning of dialogue strategies
    * Partially Observable MDPs in dialogue strategy optimization
    * Statistical parsing in dialogue systems
    * Machine learning and context-sensitive speech recognition
    * Learning and NLG in dialogue
    * User simulation techniques for strategy learning and testing
    * Corpora and annotation for machine learning approaches to SDS
    * Machine learning for multimodal interaction
    * Evaluation of statistical approaches in SDS

Contact
Session organizers:

Oliver Lemon
Edinburgh University
School of Informatics

Olivier Pietquin
SUPÉLEC - Metz Campus
IMS Research Group
Metz


More information about the Elsnet-list mailing list