Special Sessions

SS-5

Speech Technology for Under-Resourced Languages

Introduction
Most research in the field of speech technology has traditionally been conducted in very few languages such as English, French, Spanish or Chinese. The given special poster session is focused on research and development of new speech technologies for less-resourced national languages, mainly, used in the following large geographical regions: Eastern Europe, South and Southeast Asia, West Asia, North Africa, Sub-Saharan Africa. Usually these languages are under-presented at the Interspeech conferences and other ISCA-originated programs.

The special session is open to discuss problems and peculiarities of targeted languages in application to spoken language technologies, including but not limited to automatic speech recognition, text-to-speech, speech-to-speech translation, spoken dialogue systems in an internationalized context. When developing speech-based technologies researchers are faced with many new problems from lack of audio databases and linguistic resources (lexicons, grammars, text collections), to inefficiency of existing methods for language and acoustical modeling, and limited infrastructure for the creation of relevant resources. They often have to deal with novel linguistic phenomena that are poorly studied or researched (for instance, clicks in southern African languages, tone in many languages of the world, language switching in multilingual systems, etc). There are also lots of common problems and features in many groups of under-resourced languages and the aim of this special session is to provide a forum for the analysis of discussion of issues related to development of speech technologies/models/methods for these languages as well as to find some common approaches and solutions.

Well-written papers on targeted multi-language speech technologies are encouraged, and papers describing original results obtained for under-resourced languages, but important for well-elaborated languages too, are invited as well. Good papers from any countries and any authors may be accepted if they present new speech studies concerning the languages of interest of the special session. Submissions from countries suffering from under-resource language problems are high-priority for the given special session. All papers are expected to be submitted following the same schedule, procedure and format as for regular Interspeech papers, and will undergo the same blind review process by anonymous and independent reviewers as regular Interspeech-2011 papers. Authors shall also declare that their contributions are original and not being submitted for publication elsewhere (e.g., another conference, workshop, or journal). 4-page paper submission deadline is 31 March 2011 via the on-line paper submission system www.interspeech2011.org/ICMS/submissions. Accepted papers will appear in the Interspeech-2011 Proceedings and indexed in relevant databases (ISI), at least one author of each successful paper must register and attend the Interspeech-2011 in Florence and present own research in the poster form (exact date TBD).

Organizers:
The Interspeech-2011 special poster session on Speech Technology for Under-Resourced Languages is organized by a consortium of ISCA International Affairs Committee, SLTU International Workshop & Google Research. The alphabetical list of organizers is:

Etienne Barnard, North-West University, South Africa (etienne.barnard@gmail.com)
Laurent Besacier, Laboratoire d�Informatique de Grenoble, France (laurent.besacier@imag.fr)
Alexey Karpov, St. Petersburg Institute for Informatics and Automation, Russia (karpov_a@mail.ru)
Chafic Mokbel, University of Balamand, Lebanon (chafic.mokbel@balamand.edu.lb)
Pedro J. Moreno, Google Research, USA (pedro@google.com)
Yoshinori Sagisaka, Waseda University, Tokyo, Japan (ysagisaka@gmail.com)
Thippur Sreenivas, Indian Institute of Science, India (tvsree@ece.iisc.ernet.in)
Yun-Hsuan Sung, Google Research, USA (yhsung@google.com)