The focus of Winter School
on Speech and Audio Processing - 2009 (WiSSAP-09) is on Speaker and
Language Recognition. In the context of the growing significance of
speech signal processing for commercial, forensic and educational
applications the need for recognition of speakers, languages,
accent, and dialect, is fast becoming one of the central problems for
speech researchers around the world. In addition, with the rapid
proliferation of multimedia data, research in speaker-diarization,
indexing and retrieval is gathering rapid momentum. On the first day of
the School, talks will be given by eminent researchers from within
India covering the basics and fundamentals of these topics. Over the
next three days, expert speakers: Frederic Bimbot (IRISA, France), Jiri
Navratil (IBM, USA), and Andreas Stolcke (SRI, USA) will
cover in depth the theory, applications and practical aspects
of building state-of-the-art Speaker and Language-ID systems. In
addition, there will be sessions in the evenings where there will be
presentations from the Industry/Research Labs about their activities in
speech processing, interactions with the speakers and also discussion
on the open problems in this area.
WiSSAP-09 is targeted mainly towards post-graduate students, college-teachers/faculty in educational institutions and scientists/researchers in Research Labs/Industry who are interested in this area and would like to learn more about this area from some of the best researchers in the world.
WiSSAP 09 is being organized by International Speech Communication Association (ISCA), Institute of Electrical and Electronics Engineers - UP Section (IEEE - UP), BSNL-IITK Telecom Center and Indian Institue of Technology Kanpur (IIT Kanpur).
About WiSSAP:
The series of Winter School in Speech and Audio Processing provides a regular forum for research students, faculty and R&D engineers working in these areas to enhance their background and simplify the intricate research aspects involved in these areas. The schools work on a non-profit basis and hope to provide a platform for a qualitative exchange of ideas for utilizing speech technology in Indian Context. WiSSAP-09 is the fourth one in the series, following the very successful WiSSAP 06, WiSSAP 07 and WiSSAP 08.
WiSSAP-09 is targeted mainly towards post-graduate students, college-teachers/faculty in educational institutions and scientists/researchers in Research Labs/Industry who are interested in this area and would like to learn more about this area from some of the best researchers in the world.
WiSSAP 09 is being organized by International Speech Communication Association (ISCA), Institute of Electrical and Electronics Engineers - UP Section (IEEE - UP), BSNL-IITK Telecom Center and Indian Institue of Technology Kanpur (IIT Kanpur).
About WiSSAP:
The series of Winter School in Speech and Audio Processing provides a regular forum for research students, faculty and R&D engineers working in these areas to enhance their background and simplify the intricate research aspects involved in these areas. The schools work on a non-profit basis and hope to provide a platform for a qualitative exchange of ideas for utilizing speech technology in Indian Context. WiSSAP-09 is the fourth one in the series, following the very successful WiSSAP 06, WiSSAP 07 and WiSSAP 08.