8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Audio-Visual Spoken Language Processing

Jinyoung Kim (1), Jeesun Kim (2), Chris Davis (2)

(1) Chonnam University, Korea
(2) The University of Melbourne, Australia

The multimodal character of speech processing has attracted research endeavors that range from engineers working on automatic speech recognition through to psychologists interested in language processing. This paper serves as a broad introduction to the special Audio-Visual Spoken Language (AVSP) session. The paper focuses on recent developments in the area and touches on theory as well as application. We consider how the scope of the conception of AVSP has broadened; how issues concerning the developmental aspects of AVSP have been tackled; how measures of AV processing have become more sophisticated and how new applications incorporating the visual aspects of speech have been devised. The main aim of this limited review is to highlight the range of the issues and the innovative nature of research programs that fall within this area.

Full Paper

Bibliographic reference.  Kim, Jinyoung / Kim, Jeesun / Davis, Chris (2004): "Audio-visual spoken language processing", In INTERSPEECH-2004, 1133-1136.