Spoken language processing for audio archives of lectures and panel discussions

Author

Kawahara, Tatsuya

Author_Institution

Acad. Center for Comput. & Media Studies, Kyoto Univ., Japan

fYear

2004

fDate

1-2 March 2004

Firstpage

23

Lastpage

30

Abstract

Intelligent archiving systems of lectures and panel discussions based on automatic transcription and indexing are introduced. Our speech recognition system Julius has been improved to deal with these kinds of spontaneous speech. Transcriptions are automatically edited for improving readability, and then key sentences are indexed for each segment based on statistically derived discourse markers and topic words. For panel discussions consisting of multiple speakers, unsupervised speaker indexing is applied beforehand to segment audio into speaker turns. Thus, we realize efficient browsing of these audio archives.

Keywords

indexing; information retrieval systems; natural languages; speech processing; speech recognition; audio archives browsing; audio segmentation; automatic transcription; intelligent archiving system; natural language; panel discussion; speech recognition system; statistically derived discourse marker; unsupervised speaker indexing;

fLanguage

English

Publisher

ieee

Conference_Titel

Informatics Research for Development of Knowledge Society Infrastructure, 2004. ICKS 2004. International Conference on

Print_ISBN

0-7695-2150-9

Type

conf

DOI

10.1109/ICKS.2004.1313405

Filename

1313405