Retrieval from spoken documents using content and speaker information

Author

Viswanathan, Mahesh ; Beigi, Homayoon S M ; Dharanipragada, Satya ; Tritschler, Alain

Author_Institution

IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA

fYear

1999

fDate

20-22 Sep 1999

Firstpage

567

Lastpage

572

Abstract

There has been a recent upsurge in the deployment of emerging technologies such as speech and speaker recognition which are reaching maturity. We discuss the details of the components required to build a system for audio indexing and retrieval for spoken documents using content and speaker based information facilitated by speech and speaker recognition. The real power of spoken document analysis is in using both content and speaker information together in retrieval by combining the results. The experiments described here are in the broadcast news domain, but the underlying techniques can easily be extended to other speech-centric applications and transactions

Keywords

audio signal processing; content-based retrieval; indexing; information retrieval; speech recognition; audio indexing; audio retrieval; broadcast news domain; content; speaker information; speaker recognition; speech recognition; speech-centric applications; speech-centric transactions; spoken document analysis; spoken document retrieval; Application specific integrated circuits; Content based retrieval; Data mining; Electrical capacitance tomography; Indexing; Information retrieval; Loudspeakers; Speaker recognition; Speech recognition; Text recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on

Conference_Location

Bangalore

Print_ISBN

0-7695-0318-7

Type

conf

DOI

10.1109/ICDAR.1999.791851

Filename

791851