The THISL spoken document retrieval project

Author

Renals, Steve

Author_Institution

Dept. of Comput. Sci., Sheffield Univ., UK

Volume

2

fYear

1999

fDate

36342

Firstpage

1049

Abstract

THISL is an ESPRIT Long Term Research Project focused on the automatic indexing and retrieval of broadcast television and radio programmes. In particular it is concerned with the production of a demonstrator news-on-demand system to navigate an archive of BBC news broadcasts. Prototype systems based on both British and North American broadcast news have been constructed. The North American system has been successfully evaluated within the framework of the TREC-6 and TREC-7 spoken document retrieval tracks, and the system based on BBC TV and radio news archives will be evaluated by BBC R&D

Keywords

indexing; information retrieval; multimedia systems; radio broadcasting; speech recognition; television broadcasting; BBC TV; BBC news broadcasts; British news; ESPRIT Long Term Research Project; North American system; THISL spoken document retrieval project; TREC-6; TREC-7 spoken document retrieval; automatic indexing; broadcast news; broadcast television; demonstrator news-on-demand system; radio news archives; radio programmes; Broadcast technology; Computer science; Error analysis; Information retrieval; Machine assisted indexing; Multimedia communication; Production systems; Radio broadcasting; Speech recognition; TV broadcasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Computing and Systems, 1999. IEEE International Conference on

Conference_Location

Florence

Print_ISBN

0-7695-0253-9

Type

conf

DOI

10.1109/MMCS.1999.778655

Filename

778655