Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Recognition, Indexing and Retrieval of British Broadcast News with the THISL System

Tony Robinson (1), Dave Abberley (2), David Kirby (3), Steve Renals (2)

(1) SoftSound; (2) Sheffield University; (3) British Broadcasting Corporation; UK

This paper describes the THISL spoken document retrieval system for British and North American Broadcast News. The system is based on the Abbot large vocabulary speech recognizer and a probabilistic text retrieval system. We discuss the development of a realtime British English Broadcast News system, and its integration into a spoken document retrieval system. Detailed evaluation is performed using a similar North American Broadcast News system, to take advantage of the TREC SDR evaluation methodology. We report results on this evaluation, with particular reference to the effect of query expansion and of automatic segmentation algorithms.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Robinson, Tony / Abberley, Dave / Kirby, David / Renals, Steve (1999): "Recognition, indexing and retrieval of british broadcast news with the THISL system", In EUROSPEECH'99, 1267-1270.