Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Improvements in Accuracy and Speed in the HTK Broadcast News Transcription System

P. C. Woodland (1,2), J. J. Odell (2), T. Hain (1), G. L. Moore (1), T. R. Niesler (1), Andreas Tuerk (1), E. W. D. Whittaker (1)

(1) Cambridge University Engineering Department, Cambridge, UK
(2) Entropic Ltd., Compass House, Cambridge, UK

This paper describes a number of recent improvements to the HTK Broadcast News Transcription System. Changes to the system include the use of more acoustic training data; use of cluster-based variance normalisation and vocal tract length normalisation; the use of interpolated language models and enhanced adaptation using a full variance transform. These changes produce an reduction in word error rate of 13%. A simplified version of the system has also been constructed that runs in less than 10 times real-time and gives a 2.3% absolute higher error rate than the 300xRT full system.

Full Paper (PDF)

Bibliographic reference.  Woodland, P. C. / Odell, J. J. / Hain, T. / Moore, G. L. / Niesler, T. R. / Tuerk, Andreas / Whittaker, E. W. D. (1999): "Improvements in accuracy and speed in the HTK broadcast news transcription system", In EUROSPEECH'99, 1043-1046.