Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Recent Improvements in Speech Recognition Performance on Large Vocabulary Conversational Speech (Voicemail and Switchboard)

Jing Huang, B. Kingsbury, L. Mangu, Mukund Padmanabhan, George Saon, Geoffrey Zweig

IBM T. J. Watson Research Center, Yorktown Heights, NY, USA

In this paper we report recent improvements in word error performance on a voicemail transcription task. Last year, the speaker independent word error rate (WER) on the dev test set of the Voicemail Transcription task was reported at 35.45% [1]. This year, we report a relative 20% gain over this number. The improvements were obtained using several new algorithms and an increased amount of training data. In addition to benchmarking the performance of these algorithms on the Voicemail task, we have also evaluated them on the Switchboard task, and we report these results here as well. Finally, we also present the result of crossdomain experiments to evaluate the domain-independence of the constructed systems.

Reference

  1. M. Padmanabhan, G. Saon, S. Basu, J. Huang, G. Zweig, "Recent improvements on a Voicemail Transcription Task", Proceedings of Eurospeech 1999.


Full Paper

Bibliographic reference.  Huang, Jing / Kingsbury, B. / Mangu, L. / Padmanabhan, Mukund / Saon, George / Zweig, Geoffrey (2000): "Recent improvements in speech recognition performance on large vocabulary conversational speech (voicemail and switchboard)", In ICSLP-2000, vol.4, 338-341.