论文信息 - Transcription of broadcast news with a time constraint: IBM's 10xRT HUB4 system

Transcription of broadcast news with a time constraint: IBM's 10xRT HUB4 system

We describe a system which automatically transcribes broadcast news in less than 10 times real-time. We detail the system architecture of this system, which was used by IBM in the 1999 HUB4 10xRT evaluation, and show that the performance of this system is over 20 percent more accurate at the same speed than the system we used in the 1998 evaluation. Furthermore, we have closed the gap in word recognition accuracy between an unlimited resource system and this which runs in under 10 times real time from 45 percent to 14 percent.

[1] Jonathan G. Fiscus,et al. A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[2] Andreas Stolcke,et al. Finding consensus among words: lattice-based word error minimization , 1999, EUROSPEECH.

[3] Michael Picheny,et al. Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[4] Mark J. F. Gales,et al. Maximum likelihood linear transformations for HMM-based speech recognition , 1998, Comput. Speech Lang..

[5] Michael Picheny,et al. Speed improvement of the time-asynchronous acoustic fast match , 1999, EUROSPEECH.

[6] S. Chen,et al. Speaker, Environment and Channel Change Detection and Clustering via the Bayesian Information Criterion , 1998 .

[7] Michael Picheny,et al. Speed improvement of the tree-based time asynchronous search , 2000, INTERSPEECH.