Advances in Mandarin Broadcast Speech Transcription at IBM Under the DARPA GALE Program

This paper describes the technical and system building advances in the automatic transcription of Mandarin broadcast speech made at IBM in the first year of the DARPA GALE program. In particular, we discuss the application of minimum phone error (MPE) discriminative training and a new topic-adaptive language modeling technique. We present results on both the RT04 evaluation data and two larger community-defined test sets designed to cover both the broadcast news and the broadcast conversation domain. It is shown that with the described advances, the new transcription system achieves a 26.3% relative reduction in character error rate over our previous best-performing system, and is competitive with published numbers on these datasets. The results are further analyzed to give a comprehensive account of the relationship between the errors and the properties of the test data.

[1]  Jean-Luc Gauvain,et al.  Lightly supervised acoustic model training using consensus networks , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Geoffrey Zweig,et al.  fMPE: discriminatively trained features for speech recognition , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[3]  S. Wegmann,et al.  Speaker normalization on conversational telephone speech , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[4]  Ronald Rosenfeld,et al.  Using story topics for language model adaptation , 1997, EUROSPEECH.

[5]  Dongxin Xu,et al.  The BBN Mandarin broadcast news transcription system , 2005, INTERSPEECH.

[6]  George Saon,et al.  Maximum likelihood discriminant feature spaces , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[7]  Geoffrey Zweig,et al.  Advances in speech transcription at IBM under the DARPA EARS program , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[8]  Mark J. F. Gales,et al.  The Cu-Htk Mandarin Broadcast News Transcription System , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[9]  Daniel Povey,et al.  Minimum Phone Error and I-smoothing for improved discriminative training , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[10]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

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

[12]  Ricky Ho Yin Chan,et al.  Improving broadcast news transcription by lightly supervised discriminative training , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.