Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news

We describe extensions and improvements to IBM's system for automatic transcription of broadcast news. The speech recognizer uses a total of 160 hours of acoustic training data, 80 hours more than for the system described in Chen et al. (1998). In addition to improvements obtained in 1997 we made a number of changes and algorithmic enhancements. Among these were changing the acoustic vocabulary, reducing the number of phonemes, insertion of short pauses, mixture models consisting of non-Gaussian components, pronunciation networks, factor analysis (FACILT) and Bayesian information criteria (BIC) applied to choosing the number of components in a Gaussian mixture model. The models were combined in a single system using NIST's script voting machine known as rover (Fiscus 1997).

[1]  R. Gopinath.  CONSTRAINED MAXIMUM LIKELIHOOD MODELING WITH GAUSSIAN DISTRIBUTIONS , 2001 .

[2]  Richard M. Schwartz,et al.  A compact model for speaker-adaptive training , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[3]  Peder A. Olsen,et al.  Maximum likelihood estimates for exponential type density families , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[4]  Mark J. F. Gales,et al.  Tail distribution modelling using the richter and power exponential distributions , 1999, EUROSPEECH.

[5]  Ponani S. Gopalakrishnan,et al.  Clustering via the Bayesian information criterion with applications in speech recognition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

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

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

[8]  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.

[9]  Mark J. F. Gales.  Cluster adaptive training for speech recognition , 1998, ICSLP.

[10]  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.

[11]  Michael Picheny,et al.  Robust methods for using context-dependent features and models in a continuous speech recognizer , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Peder A. Olsen,et al.  IBM's LVCSR system for transcription of broadcast news used in the 1997 hub4 english evaluation , 1998 .

[13]  Mark J. F. Gales,et al.  Semi-tied covariance matrices for hidden Markov models , 1999, IEEE Trans. Speech Audio Process..