Finding consensus among words: lattice-based word error minimization

We describe a new algorithm for finding the hypothesis in a recognition lattice that is expected to minimize the word error rate (WER). Our approach thus overcomes the mismatch between the word-based performance metric and the standard MAP scoring paradigm that is sentence-based, and that can lead to sub-optimal recognition results. To this end we first find a complete alignment of all words in the recognition lattice, identifying mutually supporting and competing word hypotheses. Finally, a new sentence hypothesis is formed by concatenating the words with maximal posterior probabilities. Experimentally, this approach leads to a significant WER reduction in a large vocabulary recognition task.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  Lalit R. Bahl,et al.  A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  John J. Godfrey,et al.  SWITCHBOARD: telephone speech corpus for research and development , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  D Gusfield,et al.  Efficient methods for multiple sequence alignment with guaranteed error bounds , 1993, Bulletin of mathematical biology.

[5]  D. Gusfield.  Efficient methods for multiple sequence alignment with guaranteed error bounds , 1993 .

[6]  Mitchel Weintraub,et al.  LVCSR log-likelihood ratio scoring for keyword spotting , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[7]  Mitch Weintraub,et al.  Explicit word error minimization in n-best list rescoring , 1997, EUROSPEECH.

[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]  Mitch Weintraub,et al.  Neural-network based measures of confidence for word recognition , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.