Abstract for woodland_stw00

Proc. Speech Transcription Workshop, 2000

LARGE SCALE MMIE TRAINING FOR CONVERSATIONAL TELEPHONE SPEECH RECOGNITION

P.C. Woodland & D. Povey

May 2000

This paper describes a lattice-based framework for maximum mutual information estimation (MMIE) of HMM parameters which has been used to train HMM systems for conversational telephone speech transcription using up to 265 hours of training data. These experiments represent the largest-scale application of discriminative training techniques for speech recognition of which the authors are aware, and have led to significant reductions in word error rate for both triphone and quinphone HMMs compared to our best models trained using maximum likelihood estimation. The use of MMIE training was a key contributer to the performance of the CU-HTK March 2000 Hub5 evaluation system.


| (ftp:) woodland_stw00.ps.gz | (http:) woodland_stw00.ps.gz | (ftp:) woodland_stw00.pdf | (http:) woodland_stw00.pdf | (http:) woodland_stw00.html/ |

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.