Abstract for woodland_asr00

Proc. ASR 2000, Paris

LARGE SCALE DISCRIMINATIVE TRAINING FOR SPEECH RECOGNITION

P.C. Woodland & D. Povey

Sept 2000

This paper describes, and evaluates on a large scale, the lattice based framework for discriminative training of large vocabulary speech recognition systems based on Gaussian mixture hidden Markov models (HMMs). The paper concentrates on the maximum mutual information estimation (MMIE) criterion 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 MMIE lattice-based implementation used; techniques for ensuring improved generalisation; and interactions with maximum likelihood based adaptation are all discussed. Furthermore several variations to the MMIE training scheme are introduced with the aim of reducing over-training.


| (ftp:) woodland_asr00.ps.gz | (http:) woodland_asr00.ps.gz | (ftp:) woodland_asr00.pdf | (http:) woodland_asr00.pdf |

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.