Minimum word classification error training of HMMS for automatic speech recognition

This paper presents a novel discriminative training criterion, minimum word classification error (MWCE). By localizing conventional string-level MCE loss function to word-level, a more direct measure of empirical word classification error is approximated and minimized. Because the word-level criteri...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhi-Jie Yan, Bo Zhu, Yu Hu, Ren-Hua Wang
Format: Conference Proceeding
Language:English
Subjects:
Automatic speech recognition
Discriminative training
Hidden Markov models
Large-scale systems
Lattices
Loss measurement
Minimum classification error
Minimum word classification error
Optimization methods
Pipelines
Solids
Speech recognition
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel discriminative training criterion, minimum word classification error (MWCE). By localizing conventional string-level MCE loss function to word-level, a more direct measure of empirical word classification error is approximated and minimized. Because the word-level criterion better matches performance evaluation criteria such as WER, an improved word recognition performance can be achieved. We evaluated and compared MWCE criterion in a unified DT framework, with other commonly-used criteria including MCE, MMI, MWE, and MPE. Experiments on TIMIT and WS JO evaluation tasks suggest that word-level MWCE criterion can achieve consistently better results than string-level MCE. MWCE even outperforms other substring-level criteria on the above two tasks, including MWE and MPE.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2008.4518661