Investigating data selection for minimum phone error training of acoustic models

Shih Hung Liu, Fang Hui Chu, Shih Hsiang Lin, Berlin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper considers minimum phone error (MPE) Dased discriminative training of acoustic models for Mandarin broadcast news recognition. A novel data selection approach based on the normalized frame-level entropy of Gaussian posterior probabilities obtained from the word lattice of the training utterance was explored. It has the merit of making the training algorithm focus much more on the training statistics of those frame samples that center nearly around the decision boundary for better discrimination. Moreover, we presented a new phone accuracy function based on the frame-level accuracy of hypothesized phone arcs instead of using the raw phone accuracy function of MPE training. The underlying characteristics of the presented approaches were extensively investigated and their performance was verified by comparison with the original MPE training approach. Experiments conducted on the broadcast news collected in Taiwan showed that the integration of the frame-level data selection and accuracy calculation could achieve slight but consistent improvements over the baseline system.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
Pages348-351
Number of pages4
Publication statusPublished - 2007 Dec 1
EventIEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, China
Duration: 2007 Jul 22007 Jul 5

Publication series

NameProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

Other

OtherIEEE International Conference onMultimedia and Expo, ICME 2007
CountryChina
CityBeijing
Period07/7/207/7/5

    Fingerprint

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Liu, S. H., Chu, F. H., Lin, S. H., & Chen, B. (2007). Investigating data selection for minimum phone error training of acoustic models. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007 (pp. 348-351). [4284658] (Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007).