Dividing the distributions of HMM and linear interpolation in speech recognition

Kiyoshi Asai, Satoru Hayamizu, Ken'ichi Handa

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

1 Citation (Scopus)

Abstract

In this paper, we present an explicit criterion for deciding whether to divide the HMM-based phone model into more precise(for example, context dependent) models, or not. We also discuss the cases when linear interpolations of these models are used, and present an explicit solution of the interpolation weight λ. These criteria are obtained by evaluating the estimation errors of the distributions of these models. We show that the estimation errors should be evaluated by the projected covariance matrices of the estimation errors of the logarithm of the probabilities.

Original languageEnglish
Title of host publicationICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages29-32
Number of pages4
ISBN (Electronic)0780305329
DOIs
Publication statusPublished - 1992
Externally publishedYes
Event1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992 - San Francisco, United States
Duration: 1992 Mar 231992 Mar 26

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
ISSN (Print)1520-6149

Other

Other1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992
Country/TerritoryUnited States
CitySan Francisco
Period92/3/2392/3/26

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Dividing the distributions of HMM and linear interpolation in speech recognition'. Together they form a unique fingerprint.

Cite this