Phoneme HMM evaluation algorithm without phoneme labeling applied to continuous speech hmm evaluation

1 January 1994

journal article
research article
Published by Wiley in Electronics and Communications in Japan (Part III: Fundamental Electronic Science)

Vol. 77 (11) , 13-21
https://doi.org/10.1002/ecjc.4430771102

Abstract

Phoneme Hidden Markov Model (HMM) are generally evaluated in terms of the phoneme recognition rate by using speech data extracted based on phoneme labels. This paper proposes an evaluation method that does not use phoneme labels for extraction. Consequently, phoneme HMMs can be evaluated even if a speech database without phoneme labeling is used.In this study, concatenation training of the phoneme HMMs is executed using a large‐scale speaker‐independent continuous‐speech database. Evaluation of the HMM phoneme recognition rate which is a function of the number of training speakers, using the proposed evaluation method demonstrates its effectiveness.

Keywords

This publication has 6 references indexed in Scilit:

Large-vocabulary speaker-independent continuous speech recognition using HMM
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
Minimizing speaker variation effects for speaker-independent speech recognition
Published by Association for Computational Linguistics (ACL) ,1992
A new paradigm for speaker-independent training
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1991
A new paradigm for speaker-independent training and speaker adaptation
Published by Association for Computational Linguistics (ACL) ,1990
Recent progress in the SPHINX Speech Recognition system
Published by Association for Computational Linguistics (ACL) ,1989
An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition
Bell System Technical Journal, 1983