Speaker adaptation based on MAP estimation of HMM parameters

Authors:
Chin-Hui Lee;Jean-Luc Gauvain
Affiliations:
Speech Research Department, AT&T Bell Laboratories, Murray Hill, NJ;LIMSI, CNRS, Orsay, France and Speech Research Department, AT&T Bell Laboratories, Murray Hill, NJ
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 4
Cited 4

Bayesian learning of Gaussian mixture densities for hidden Markov models

HLT '91 Proceedings of the workshop on Speech and Natural Language
Bayesian learning for hidden Markov model with Gaussian mixture state observation densities

Speech Communication - Eurospeech '91
Vocabulary-independent speech recognition: the Vocind System

Vocabulary-independent speech recognition: the Vocind System
MAP estimation of continuous density HMM: theory and applications

HLT '91 Proceedings of the workshop on Speech and Natural Language

Speaker state recognition using an HMM-based feature extraction method

Computer Speech and Language
Aging speech recognition with speaker adaptation techniques: Study on medium vocabulary continuous Bengali speech

Pattern Recognition Letters
Adaptation to non-native speech using evolutionary-based discriminative linear transforms

Engineering Applications of Artificial Intelligence
Using out-of-language data to improve an under-resourced speech recognizer

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, Bayesian learning has been developed as a mathematical tool for obtaining maximum a posteriori (MAP) estimates of hidden Markov model (HMM) parameters. This framework offers a way to incorporate newly acquired application-specific data into existing acoustic HMMs and combine them in an optimal manner. It is therefore an efficient technique for handling the sparse training data problem which is often encountered in speech recognition. In this study a number of important issues related to the application of Bayesian learning techniques to speaker adaptation are investigated. We show that the seed models required to construct prior densities to obtain the MAP estimate can be a speaker-independent model, a set of female and male models or even a task independent acoustic model. Speaker-adaptive training algorithms are shown to be effective in improving the performance of both speaker-dependent and speaker-independent speech recognition systems.