Accession Number : ADA319617

Title :   Recognition-Time Speaker Adaptation in a Tied-Mixture HMM Continuous Speech Recognizer.

Descriptive Note : Technical rept.,

Corporate Author : MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB

Personal Author(s) : Necioglu, B. F. ; Paul, D. B.

PDF Url : ADA319617

Report Date : 16 DEC 1996

Pagination or Media Count : 20

Abstract : All speech recognition systems, whether speaker-independent or speaker-dependent, require large amounts of training data to estimate the model parameters and, generally, the more training data available, the better the recognition performance. To improve the recognition performance of a system for a new speaker without having to train entirely new models, adapting the existing models during the recognition process is a practical solution. This report describes an investigation into the subject of recognition-time speaker adaptation of a tied-mixture HMM recognition system, with the goal of implementing a system which adapts to a new speaker during the course of its usage.

Descriptors :   *ADAPTIVE SYSTEMS, *SPEECH RECOGNITION, PARAMETERS, GAUSSIAN NOISE.

Subject Categories : Voice Communications

Distribution Statement : APPROVED FOR PUBLIC RELEASE