Accession Number : ADD017842

Title :   Training of Homoscedastic Hidden Markov Models For Automatic Speech Recognition.

Corporate Author : DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s) : Luginbuhl, Tod E ; Rosseau, Michael L

Report Date : Dec 1995

Pagination or Media Count : 10

Abstract : A method for training a speech recognizer in a speech recognition system is described. The method of the present invention comprises the steps of providing a data base containing acoustic speech units, generating a homoscedastic hidden Markov model from the acoustic speech units in the data base, and loading the homoscedastic hidden Markov model into the speech recognizer. The hidden Markov model loaded into the speech recognizer has a single covariance matrix which represents the tied covariance matrix of every Gaussian probability density function PDF for every state of every hidden Markov model structure in the homoscedastic hidden Markov model. (AN)

Descriptors :   *SPEECH RECOGNITION, *PATTERN RECOGNITION, *PATENTS, DATA BASES, MATHEMATICAL MODELS, MAXIMUM LIKELIHOOD ESTIMATION, MATRICES(MATHEMATICS), TIME SERIES ANALYSIS, INPUT OUTPUT PROCESSING, PROBABILITY DENSITY FUNCTIONS, ACOUSTIC SIGNALS, SPEECH ANALYSIS, SYSTEMS ANALYSIS, COVARIANCE, STATISTICAL PROCESSES, AUTOMATIC, ACOUSTIC DATA, MARKOV PROCESSES, PHONETICS

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE