Accession Number : ADD015771

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

Descriptive Note : Patent Application, Filed 24 Feb 93,

Corporate Author : DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s) : Luginbuhl, Tod ; Rousseau, Michael ; Streit, Roy

Report Date : 24 Feb 1993

Pagination or Media Count : 27

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 PDF for every state of every hidden Markov model structure in the homoscedastic hidden Markov Model

Descriptors :   *SPEECH RECOGNITION, *PATENT APPLICATIONS, MARKOV PROCESSES, MATHEMATICAL MODELS, COVARIANCE, NAVAL RESEARCH, DATA BASES, ACOUSTIC DATA

Subject Categories : Voice Communications

Distribution Statement : APPROVED FOR PUBLIC RELEASE