Training of Homoscedastic Hidden Markov Models for Automatic Speech Recognition.

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

Document Details

Document Type
Technical Report
Publication Date
Feb 24, 1993
Accession Number
ADD015771

Entities

People

  • Michael Rousseau
  • Roy Streit
  • Tod Luginbuhl

Organizations

  • United States Department of the Navy

Tags

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Automatic
  • Covariance
  • Databases
  • Hidden Markov Models
  • Information Science
  • Inventions
  • Markov Models
  • Models
  • Natural Language Processing
  • Recognition
  • Training

Fields of Study

  • Engineering

Readers

  • Acoustics.
  • Computer Vision.
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation