US 5,963,906 A · Speech recognition training

Abstract

A method and system performs speech recognition training using Hidden Markov Models. Initially, preprocessed speech signals that include a plurality of observations are stored by the system. Initial Hidden Markov Model (HMM) parameters are then assigned. Summations are then calculated using modified equations derived substantially from the following equations, wherein u.ltoreq.v<w: P(X.sub.u.sup.v)=P(x.sub.u.sup.v)P(x.sub.v+1.sup.w) and .OMEGA..sub.ij (x.sub.u.sup.w)=.OMEGA..sub.ij (x.sub.u.sup.v)P(x.sub.v+1.sup.w)+P(x.sub.u.sup.v).OMEGA..sub.ij (x.sub.v+1.sup.w) The calculated summations are then used to perform HMM parameter reestimation. It then determines whether the HMM parameters have converged. If they have, the HMM parameters are then stored. However, if the HMM parameters have not converged, the system again calculates summations, performs HMM parameter reestimation using the summations, and determines whether the parameters have converged. This process is repeated iteratively until the HMM parameters have converged.

Claims8

Dependent claims

In a method of performing speech recognition training using Hidden Markov Models comprising the steps of storing preprocessed speech signals that include a plurality of observations, assigning initial model parameters, performing model reestimation using the Baum-Welch algorithm, and storing the model parameters if they have converged, wherein the improvement comprises:

partitioning the stored speech signals into at least a first and second set of training data;
calculating a first summation using the first set of training data;
calculating a second summation using the second set of training data;
calculating a final summation using the first and second summations;
and
using said final summation in the model reestimation step, wherein the first summation and the second summation are calculated on parallel processors.

3 more elements

Dependencies are inferred from the claim text.

Speech recognition training

Life of this patent

Speech recognition training

Life of this patent

Abstract

Claims8