Training of homoscedastic hidden Markov models for automatic spe

Details Training of homoscedastic hidden Markov models for automatic spe Training of homoscedastic hidden Markov models for automatic spe

1993-02-24

1995-12-05

MacDonald, Allen R.

395 265, G10L 900

Patent

active

054737281

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.

REFERENCES:
patent: 4819271 (1989-04-01), Bahl et al.
patent: 4827521 (1989-05-01), Bahl et al.
patent: 5193142 (1993-03-01), Zhao
K. K. Paliwal, "A Study of LSF Representation For Speaker--Dependent and aker--Independent HMM-Based Speech Recognition Systems", ICASSP '90, 1990, pp. 801-804.
J. S. Bridle et al., "An Alphanet Approach to Optimising Input Transformations For Continuous Speech Recognition", ICASSP '91 1991 pp. 277-280.

Affiliated with

Also associated with

Rating

Training of homoscedastic hidden Markov models for automatic spe does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Training of homoscedastic hidden Markov models for automatic spe, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training of homoscedastic hidden Markov models for automatic spe will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1380698