Rapidly training a speech recognizer to a subsequent speaker giv

Details Rapidly training a speech recognizer to a subsequent speaker giv Rapidly training a speech recognizer to a subsequent speaker giv

1987-08-10

1989-03-28

Salce, Patrick R.

Electrical audio signal processing systems and devices

One-way audio signal program distribution

Public address system

3645135, G01L 500

Patent

active

048171565

ABSTRACT:
Apparatus and method for training the statistics of a Markov Model speech recognizer to a subsequent speaker who utters part of a training text after the recognizer has been trained for the statistics of a reference speaker who utters a full training text. Where labels generated by an acoustic processor in response to uttered speech serve as outputs for Markov models, the present apparatus and method determine label output probabilities at transitions in the Markov models corresponding to the subsequent speaker where there is sparse training data. Specifically, label output probabilities for the subsequent speaker are re-parameterized based on confusion matrix entries having values indicative of the similarity between an lth label output of the subsequent speaker and a kth label output for the reference speaker. The label output probabilities based on re-parameterized data are combined with initialized label output probabilities to form "smoothed" label output probabilities which feature smoothed probability distributions. Based on label outputs generated when the subsequent speaker utters the shortened training text, "basic" label output probabilities computed by conventional methodology are linearly averaged against the smoothed label output probabilities to produce improved label output probabilities.

REFERENCES:
patent: 4587670 (1986-05-01), Levinson et al.
patent: 4713777 (1987-12-01), Klovstad et al.
patent: 4713778 (1987-12-01), Baker
patent: 4718092 (1988-01-01), Klovstad
patent: 4718093 (1988-01-01), Brown
patent: 4718094 (1988-01-01), Bahl et al.
patent: 4741036 (1988-04-01), Bahl et al.
patent: 4748670 (1988-05-01), Bahl et al.
patent: 4759068 (1988-07-01), Bahl et al.
"An Introduction to Hidden Markov Models", Rabiner et al., IEEE ASSP Magazine, Jan. 1986, pp. 4-7.

Affiliated with

Also associated with

Rating

Rapidly training a speech recognizer to a subsequent speaker giv does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Rapidly training a speech recognizer to a subsequent speaker giv, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Rapidly training a speech recognizer to a subsequent speaker giv will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1666158