Method for speaker adaptation of speech models recognition schem

Details Method for speaker adaptation of speech models recognition schem Method for speaker adaptation of speech models recognition schem

1997-04-09

1998-11-10

Dorvil, Richemond

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704256, G10L 708

Patent

active

058358900

ABSTRACT:
In a speaker adaptation method for speech models, input speech is transformed to a feature parameter sequence like a cepstral sequence, and N model sequences of maximum likelihood for the feature parameter sequence are extracted from speaker-independent speech HMMs by an N-best hypothesis extraction method. The extracted model sequences are each provisionally adapted to maximize its likelihood for the feature parameter sequence of the input speech while changing the HMM parameters of each sequence, and that one of the provisionally adapted model sequences which has the maximum likelihood for the feature parameter sequence of the input speech is selected and speech models of the selected sequence are provided as adapted HMMs of the speaker to be recognized.

REFERENCES:
patent: 4783804 (1988-11-01), Juang et al.
patent: 4829577 (1989-05-01), Kuroda et al.
patent: 5023912 (1991-06-01), Segawa
patent: 5046099 (1991-09-01), Nishimura
patent: 5050215 (1991-09-01), Nishimura
patent: 5233681 (1993-08-01), Bahl et al.
patent: 5278942 (1994-01-01), Bahl et al.
patent: 5289562 (1994-02-01), Mitzuta et al.
patent: 5293584 (1994-03-01), Brown et al.
patent: 5465317 (1995-11-01), Epstein
patent: 5497447 (1996-03-01), Bahl et al.
patent: 5502791 (1996-03-01), Nishimura et al.
patent: 5579436 (1996-11-01), Chou et al.
patent: 5621859 (1997-04-01), Schwartz et al.
patent: 5715367 (1998-02-01), Gillick et al.
patent: 5737489 (1998-04-01), Chou et al.
Matsui, Tomoko, et al., "N-Best Based Unsupervised Speaker Adaptation," IEICE Technical Report, vol. 96, No. 449, Jan. 17, 1997, pp. 1-8.

Affiliated with

Also associated with

Rating

Method for speaker adaptation of speech models recognition schem does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method for speaker adaptation of speech models recognition schem, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for speaker adaptation of speech models recognition schem will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1528755