Method for speaker adaptation of speech models recognition scheme using the method and recording medium having the speech recognition method recorded thereon
Number of patents in Portfolio can not be more than 2000
United States of America Patent
Stats
-
Nov 10, 1998
Grant Date -
N/A
app pub date -
Apr 9, 1997
filing date -
Aug 2, 1996
priority date (Note) -
In Force
status (Latency Note)
Importance
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.
First Claim
Family
International Classification(s)
Cited Art Landscape
Patent Citation Ranking
Advertisement
Advertisement
Advertisement
Recipient Email Address
Recipient Email Address
Comment
Recipient Email Address
Add to Portfolio(s)
To add this patent to one, or more, of your portfolios, simply click the add button.
This Patent is in these Portfolios:
Add to additional portfolios:
Last Refreshed On:
Changes done successfully