Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2007-05-08
2007-05-08
Armstrong, Angela (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
Reexamination Certificate
active
09433609
ABSTRACT:
A method and apparatus are provided for automatically training or modifying one or more models of acoustic units in a speech recognition system. Acoustic models are modified based on information about a particular application with which the speech recognizer is used, including speech segment alignment data for at least one correct alignment and at least one wrong alignment. The correct alignment correctly represents a phrase that the speaker uttered. The wrong alignment represents a phrase that the speech recognition system recognized that is incorrect. The segment alignment data is compared by segment to identify competing segments and those that induced the recognition error. When an erroneous segment is identified, acoustic models of the phoneme in the correct alignment are modified by moving their mean values closer to the segment's acoustic features. Concurrently, acoustic models of the phoneme in the wrong alignment are modified by moving their mean values further from the acoustic features of the segment of the wrong alignment. As a result, the acoustic models will converge to more optimal values based on empirical utterance data representing recognition errors.
REFERENCES:
patent: 5027406 (1991-06-01), Roberts et al.
patent: 6076053 (2000-06-01), Juang et al.
patent: 6076057 (2000-06-01), Narayanan et al.
patent: 6260013 (2001-07-01), Sejnoha
patent: 6272462 (2001-08-01), Nguyen et al.
B. Juang et al., “Discriminative Learning for Minimum Error Classification,” IEEE Transactions on Signal Processing 40:12 (Dec. 1992), at 3043.
Q. Huo et al., “A Study of On-Line Quasi-Bayes Adaptation for CDHMM-Based Speech Recognition,” IEEE Trans. on Speech and Audio Processing, vol. 2, at 705 (1996).
A. Sankar et al., “An Experimental Study of Acoustic Adaptation Algorithms,” IEEE Trans. on Speech and Audio Processing, vol. 2, at 713 (1996).
L. Bahl et al., “Discriminative Training of Gaussian Mixture Models for Large Vocabulary Speech Recognition Systems,” IEEE Trans. on Speech and Audio Processing, vol. 2, at 613 (1996).
Barnard Etienne
Dahan Jean-Guy
Armstrong Angela
Bromberg & Sunstein LLP
SpeechWorks International, Inc.
LandOfFree
Method and apparatus for discriminative training of acoustic... 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 and apparatus for discriminative training of acoustic..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for discriminative training of acoustic... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3816436