Speaker selection training via a-posteriori Gaussian mixture...

Details Speaker selection training via a-posteriori Gaussian mixture... Speaker selection training via a-posteriori Gaussian mixture...

2004-10-01

2009-08-11

Dorvil, Richemond (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S248000, C704S250000, C704S256000

Reexamination Certificate

active

07574359

ABSTRACT:
The present invention is directed to a 3-stage adaptation framework based on speaker selection training. First a subset of cohort speakers is selected for a test speaker. Then cohort models are transformed to be closer to the test speaker. Finally the adapted model for the test speaker is obtained by combining these transformed cohort models. Combination weights as well as bias items can be adaptively learned from adaptation data.

REFERENCES:
patent: 6073096 (2000-06-01), Gao et al.
patent: 6697778 (2004-02-01), Kuhn et al.
patent: 2005/0021335 (2005-01-01), Chaudhari et al.
patent: 2005/0251532 (2005-11-01), Radhakrishnan et al.
Gao et al., Y., “Speaker Adaptation Based on Pre-Clustering Training Speakers”, Proceedings of EuroSpeech '97, vol. 4, pp. 2091-2094, Sep. 1997.
Gales, M., “Cluster Adaptive Training of Hidden Markov Models”, IEEE Transactions on Speech and Audio Processing, vol. 8, No. 4, pp. 417-428, Jul. 2000.
Hazen, T., “A comparison of novel techniques for rapid speaker adaptation”, Speech Communication, vol. 31, pp. 15-33, 2000.
Huang et al., C., “Speaker Selection Training for Large Vocabulary Continuous Speech Recognition”, Proceedings ICASSP2002, 2002.
Huang et al., C., “Adaptive Model Combination for Dynamic Speaker Selection Training”, Proceedings ICSLP2002, vol. 1, pp. 65-68, 2002.
Kuhn et al., R., “Rapid Speaker Adaptation in Eigenvoice Space”, IEEE Transactions on Speech and Audio Processing, vol. 8, No. 6, pp. 695-707, Nov. 2000.
Lee et al., C., “A Study on Speaker Adaptation of the Parameters of Continuous Density Hidden Markov Models”, IEEE Transactions on Signal Processing, vol. 39, No. 4, pp. 806-814, Apr. 1991.
Leggetter et al., C., “Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models”, Computer Speech and Language, vol. 9, pp. 171-185, 1995.
Matrouf et al., D., “A Posteriori and a Priori Transformations for Speaker Adaptation in Large Vocabulary Speech Recognition Systems”, Eurospeech 2001, vol. 2, pp. 1245-1248, 2001.
Padmanabhan et al., M., “Speaker Clustering and Transformation for Speaker Adaptation in Speech Recognition Systems”, IEEE Transactions on Speech and Audio Processing, vol. 6, No. 1, Jan. 1998.
Yoshizawa et al., S., “Evaluation on Unsupervised Speaker Adaptation Based on Sufficient HMM Statistics of Selected Speakers”, Eurospeech 2001, vol. 2, pp. 1219-1222, 2001.
Reynolds et al., D., “Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models”, IEEE Transactions on Speech and Audio Processing, vol. 3, No. 1, pp. 72-83, Jan. 1995.

Affiliated with

Also associated with

Rating

Speaker selection training via a-posteriori Gaussian mixture... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speaker selection training via a-posteriori Gaussian mixture..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speaker selection training via a-posteriori Gaussian mixture... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4086744