Speaker adaptation system and method based on class-specific pre

Details Speaker adaptation system and method based on class-specific pre Speaker adaptation system and method based on class-specific pre

1998-02-04

2000-06-06

Hudspeth, David R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704255, G10L 1506

Patent

active

06073096&

ABSTRACT:
A method of speech recognition, in accordance with the present invention includes the steps of grouping acoustics to form classes based on acoustic features, clustering training speakers by the classes to provide class-specific cluster systems, selecting from the cluster systems, a subset of cluster systems closest to adaptation data from a test speaker, transforming the subset of cluster systems to bring the subset of cluster systems closer to the test speaker based on the adaptation data to form adapted cluster systems and combining the adapted cluster systems to create a speaker adapted system for decoding speech from the test speaker. System and methods for building speech recognition systems as well as adapting speaker systems for class-specific speaker clusters are included.

REFERENCES:
patent: 5598507 (1997-01-01), Kimber et al.
patent: 5659662 (1997-08-01), Wilcox et al.
patent: 5787394 (1998-07-01), Bahl et al.
patent: 5793891 (1998-08-01), Takahashi et al.
patent: 5812975 (1999-04-01), Komori et al.
patent: 5835890 (1998-10-01), Matsui et al.
patent: 5864810 (1999-01-01), Digalakis et al.
patent: 5895447 (1999-04-01), Ittycheriah et al.
patent: 5983178 (1999-11-01), Naito et al.
X.D. Huang, "A Study on Speaker-Adaptive Speech Recognition", School of Computer Science, Carnegie Mellon University, Pittsburg, PA, pp. 278-283.
Richard Schwartz et al., "Comparative Experiments on Large Vocabulary Speech Recognition", BBN Systems & Technologies, Cambridge, MA, pp. 75-80.
F. Alleva et al., "Applying Sphinx-II to the DARPA Wall Street Journal CSR Task", School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, pp. 393-398.
Jean-Luc Gauvain et al., "Maximum a Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains", IEEE Transactions on Speech and Audio Processing, vol. 2, No. 2, Apr. 1994, pp. 291-298.
C. J. Leggetter et al., "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models", Computer Speech and Language, 1995, 9, pp. 171-185.
Tetsuo Kosaka et al., "Speaker-independent Speech Recognition Based on Tree-structured Speaker Clustering", Computer Speech and Language, 1996, 10, pp. 55-74.
M. Padmanabhan et al., "Speaker Clustering and Transformation for Speaker Adaptation in Large-Vocabulary Speech Recognition Systems", Apr. 1996, .COPYRGT.1995 IEEE.
M. Yamada et al., "Fast Algorithm for Speech Recognition Using Speaker Cluster HMM", ESCA, Eurospeech97, Rhodes Greece, ISSN 1018-4074, pp. 2043-2046.
Timothy J. Hazen et al., "A Comparison of Novel Techniques for Instantaneous Speaker Adaptation.sup.1 ", ESCA, Eurospeech97, Greece, ISSN 1018-4074, pp. 2047-2050.

Affiliated with

Also associated with

Rating

Speaker adaptation system and method based on class-specific pre 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 adaptation system and method based on class-specific pre, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speaker adaptation system and method based on class-specific pre will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2222948