Lattice-based unsupervised maximum likelihood linear...

Details Lattice-based unsupervised maximum likelihood linear... Lattice-based unsupervised maximum likelihood linear...

2007-05-08

2007-05-08

Lerner, Martin (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S244000, C704S246000

Reexamination Certificate

active

09670251

ABSTRACT:
Methods and arrangements using lattice-based information for unsupervised speaker adaptation. By performing adaptation against a word lattice, correct models are more likely to be used in estimating a transform. Further, a particular type of lattice proposed herein enables the use of a natural confidence measure given by the posterior occupancy probability of a state, that is, the statistics of a particular state will be updated with the current frame only if the a posteriori probability of the state at that particular time is greater than a predetermined threshold.

REFERENCES:
patent: 4829577 (1989-05-01), Kuroda et al.
patent: 4980918 (1990-12-01), Bahl et al.
patent: 5271088 (1993-12-01), Bahler
patent: 5598507 (1997-01-01), Kimber et al.
patent: 5625748 (1997-04-01), McDonough et al.
patent: 5822729 (1998-10-01), Glass
patent: 5864810 (1999-01-01), Digalakis et al.
patent: 5963903 (1999-10-01), Hon et al.
patent: 6003002 (1999-12-01), Netsch
patent: 6038528 (2000-03-01), Mammone et al.
patent: 6134527 (2000-10-01), Meunier et al.
patent: 6151574 (2000-11-01), Lee et al.
patent: 6226611 (2001-05-01), Neumeyer et al.
patent: 6272462 (2001-08-01), Nguyen et al.
patent: 6389393 (2002-05-01), Gong
patent: 6411929 (2002-06-01), Ishiwatari et al.
patent: 6411930 (2002-06-01), Burges
patent: 6421641 (2002-07-01), Huang et al.
patent: 6542866 (2003-04-01), Jiang et al.
patent: 6697778 (2004-02-01), Kuhn et al.
patent: 6847734 (2005-01-01), Hamamura
Woodland et al., “Iterative Unsupervised Adaptation Using Maximum Likelihood Linear Regression,” Fourth International Conference on Spoken Language, 1996. ICSLP 96. Proceedings. Oct. 3-6, 1996, vol. 2, pp. 1133 to 1136.
Padmanabhan et al., “Speaker clustering and transformation for speaker adaptation in speech recognition systems,” IEEE Transactions of Speech and Audio Processing, Jan. 1998, vol. 6, Issue 1, pp. 71 to 77.
Bahl et al., “Discriminative training of Gaussian mixture models for large vocabulary speech recognition sytems,” 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, May 7-10, 1996, vol. 2, pp. 613 to 616.
Y. Ephraim, “A Bayesian estimation approach for speech enhancement using hidden Markov models,” IEEE Transactions on Signal Processing, Apr. 1992, vol. 40, Issue 4, pp. 725 to 735.
Wikipedia, Definition of “Language Model”, Mar. 1, 2006, One Page.
Wikipedia, “Hidden Markov model”, 5 Pages.
M. Padmanabhan et al., “Lattice Based Unsupervised MLLR for Speaker Adaptation in Speech Recognition Systems”, ISCA ITRW ASR2000 Paris, France, 2000.
R. Kneser et al., “Improved Backing-off for n-gram Language Modeling”, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, 1995.
L. Mangu et al., “Lattice Compression in the Consensual Post-Processing Framework”, Proceedings of SCI/ISAS, Orlando, Florida, 1999.
T. Kemp et al., “Estimating Confidence Using Word Lattices”, Proceedings of ICASSP '97 , 1997.
G. Evermann et al., “Large Vocabulary Decoding and Confidence Estimation Using Word Posterior Probabilities”, Proceedings of ICASSP '00, 2000.
M. Padmanabhan et al., “Recent Improvements in Voicemail Transcription”, Proceedings of EUROSPEECH '99, Budapest, Hungary, 1999.
G. Saon et al., “Maximum Likelihood Discriminant Feature Spaces”, Proceecings of ICASSP '2000, Istanbul, 2000.
F. Wallhoff et al., “Frame-Discriminative and Confidence-Driven Adaptation for LVCSR”, Proceedings of ICASSP'00, 2000.
C.J. Leggetter et al., “Flexible Speaker Adaptation Using Maximum Likelihood Linear Regression”, Cambridge University Press.

Affiliated with

Also associated with

Rating

Lattice-based unsupervised maximum likelihood linear... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Lattice-based unsupervised maximum likelihood linear..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Lattice-based unsupervised maximum likelihood linear... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3823007