Unsupervised incremental adaptation using maximum likelihood...

Details Unsupervised incremental adaptation using maximum likelihood... Unsupervised incremental adaptation using maximum likelihood...

2006-02-14

2006-02-14

McFadden, Susan (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S245000

Reexamination Certificate

active

06999926

ABSTRACT:
A maximum likelihood spectral transformation (MLST) technique is proposed for rapid speech recognition under mismatched training and testing conditions. Speech feature vectors of real-time utterances are transformed in a linear spectral domain such that a likelihood of the utterances is increased after the transformation. Cepstral vectors are computed from the transformed spectra. The MLST function used for the spectral transformation is configured to handle both convolutional and additive noise. Since the function has small number of parameters to be estimated, only a few utterances are required for accurate adaptation, thus essentially eliminating the need for training speech data. Furthermore, the computation for parameter estimation and spectral transformation can be done efficiently in linear time. Therefore, the techniques of the present invention are well-suited for rapid online adaptation.

REFERENCES:
patent: 4817156 (1989-03-01), Bahl et al.
patent: 5230037 (1993-07-01), Giustiniani et al.
patent: 5625749 (1997-04-01), Goldenthal et al.
patent: 5937384 (1999-08-01), Huang et al.
patent: 6006175 (1999-12-01), Holzrichter
patent: 6188982 (2001-02-01), Chiang
patent: 6539352 (2003-03-01), Sharma et al.
patent: 6760701 (2004-07-01), Sharma et al.
C.J. Leggetter et al. entitled “Speaker Adaptation of Continuous Density HMMs Using Multivariate Linear Regression,”International Conference on Spoken Language Processing, pp. 451-454 (1994).
D. Yuk et al. entitled “Adaptation to Environment and Speaker Using Maximum Likelihood Neural Networks,”Eurospeech, pp. 2531-2534 (Sep. 1999).
L.E. Baum entitled “An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes,”Inequalities, Chapter 3, pp. 1-8 (1972).
G.D. Forney, Jr. entitled “The Viterbi Algorithm,”Proceedings of the IEEE, vol. 61, No. 3, pp. 268-278 (Mar. 1973).
S. Furui entitled “Cepstral Analysis Technique for Automatic Speaker Verification,”IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-29(2), pp. 254-272, Sep. 1996.

Affiliated with

Also associated with

Rating

Unsupervised incremental adaptation using maximum likelihood... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Unsupervised incremental adaptation using maximum likelihood..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Unsupervised incremental adaptation using maximum likelihood... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3635265