Method for speech processing involving whole-utterance modeling

Details Method for speech processing involving whole-utterance modeling Method for speech processing involving whole-utterance modeling

2005-11-01

2005-11-01

Ometz, David L. (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S246000, C704S243000, C704S256100

Reexamination Certificate

active

06961703

ABSTRACT:
A speech verification process involves comparison of enrollment and test speech data and an improved method of comparing the data is disclosed, wherein segmented frames of speech are analyzed jointly, rather than independently. The enrollment and test speech are both subjected to a feature extraction process to derive fixed-length feature vectors, and the feature vectors are compared, using a linear discriminant analysis and having no dependence upon the order of the words spoken or the speaking rate. The discriminant analysis is made possible, despite a relatively high dimensionality of the feature vectors, by a mathematical procedure provided for finding an eigenvector to simultaneously diagonalize the between-speaker and between-channel covariances of the enrollment and test data.

REFERENCES:
patent: 4720863 (1988-01-01), Li et al.
patent: 4837830 (1989-06-01), Wrench, Jr. et al.
patent: 5339385 (1994-08-01), Higgins
patent: 5414755 (1995-05-01), Bahler et al.
patent: 5526465 (1996-06-01), Carey et al.
patent: 5613037 (1997-03-01), Sukkar
patent: 5687287 (1997-11-01), Gandhi et al.
patent: 5754977 (1998-05-01), Gardner et al.
patent: 5806034 (1998-09-01), Naylor et al.
patent: 5832063 (1998-11-01), Vysotsky et al.
patent: 5835890 (1998-11-01), Matsui et al.
patent: 5873061 (1999-02-01), Hab-Umbach et al.
patent: 5960399 (1999-09-01), Barclay et al.
patent: 5983178 (1999-11-01), Naito et al.
patent: 6343267 (2002-01-01), Kuhn et al.
“On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word Recognition”, by L.R. Rabiner et al., published in the Bell System Technical Journal, vol. 62, No. 4, pp. 1075-1105, Apr. 1993.
“Recognition in Face Space”, by Matthew A. Turk and Alex P. Pentland, published in Automatic Recognition of Objects (SPIE Milestones), pp. 3-11, 1990.
“The Use of Multiple Measurements in Taxonomic Problems”, by R.A. Fisher, pp. 32.178a-32.188, reprinted from Annals of Eugenics, vol. VII, Part II, pp. 179-188, 1936.
Pattern Classification and Scene Analysis, by Richard O. Duda and Peter E. Hart, Part I, Section 4.10, “Fisher's Linear Discriminant”, pp. 114-118, 1973.
“An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes”, by Leonard E. Baum, pp. 1-8, published in Inequalities, vol. 3, No. 1, 1972.
“Maximum Likelihood from Incomplete Data via the EM Algorithm”, by A.P. Dempster et al., pp. 1-38, published in J. Royal Statistics Society, vol. 39, 1977.
VLSI Signal Processing, chapter 9 entitled, “Real Time Speech Processing”, pp. 308-315, 316-327 and 329-348, published by the IEEE Press, 1984.

Affiliated with

Also associated with

Rating

Method for speech processing involving whole-utterance modeling 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 for speech processing involving whole-utterance modeling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for speech processing involving whole-utterance modeling will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3518586