Feature extraction and normalization for speech recognition

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 213, 395 233, G10L 916

Patent

active

057129568

ABSTRACT:
Speech data is converted into logarithmic spectrum data and orthogonally transformed to develop feature vectors. Normalization coefficient data and unit vector data are stored. An inner product of the feature vector data and the unit vector data is calculated. The inner product may be the average of inner products for a word or a sentence, or may be a regressive average of them. A normalization vector, which corresponds to a second or higher order curve obtained by least-square error approximation of the speech data on logarithmic spectrum space, is calculated on the transformed feature vector space by using the inner product, the normalization coefficient data, and the unit vector data. Normalization of the feature vectors is performed by subtracting the normalization vector from the feature vectors on the transformed feature vector space. Then, a recognition is performed based on the normalized feature vector.

REFERENCES:
patent: 4520500 (1985-05-01), Mizuno et al.
patent: 4625286 (1986-11-01), Papamichalis et al.
patent: 4837828 (1989-06-01), Watari
patent: 4852181 (1989-07-01), Morito et al.
patent: 5001761 (1991-03-01), Hattori
patent: 5555320 (1996-09-01), Irie et al.
patent: 5604839 (1997-02-01), Acero et al.
patent: 5617508 (1997-04-01), Reaves
Nakajima et al., "Estimation of Vocal Tract Sectional Area Functions by Adaptive Inverse Filter Method", Proc., Accoustical Society of Japan, May, 1973, pp. 163-164.
Furui, "Digital Speech Processing", Tokai University Publishing Society, 1985, pp. 44-47.
Hino, "Spectrum Analysis", Asakura Bookstore, 1977, pp. 62-63.
Nakagawa, "Speech Recognition by Probability Models", The Institute of Electronics, Information and Communication Engineers, 1988, pp. 44-46.
Nakajima et al., "Estimation of vocal tract area functions by adaptive inverse filtering methods", Bulletin of the Electrotechnical Laboratory, 1973, Japan, vol. 37. No. 4, pp. 462-481.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Feature extraction and normalization for speech recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Feature extraction and normalization for speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature extraction and normalization for speech recognition will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-348678

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.