Speech recognition using preclassification and spectral normaliz

Details Speech recognition using preclassification and spectral normaliz Speech recognition using preclassification and spectral normaliz

1989-05-09

1990-07-10

Harkcom, Gary V.

Electrical audio signal processing systems and devices

One-way audio signal program distribution

Public address system

381 43, G10L 500

Patent

active

049411780

ABSTRACT:
A two stage classification process is used in a speech recognition system. In the first stage, a slope vector template is generated from an extended LPC analysis using a universal bandwidth expansion technique. Using a dynamic programming technique, that first vector template identifies a subset of the overall vocabulary of the system. The speech signal is inverse filtered using the slope vector and a second LPC analysis is performed on the slope removed speech. The LPC vector is applied to an all-pass filter for initial nonlinear spectral shift of the speech. Final classification is then based on a normalizing spectral warp routine within a dynamic time warp program. The spectral warp is based on a closed form, near log transformation.

REFERENCES:
patent: 3387093 (1964-04-01), Stewart
patent: 3588363 (1971-06-01), Herscher
patent: 3681530 (1972-08-01), Manley et al.
patent: 4349700 (1982-09-01), Pirz et al.
patent: 4394538 (1983-07-01), Warren et al.
patent: 4400788 (1983-08-01), Myers et al.
patent: 4415767 (1983-11-01), Gill et al.
patent: 4454586 (1984-06-01), Pirz et al.
patent: 4488243 (1984-12-01), Brown et al.
patent: 4519094 (1985-05-01), Brown et al.
patent: 4712243 (1987-12-01), Ninomiya et al.
patent: 4715004 (1987-12-01), Kabasawa et al.
patent: 4718094 (1988-01-01), Bahl et al.
patent: 4720864 (1988-01-01), Tajima et al.
patent: 4736428 (1988-04-01), Deprettere et al.
Jaschul, "An Approach to Speaker Normalization for Automatic Speech Recognition", ICASSP 79, Apr. 2-4, 1979, pp. 235-238.
C. K. Chuang and S. W. Chan, "Speech Recognition Using Variable-Frame-Rate Coding", IEEE ICASSP, pp. 1,033-1,036, Apr. 1983.
F. Itakura, "Minimal Prediction Residual Principle Applied to Speech Recognition", IEEE Trans. ASSP, vol. 23, pp. 67-72, 1975.
S. E. Levinson, L. R. Rabiner, A. Rosenberg, and J. G. Wilpon, "Interactive Clustering Techniques for Selecting Speaker-Independent Reference Templates for Isolated Word Recognition", IEEE Trans. on Acoust., Speech, and Signal Proc., vol. 27, p. 134, '79.
A. Oppenheim et al., "Computation of Spectra with Unequal Resolution Using the Fast Fourier Transform", Proc. IEEE, vol. 59, pp. 299-301, Feb. 1971.
H. Sakoe and S. Chiba, "Dynamic Programming Algorithm Optimization for Spoken Word Recognition", IEEE Trans. ASSP, vol. 26, pp. 43-49, 1978.
"How Digital Signal Processing Works", High Technology, Oct. 1985.
H. Matsumoto and H. Wakita, "Speaker Normalization by Frequency Warping", Speech Research Semi., S79-25, Japan, Jul. 1979.
T. Fukabayashi et al., "Speech Segmentation and Recognition Using Adaptive Linear Prediction Algorithm", IEEE-ICASSP, pp. 17.12.1-17.12.4.

Affiliated with

Also associated with

Rating

Speech recognition using preclassification and spectral normaliz does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech recognition using preclassification and spectral normaliz, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition using preclassification and spectral normaliz will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1725367