Patent
1994-04-20
1997-11-25
MacDonald, Allen R.
395 241, 395 245, G10L 506
Patent
active
056921039
ABSTRACT:
In the recognition phase, the signal originating from a sensor is processed to obtain parameters which are compared with those stored in a dictionary in the learning phases so as to recognize the voice structures uttered by the user in a noisy environment. The obtaining of the said parameters during the learning and recognition phases includes the formation of digital frames of predetermined length from the signal originating from the sensor, the transformation of each frame from the time domain to the frequency domain to obtain a spectrum X(i), and the application of an inverse transformation, from the frequency domain to the time domain, to the magnitude .vertline.X(i).vertline..sup..gamma., where .vertline.X(i).vertline. represents the modulus of the spectrum and .gamma. represents an appropriate exponent.
REFERENCES:
patent: 4937872 (1990-06-01), Hopfield et al.
patent: 5027406 (1991-06-01), Roberts et al.
patent: 5127055 (1992-06-01), Larkey
patent: 5150449 (1992-09-01), Yoshida et al.
patent: 5345536 (1994-09-01), Hoshini et al.
patent: 5404422 (1995-04-01), Sakamoto et al.
patent: 5440661 (1995-08-01), Papcun
"Spectral Analysis Using Generalized Cepstrum" T. Kobayashi et al IEEE Trans on Acoustics, Speech, and Signal processing, vol. ASSP-32 N.degree. 5, Oct. 1984, pp. 1087-1089.
"Low dimensional representation of vowels based on all-pole modeling in the psychophysical domain" H. Hermansky et al, Speech communication, 1985, vol. 4, pp. 181-187.
"Linear predictive modeling of speech in modified spectral domains" H.Hermansky et al, STL Research Reports N.degree. 1, Nov. 1987 pp. 5.1-5.20.
International Conference on Acoustics Speech and Signal Processing vol. 2, 14 mai 1991, Toronto Canada pp. 957-960, Wu et al., "Fast self adapting broadband noise removal in the cepstral domain" (May 1991).
Treizieme Colloque sur le Traitement du Signal et des Images (Gretsi) 16 Sep. 1991, Juan les Pins France, pp. 733-736. Faucon, le Bouquin "Debruitage de la parole pour les radio-mobiles".
"Spectral Root Homomorphic Deconvolution System", J.S. LIM IEEE Trans. on Acoustics, Speech and Signal Processing, vol. ASSP-27 N.degree. 3, Jun. 1979, pp. 223-233.
"Optimization of perceptually-based ASR front-end" H. Hermansky et al Proc. IEEE-ICASSP, 1988, pp. 219-222.
"Use of Generalized Cepstral Distance Measure in Isolated Word Recognition", T. Kobayashi et al. Electronics and Communications in Japan. Part 3, vol. 72, N.degree. 6, 1989, pp. 1-8. Translated from Denshi Joho Isushin Gakkai Ronbunshi, vol. 71-A, N.degree. 3, Mar. 1988, pp. 608-615.
"Perceptual linear predictive (PLP) analysis of speech" H.Hermansky J. Acoust. Soc. Am 87(4), Apr. 1990, pp. 1738-1752.
"Non-linear spectral subtraction (NSS) and hidden markov models for robust speech recognition in car noise environments" P.Lockwood et al Proc. IEEE-ICASSP 1992 pp. I.265-I.268.
"Experiments with a Nonlinear Spectral Subtractor (NSS), Hidden Markov Models and the projection, for robust speech recognition in cars" P. Lockwood et al, Speech Communication vol. 11(2-3) 1992, pp. 215-228.
"Spectral Estimation of Speech by Mel-Generalized Cepstral Analysis" K. Tokuda et al. Electronics and Communications in Japan, vol. 76 N.degree. 2, 1993, pp. 30-43. Translated from Denshi Joho Tsushin Ronbunshi, vol. 75-A, N.degree. 7, Jul. 1992, pp. 1124-1134.
Alexandre Patrice
Lockwood Philip
Dorvil Richemond
MacDonald Allen R.
Matra Communication
LandOfFree
Method of speech recognition with learning 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 of speech recognition with learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of speech recognition with learning will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2114477