Method and apparatus for improved speech recognition from stress

Details Method and apparatus for improved speech recognition from stress Method and apparatus for improved speech recognition from stress

1994-07-06

1998-05-26

MacDonald, Allen R.

395 242, 395 25, G10L 506

Patent

active

057580227

ABSTRACT:
Speech recognition of Lombard-induced speech at a high rate of recognition is shown using a neural network (NN) utilizing nonlinear imaging characteristics. In a training phase, systematic parameter changes of Lombard-induced speech are trained to a neural network. In a speech recognition phase, imaging of Lombard-induced speech patterns to Lombard-free speech patterns takes place through the trained parameter changes.

REFERENCES:
patent: 5001761 (1991-03-01), Hattori
patent: 5228087 (1993-07-01), Bickerton
patent: 5263107 (1993-11-01), Ueda et al.
patent: 5278911 (1994-01-01), Bickerton
patent: 5361324 (1994-11-01), Takizawa et al.
patent: 5404422 (1995-04-01), Sakamoto et al.
"Recent Achievements in Speech Processing Technologies and Their Applications", M. Immendoerfer et al, Electrical Communications, vol. 62, No. 3/4, 1988, pp. 288-293.
"Improved Automatic Recognition of Speech in Noise and Lombard Effect", J. Hansen et al, EUSIPCO 1992, Brussels, pp. 403-406.
"The Variability of Speech Produced in Noise", J. Junqua, ESCA Workshop on Speech Processing in Adverse Conditions, Cannes, France, 1992, pp. 43-51.
"Noise-Robust Speech Recognition by Template Adaptation", S. Dvorak et al, DAGA 1991, Bochum, pp. 1-3.
"Robust Speaker-Independent Word Recognition Using Static, Dynamic and Acceleration Features: Experiments with Lombard and Noisy Speech", B. Hanson et al, IEEE ICASSP 1990, pp. 857-860.
"Noise-Robust Speech Recognition Using a Cepstral Noise Reduction Neural Network Architecture", H. Sorensen, International Joint Conference on Neural Networks, Jul. 8-12, 1991, Seattle, pp. II-795-II800.
"Robust Speech Parameters Extraction for Word Recognition in Noise Using Neural Networks", L. Barbier et al, International Conference on Acoustics, Speech, and Signal Processing, May 14-17, 1991, Toronto, pp. 145-148.
ICASSP-93. Anglade et al., "Speech discrimination in adverse conditions using acoustics knowledge and selectively trained neural network", pp. 279-82 vol. 2, Apr. 1993
ICASSP 91. Sorensen, "A cepstral noise reduction multi-layer neural network", pp. 933-6 vol. 2, May. 1991.
ICASSP 90. Hnason et al., "Robust speaker-independent word recognition using static, dynamic and acceleration features: experiments with Lombard and Noisy speech". pp. 857-860 vol. 2, Apr. 1990.

Affiliated with

Also associated with

Rating

Method and apparatus for improved speech recognition from stress 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 and apparatus for improved speech recognition from stress, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for improved speech recognition from stress will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1974221