Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1997-06-05
1999-08-24
Tsang, Fan S.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704222, 704252, 704254, G06E 100, G10L 302, G10L 502
Patent
active
059436476
ABSTRACT:
A speech recognition method that combines HMMs and vector quantization to model the speech signal and adds spectral derivative information in the speech parameters. Each state of a HMM is modeled by two different VQ-codebooks. One is trained by using the spectral parameters and the second is trained by using the spectral derivative parameters.
REFERENCES:
patent: 4815134 (1989-03-01), Picone et al.
patent: 5274739 (1993-12-01), Woodard
patent: 5371853 (1994-12-01), Kao et al.
patent: 5414796 (1995-05-01), Jacobs et al.
patent: 5455888 (1995-10-01), Iyengat et al.
patent: 5533138 (1996-07-01), Kim et al.
patent: 5590242 (1996-12-01), Juang et al.
S. Nakagawa et al., "A New Speech Recognition Method Based on VQ-Distortion Measure and HMM", Proceedings of Int'l. Conference on Acoustics, Speech and Signal Processing, pp. II-676 to II-679, Minneapolis, MN, Apr., 1993.
Y. Linde et al., "An Algorithm for Vector Quantizer Design", IEEE Transactions on Communications, vol. COM-28, No. 1, Jan. 1980.
L.R. Rabiner et al. "Higher Performance Connected Digit Recognition Using Hidden Markov Models", IEEE Transactions on Acoustics Speech and Signal Processing, vol. 37, pp. 1214-1225, Aug. 1989.
High Accuracy Speaker Verification System Specification Sheet, Apr. 1992, Ensigma Ltd., Turing House, Station Road, Chepstow, Gwent, NP6 5PB, United Kingdom.
D.K. Burton, "Text-Dependent Speaker Verification Using Vector Quantization Source Coding", IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-35, No. 2, pp. 133-143, Feb. 1987.
H. Hermansky, "Perceptual Linear Predictive (PLP) Analysis of Speech", Journal of Acoustical Society of America, vol. 87, No. 4, Apr. 1990, pp. 1738-1752.
Dunn Michael L.
Hoosain Allan
Tecnomen Oy
Tsang Fan S.
LandOfFree
Speech recognition based on HMMs 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 based on HMMs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition based on HMMs will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-476733