Patent
1994-02-14
1997-07-15
MacDonald, Allen R.
395 228, 395 231, G10L 500
Patent
active
056490569
ABSTRACT:
A sound analyzer sound analyzes an input speech signal to obtain feature vectors. A matrix quantizer performs a matrix quantization process between the feature vectors obtained by the sound analyzer and a phonetic segment dictionary prepared in phonetic segment units to obtain a phonetic segment similarity sequence. A PS-phoneme integrating section integrates the phonetic segment similarity sequence into a phonemic feature vector. A HMM recognizer checks the phonemic feature vector using a HMM prepared in certain units, to thereby perform a recognition process.
REFERENCES:
patent: 4446531 (1984-05-01), Tanaka
patent: 4736429 (1988-04-01), Niyada et al.
patent: 4888823 (1989-12-01), Nitta et al.
patent: 5027406 (1991-06-01), Roberts et al.
patent: 5046099 (1991-09-01), Nishimura
patent: 5131043 (1992-07-01), Fujii et al.
patent: 5289562 (1994-02-01), Mizuta et al.
Rigoll, "Information Theory Principles for the Design of Self-Organizing Maps in Combination with Hidden Markov Modeling for Continuous Speech Recognition," International Joint Conference on Neural Networks, San Diego, CA, pp. 569-574 (Jun. 17-21, 1990).
Tseng et al., "Fuzzy Vector Quantization Applied to Hidden Markov Modeling," International Conference on Acoustics, Speech, and Signal Processing, Dallas, TX, pp. 641-644, vol. 2, (Apr. 6-9, 1987).
L.R. Rabiner, "A Turtorial on Hidden Markov Models and Selected Applications in Speech Recognition", published in Readings in Speech Recognition Edited by A. Waibel and Kai-Fu Lee, pp. 267-296 (1990).
Collins Alphonso A.
Kabushiki Kaisha Toshiba
MacDonald Allen R.
LandOfFree
Speech recognition system and method which permits a speaker's u 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 system and method which permits a speaker's u, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition system and method which permits a speaker's u will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1497822