Patent
1991-06-07
1993-07-20
Fleming, Michael R.
G10L 902
Patent
active
052300374
ABSTRACT:
A method and a system for synthesizing speech from unrestricted text, based on the principle of associating a written string of text with a sequence of speech features vectors that most probably model the corresponding speech utterance. The synthesizer is based on the interaction between two different Ergodic Hidden Markov Models: an acoustic model reflecting the constraints on the acoustic arrangement of speech, and a phonetic model interfacing phonemic transcription to the speech features representation.
REFERENCES:
patent: 4852180 (1989-07-01), Levinson
patent: 4882759 (1989-11-01), Bahl et al.
patent: 5033087 (1991-07-01), Bahl et al.
Falaschi, A. et al., "A Functional Based Phonetic Units Definition for Statistical Speech Recognizers", Eurospeech Proceedings, Paris, France, Sep. 1989, vol. 1, pp. 13-16.
Juang, B. H., "On the Hidden Markov Model and Dynamic Time Warping for Speech Recognition-A Unified View", AT&T Bell Lab. Tech. Journal, vol. 63, No. 7, Sep. 1984, pp. 1213-1243.
Cernuschi-Frias, B. et al., "On the Exact Maximum Likelihood Estimation of Gaussian Autoregressive Processes", IEEE Trans. on Acoustics, Speech, and Signal Proc., vol. 36, No. 6, Jun. 1988, pp. 922-924.
Falaschi, A. et al., "A Finite States Markov Quantizer for Speech Coding", ICASSP Conference Proc., N.M., Jun. 1990, pp. 205-208.
Falaschi, A. et al., "A Hidden Markov Model Approach to Speech Synthesis", Eurospeech Proc. off Paris, France, 1989, pp. 187-190.
Giustiniani Massimo
Pierucci Piero
Doerrler Michelle
Fleming Michael R.
International Business Machines - Corporation
Schechter Marc D.
LandOfFree
Phonetic Hidden Markov model speech synthesizer does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Phonetic Hidden Markov model speech synthesizer, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Phonetic Hidden Markov model speech synthesizer will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1766936