Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1996-07-15
1999-08-17
MacDonald, Allen R.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704240, G10L 506
Patent
active
059407948
ABSTRACT:
A boundary estimation method capable of readily learning the probability of existence of a boundary in speech and a speech recognition apparatus with high precision and less model calculation. In a learning mode, an estimator estimates distributions of boundary samples and non-boundary samples. In an estimation mode, a likelihood calculator calculates a likelihood of a boundary from a boundary probability density and a non-boundary probability density. In the speech recognition apparatus, a feature extractor analyzes the input speech to convert it into feature parameters of time series, a boundary detector detects phonetic boundary equivalent areas in the input speech from the output of the feature extractor, a model calculator prepares a plurality of phonetic model series corresponding to the feature parameters and restricts a time when the boundaries of the phonetic model series are formed to the phonetic boundary equivalent areas detected by the boundary detector, and a phonetic series transform selects suitable phonetic model series corresponding to the input speech from the result of the model calculator.
REFERENCES:
patent: 4803729 (1989-02-01), Baker
patent: 4805100 (1989-02-01), Ozeki
patent: 4881266 (1989-11-01), Nitta et al.
patent: 4977599 (1990-12-01), Bahl et al.
patent: 5305442 (1994-04-01), Junqua
"A Neural Network for Phonetic Segmentation of Continuous Speech", Acoustical Society of Japan Proceedings, 2-P-6, Oct. 1988.
"Phoneme Segmentation Expert System Using Spectrogram Reading Knowledge", Electronic Information Communications Association of Japan Transactions D-II vol. J73-D-II, No. 1, pp. 1-10, Jan. 1990.
"Segmentation of Continuous Speech by HMM and Bayesian Probability", Electronic Information Communications Association of Japan Transactions D-II vol. J72-D-II, No. 1, pp. 1-10, Jan. 1989.
"Phonemic Units Segmentation in Various Phonetic Environments", Electronic Information Communications Association of Japan Transactions D-II vol. J72-D-II, No. 8, pp. 1221-1227, Aug. 1989.
"A Phoneme Segmentation Parameter Based on the Onset-Sensitive Auditory Neuron Model", Electronic Information Communications Association of Japan Transactions A vol. J71-A, No. 3, pp. 592-600 Mar. 1988.
"A Segmentation Algorithm for Connected Word Recognition Based on Estimation Principles", IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-31, No. 4, Aug. 1983.
"Development of an Acoustic-Phonetic Hidden Markov Model for Contiuous Speech Recognition", Ljolje et al., IEEE Transactions on Signal Processing, vol. 39, No. 1, pp. 29-39, Jan. 1991.
"Speech Recognition Using Time-Dependent Linear Phonetic-Context Model", Acoustical Society of Japan Proceedings, 2-P-27, Mar. 1990.
"Phonetic Segmentation by Mixture Continuous Parameter Models", Acoustical Society of Japan Proceedings, 2-Q-16, Oct. 1992.
On Robustness of the Mixture Density Segmentation Method to a New Speaker, Acoustical Society of Japan Proceedings, 2-4-7, Mar. 1993.
Thomas Parsons, Voice and Speech Processing, McGraw Hill 1986.
Plannerer et al., Recognition Of Demisyllable Based Units Using Semicontinuous Hidden Markov Models, IEEE 1992.
MacDonald Allen R.
Mattson Robert C.
Mitsubishi Denki & Kabushiki Kaisha
LandOfFree
Boundary estimation method of speech recognition and speech reco does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Boundary estimation method of speech recognition and speech reco, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Boundary estimation method of speech recognition and speech reco will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-325559