Electrical audio signal processing systems and devices – One-way audio signal program distribution – Public address system
Patent
1992-07-07
1993-07-13
Kemeny, Emanuel S.
Electrical audio signal processing systems and devices
One-way audio signal program distribution
Public address system
G10L 500
Patent
active
052280870
ABSTRACT:
Speech recognition is carried out by performing a first analysis of a speech signal using a Hidden Semi Markov Model and an asymmetric time warping algorithm. A second analysis is also performed using Multi-Layer Perceptron techniques in conjunction with a neural net. The first analysis is used by the second to identify word boundaries. Where the first analysis provides an indication of the word spoken above a certain level of confidence, an output representative of the word spoken may be generated solely in response to the first analysis, the second analysis being utilized when the level of confidence falls. The output controls a function of an aircraft and provides feedback to the speaker of the words spoken.
REFERENCES:
patent: 4286115 (1981-08-01), Sakoe
patent: 4624008 (1986-11-01), Vensko
patent: 5040215 (1991-08-01), Amano et al.
"Isolated Word Recognition Method", IBM TDB vol. 29, No. 4, Sep. 1986.
"A Noise Compensating Spectrum Distance Measure Applied to Automatic Speech Recognition", by Bridle et al., Proc. of The Institute of Acoustics, vol. 6, No. 4, Nov. 1984, pp. 307-314.
"Application of Hidden Markov Models to Automatic Speech Endpoint Detection", by Wilpon et al., Computer Speech and Language, vol. 2, 1987, pp. 321-341.
"Experiments in Isolated Digit Recognition Using the Multi-Layer Perceptron", by Peeling et al., RSRE Memorandum No. 4073, Dec. 17, 1987, pp. 1-18.
"The JSRU Channel Vocoder", by Holmes, IEE Proc., vol. 127, Pt. F, No. 1, pp. 53-60, Feb. 1980.
"A Noise Compensating Spectrum Distance Measure Applied to Automatic Speech Recognition", by Bridle et al., Proc. Inst. Acoust. Autumn Meeting, Windeamere, Nov. 1984.
"Explicit Modelling of State Occupancy in Hidden Markov Models for Automatic Speech Recognition,"by Russell et al., Proc. IEEE Int. Conf. on Acoustics, Tampa, Mar. 26-29, 1985.
"Isolated Digital Recognition Using the Multi-Layer Perceptron" by Peeling et al., Proc. NATO ASI Speech Understanding, Bad Windsheim, Jul. 3-18, 1987.
"Learning Internal Represenations by Error Propagation", by Rumelhart et al., Inst. For Cogn. Science, UCSD, ICS Report 8506, Sep. 1985.
"Stochastic Models and Template Matching:[Etc]", by Bridle, Proc. Inst. Acoust., Autumn Meeting, Nov. 1984.
"Continuous Connected Word Recognition Using Whole Word Templates" by J. S. Bridle, et al., The Radio and Electronic Engineer, vol. 53, No. 4, pp. 167-175, Apr. 1983.
Kemeny Emanuel S.
Smiths Industries Public Limited Company
LandOfFree
Speech recognition apparatus and methods 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 apparatus and methods, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition apparatus and methods will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2318780