Neural network speech recognition apparatus recognizing the freq

Details Neural network speech recognition apparatus recognizing the freq Neural network speech recognition apparatus recognizing the freq

1993-08-06

1996-01-02

MacDonald, Allen R.

395 11, G10L 900

Patent

active

054816440

ABSTRACT:
The speech recognition apparatus recognizes a frequency of successively input identical speech data sequences. The speech recognition apparatus includes a speech recognition non-layered neural network unit. Speech data sequence is inputted as feature vectors from a feature extracting unit. The neural network performs speech recognition and determines whether the input speech data sequence matches at least one predetermined speech data sequence. The neural network generates a speech recognition signal when the input speech data sequence matches the at least one predetermined speech data sequence. A recognition signal detecting unit outputs a reset instruction signal each time the neural network generates the speech recognition signal. An internal state value setting unit resets the neural network unit to an initial state each time the recognition signal detecting unit outputs the reset instruction signal. Since the neural network unit is reset each time the speech recognition signal is outputted, accurate detection can be achieved even when speech data sequence to be recognized is inputted successively.

REFERENCES:
patent: 4947482 (1990-08-01), Brown
patent: 5014219 (1991-05-01), White
patent: 5040215 (1991-08-01), Amano et al.
patent: 5046019 (1991-09-01), Basehore
patent: 5182794 (1993-01-01), Gasperi et al.
patent: 5247584 (1993-09-01), Krogman
patent: 5285522 (1994-02-01), Mueller
patent: 5285523 (1994-02-01), Takahashi
C. Iooss, "From Lattices of Pnonemes to Sentences: A Recurrent Neural Network Approach", Int'l Joint Conf. on Neural Networks, Jul. 8-14, 1991, vol. 2, pp. 833-838.
A. N. Michel, "Associative Memories via Artificial Neural Networks", IEEE Control Systems Magazine, Apr. 1990, pp. 6-17.
M. Sompolinsky, "Chaos in Random Neural Networks", Physical Review Letter, Jul. 18, 1988, pp. 259-262.
Palakal et al., "Speaker-Invariant Phoneme Recognition Using Multiple Neural Network Models", 1991 IEEE Int'l. Conf. on Neural Networks, Jul. 8-11, 1991, pp. 839-844.
Naylor et al., "The Application of Neural Networks to Wordspotting", 1992 26th Asilomar Conf. on Signals, Systems & Computers, Oct. 26-28, 1992, pp. 1081-1085.
K. P. Li, et al., "A Whole Word Recurrent Neural Network for Keyword Spotting", ICASSP, Mar. 1992, pp. II-81-II-84.
N. Z. Hakim et al., "Cursive Script Online Character Recognition with a Recurrent Neural Network Model", IJCNN, Jun. 1992, pp. III-711-III-716.
John Hertz et al., "Introduction to the Theory of Neural Computation", Santa Fe Institute Studies in the Sciences of Complexity, Lecture Notes, vol. 1, Addison-Wesley, 1991, pp. 173-187.

Affiliated with

Also associated with

Rating

Neural network speech recognition apparatus recognizing the freq does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network speech recognition apparatus recognizing the freq, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network speech recognition apparatus recognizing the freq will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-242388