Speech recognition apparatus using neural network, and learning

Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

704238, 704239, G10L 500

Patent

active

057873933

ABSTRACT:
A speech recognition apparatus using a neural network. A neuron-like element according to the present invention has a means for storing a value of the inner condition thereof, a means for updating a value of internal status on the basis of an output from the neuron-like element itself, outputs from other neuron-like elements and an external input, and an output value generating means for converting a value of internal status into an external output. Accordingly, the neuron-like element itself can retain the history of input data. This enables the time series data, such as speech to be processed without providing any special means in the neural network.

REFERENCES:
patent: 5040215 (1991-08-01), Amano et al.
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5119469 (1992-06-01), Alkon et al.
patent: 5150323 (1992-09-01), Casteloz
patent: 5175794 (1992-12-01), Tattersall
patent: 5185848 (1993-02-01), Aritsuka et al.
patent: 5297237 (1994-03-01), Masuoka et al.
Tatsumi Watanabe et al., "Study of Learning methods and Shape of the Learning Surface for Recurrent Neural Networks", Theses by IEICE, vol. J74D-II, No. 12, Dec. 25, 1991, pp. 1776-1787.
Mitsuhiro Inazumi et al., "Continuous Spoken Digit Recognition by Recurrent Neural Networks", Technical Report of IEICE, SP92-125, Jan. 19, 1993, pp. 17-24.
Mitsuhiro Inazumi et al., "Connected Work Recognition by Recurrent Neural Networks", Technical Report of IEICE, SP92-25, Jun. 30, 1992, pp. 9-16.
Ken-ichi Funahashi, "On the Recurrent Neural Networks", Technical Research Report by IEICE, SP92-80, Oct. 21, 1992, pp. 51-58.
Yohji Fukuda, et al., "Phoneme Recognition using Recurrent Neural Networks", Technical Research Report by IEICE, NC91-10, May 8, 1991, pp. 71-78.
K.P. Li, et al., "A Whole Word Recurrent Neural Network of 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, "Introduction to the Theory of Neural Computation," Santa Fe Institute Studies in the Sciences of Complexity, Lecture Notes vol. I, Addison-Wesley, 1991.
IOOSS, "From Lattices of Phoneme to Sentences: A Recurrent Neural Network Approach", International Joint Conference on Neural Nets, Jul. 8-14, 1991, pp. 883-838, vol. 2.
Thomas M. English et al., "Back-Propagation Training of a Neural Network for Word Spotting", ICASSP, vol. 2, 23-26 Mar. 1992 San Francisco, CA, US, pp. 357-360.
Patent Abstracts of Japan, vol. 16 No. 75 (p. 1316), 24 Feb. 1992 and JP-A-03 265077 (Shigeki) 26 Nov. 1991 (Abstract).
Zuqiang Zhao, "Connectionist Training of Non-Linear Hidden Markov Models for Speech Recognition", IJCNN, 1991, vol. 2, 18-21 Nov. 1991 Singapore, SG, pp. 1647-1652.
Fabio Greco et al., "A Recurrent Time-Delay Neural Network for Improved Phoneme Recognition", ICASSP, 1991, vol. 1, 14-17 May 1991 Toronto, Canada, pp. 81-84.
H.-U. Bauer et al., "Nonlinear dynamics of feedback multilayer perceptrons", Physical Review A, vol. 42, No. 4, 15 Aug. 1990, US, pp. 2401-2408.
Robinson ("a real-time recurrent error prpagation network word recognition system", ICASSP-92, vol. 1, Mar. 23-26, 1992, pp. 617-620).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Speech recognition apparatus using neural network, and learning 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 using neural network, and learning , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition apparatus using neural network, and learning will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-34476

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.