Speech recognition by neural network adapted to reference patter

Details Speech recognition by neural network adapted to reference patter Speech recognition by neural network adapted to reference patter

1994-07-05

1997-02-04

MacDonald, Allen R.

395 24, 395 241, G01L 106, G06F 1500

Patent

active

056007531

ABSTRACT:
A speech recognition method according to the present invention uses distances calculated through a variance weighting process using covariance matrixes as the local distances (prediction residuals) between the feature vectors of input syllables/sound elements and predicted vectors formed by different statuses of reference neural prediction models (NPM's) using finite status transition networks. The category to minimize the accumulated value of these local distances along the status transitions of all the prediction models is figured out by dynamic programming, and used as the recognition output. Learning of the reference prediction models used in this recognition method is accomplished by repeating said distance calculating process and the process to correct the parameters of the different statuses and the covariance matrixes of said prediction models in the direction of reducing the distance between the learning patterns whose category is known and the prediction models of the same category as this known category, and what have satisfied prescribed conditions of convergence through these calculating and correcting processes are determined as reference pattern models.

REFERENCES:
patent: 4587670 (1986-05-01), Levinson et al.
patent: 4805225 (1989-02-01), Clark
patent: 4852180 (1989-07-01), Levinson
patent: 4876731 (1989-10-01), Loris et al.
patent: 4975961 (1990-12-01), Sakoe
Lippmann, "Review of Neural Networks for Speech Recognition, " Neural Computation, 1989, pp. 1-38.
Sakoe et al. "Speaker-Independent Word Recognition Using Dynamic Programming Neural Networks", IEEE, ICASSP '89, 1989, S7, 8 pp. 29-32.
Tsuboka et al, "Neural Predictive Hidden Markov Model", Matsushita Electric Industrial Co. & Osaka University Paper, Dec. 1990, pp. 1341-1344.
S. Levinson, "Structural Methods in Automatic Speech Recognition", Proceedings of the IEEE, vol. 73, No. 11, Nov. 1985, pp. 1625-1650.
K. Funahashi, "On the Approximate Realization of Continuous Mappings by Neural Networks", Neural Networks, vol. 2, 1989, pp. 183-192.
R. Lippmann, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
K. Iso et al, "Speaker-Independent Word Recognition Using a Neural Prediction Model", Proceedings of the ICASSP 90 -1990 Int'l Conf. on Acoustics, Speech, and Signal Processing, Apr. 1990, pp. 441-444.
K. Shikano et al., "Speaker Adaptation Through Vector Quantization", 1986, pp. 2643-2646, ICASSP 86, IEEE.
H. Sakoe et al., "Dynamic Programming Algorithm Optimization for Spoken Word Recognition", IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-26, No. 1, Feb. 1978, pp. 43-49.
ICASSP '91 (1991 International Conference on Acoustics, Speech, And Signal Processing, Toronto, Ontario, 14th-17th May 1991), vol. 1, pp. 57-60, IEEE, New York; K. Iso et al.: "Large vocabulary speech recognition using neural prediction model".

Affiliated with

Also associated with

Rating

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-687251