Neural network, a method of learning of a neural network and pho

Details Neural network, a method of learning of a neural network and pho Neural network, a method of learning of a neural network and pho

1995-12-21

2000-02-15

Dorvil, Richemond

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

395 23, 704249, G10L 504, G06E 100

Patent

active

06026358&

ABSTRACT:
A neuron device network is provided with a speech input layer, a context layer, a hidden layer, a speech output layer and a hypothesis layer. A phoneme to be learned is spectral-analyzed by an FFT unit and a vector row at a time point t is input to a speech input layer. Also, a vector state of the hidden layer at a time t-1 is input to the context layer, the vector row at a time t+1 is input to the speech output layer as an instructor signal, and a code row for hypothesizing the phoneme, or the code row, is input to the hypothesis layer. The time series relation of the vector rows and the phoneme are hypothetically learned. Alternatively, a spectrum, a cepstrum or a speech vector row based on outputs from the hidden layer of an auto-associative neural network is input to the speech input layer, and the code row is output from the hypothesis layer, taking into account the time series relation. The speech is recognized when a CPU reads the stored output values of the hidden layer and the connection weights of the hidden layer and the hypothesis layer from a memory of the neuron device network and calculates output values of the respective neuron devices of the hypothesis layer based on the output values and the connection weights. The corresponding phoneme is determined by collating the output values of the respective neuron devices of the hypothesis layer with the code rows in an instructor signal table.

REFERENCES:
patent: 5175793 (1992-12-01), Sakamoto et al.
patent: 5214743 (1993-05-01), Asai et al.
patent: 5259039 (1993-11-01), Akamatsu
patent: 5381513 (1995-01-01), Tsuboka
patent: 5481644 (1996-01-01), Inazumi
Elman, Jeffery L., "Finding Structure in Time", Cognitive Science, 14, pp. 179-211, Apr.-Jun. 1990.
Fahlman Scott E., "Faster-Learning Variations on Back-Propagation: An Empirical Study," published by Carnegie-Mellon University Computer Science Department, Nov. 1988.
Elman, Jeffery L. Structured Representations and Connectionist Models, published by University of California, San Diego Department of Cognitive Science (1989).

Affiliated with

Also associated with

Rating

Neural network, a method of learning of a neural network and pho 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, a method of learning of a neural network and pho, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network, a method of learning of a neural network and pho will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1914246