JPH02304497A - Word recognition system - Google Patents

Abstract

PURPOSE:To secure a high recognition rate and to easily perform real-time processing by inputting mean frequency characteristics of one word of a voice to a neural network. CONSTITUTION:The recognition system 1 is constituted by combining band-pass filters 10 of (n) channels, averaging circuits 15, the neural network 20, and a decision circuit 30. Then when a word is recognized from an input voice by using the neural network 20, the mean frequency characteristics of one word of the voice are inputted to the neural network 20. Therefore, preprocessing for obtaining the input is simpler than conventional complicate feature quantity extraction and the time required for the preprocessing is shortened. Consequently, the high recognition rate is secured and the real-time processing is easily enabled.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a word recognition method suitable for recognizing words from input speech using online terminals such as electric locks and IC cards.

[Prior Art] A conventional word recognition method, as described in, for example, Japanese Patent Publication No. 63-4200 and Japanese Patent Application Laid-open No. 62-220998, is based on the following procedure.

■Extract features related to words included in input speech.

(2) Calculate the distance between the standard pattern extracted in advance in the same manner as (2) above and the feature amount extracted in (2) above.

(2) Based on the calculation result, the word whose distance is the standard pattern exhibited is determined to be the word of the input speech.

[Problems to be Solved by the Invention] However, the conventional word recognition method described above has the following problems.

Real-time processing is difficult. In other words, in conventional word recognition methods, it is necessary to use complex features in order to ensure a recognition rate above a certain level, but extracting complex features requires a complex processing device, which increases the processing time. It will also be huge.

An object of the present invention is to obtain a word recognition method that ensures a high recognition rate and that can be easily processed in real time.

[Means for Solving the Problems] The present invention as set forth in claim 1 is a single word recognition method that recognizes a word from input speech using a neural network. This uses the average frequency characteristics of .

In the present invention described in Item 1a, the neural network is a hierarchical neural network.

[Function] According to the present invention as set forth in claim 1, there are the following functions and effects.

■As an input to the neural network,
Since the "average frequency characteristics of words" are used, the preprocessing for obtaining input is simpler than conventional complex feature quantity extraction, and the time required for this preprocessing is short.

(2) In principle, neural networks allow simple and quick calculation processing of the entire network.

■In principle, each unit that makes up a neural network operates independently, and parallel arithmetic processing is possible. Therefore, calculation processing is quick.

(2) With the above (2) to (2), word recognition processing can be easily performed in real time without using a complicated processing device.

Further, according to the present invention as set forth in claim 2, in addition to the effects (1) to (2) above, there is also the following effect (2).

Currently, in a zero-layer neural network,
A simple learning algorithm (pack propagation) as described below has been established, and a neural network that can achieve a high recognition rate can be easily formed.

[Example] Fig. 1 is a schematic diagram showing an example of a word recognition system to which the present invention is applied; Fig. 2 is a schematic diagram showing a neural network; Fig. 3 is a schematic diagram showing a hierarchical neural network; FIG. 4 is a schematic diagram showing the structure of the unit.

Prior to describing specific embodiments of the present invention, the configuration of the neural network and the learning algorithm will be described.

(1) Due to its structure, neural networks
It can be roughly divided into two types: a hierarchical network shown in FIG. 2(A) and an interconnected network shown in FIG. 2(B). Although the present invention may be configured using either of these networks, the hierarchical network is more useful because a simple learning algorithm as described below has been established.

(2) Network Structure A hierarchical network, as shown in FIG. 3, has a horizontal hierarchy consisting of an input layer, an intermediate layer, and an output layer.

Each layer is composed of one or more units. The connections are forward connections from the input layer to the middle layer to the output layer, and there are no connections within each layer.

(3) Structure of the unit The unit is a model of a neuron in the brain and has a simple structure as shown in FIG. It receives input from other units, sums it up, transforms it using a certain rule (conversion function), and outputs the result. Each connection with another unit is given a variable weight that represents the strength of the connection.

(4) Learning (pack propagation) Learning of a network is to bring the actual output closer to the target value (desired output). Learn by making changes.

Further, as a learning algorithm, for example, Rumel
hart, D.E., McClelland, J.
L, and thePDP Re5earch Gr.
oup, l'ARALLEL DISTRIBUTE
DPROCESSING, the MIT Pres.
s, 1986. Pack propagation as described in .

Hereinafter, specific examples of the present invention will be described. still,
The recognition system 1 of this embodiment is configured by combining an n-channel bandpass filter 10, an averaging circuit 15, a neural network 20, and a determination circuit 30 (first
(see figure).

(A) The five words to be learned are "shoumei", "air conditioner", "curtain", "television", and "door", and the input words are "shoumei", "air conditioner", "curtain", "
The five words were ``TV'' and ``Door.''

(B) Pre-processing ■ The input speech (each of the five words) is passed through a bandpass filter 10 with a plurality of (n) channels (n=8 in this embodiment) as shown in FIG.

At this time, the output of the bandpass filter 10 is
Averaged by 5.

(C) Processing and judgment by neural network ■Preprocessing results (output of bandpass filter 10)
As shown in FIG. 1, input is made to a three-layer hierarchical neural network 20. The input layer 21 has n units (n=8.8 in this embodiment) corresponding to n channels of preprocessing.
It is composed of units). The output layer 22 includes two words corresponding to registered words and other words for each of the five words.
unit, and the whole consists of 10 units.

- The output of the neural network 20 is input to the judgment circuit 3o, and the words of the input speech are recognized this time. However, in implementing the present invention, the output of the neural network 20 is not mechanically judged by the judgment circuit 30, but is judged by the human intellect that has obtained the output of the neural network 20. Also good.

■By backpropagation of the learning algorithm described above, the network is trained t, ooo times until the output error with respect to the input converges to a constant level, and a network that can guarantee a constant recognition rate is constructed. It should be noted that learning was performed so that the unit corresponding to each registered word would be "1" and the units corresponding to other words would be rOJ as outputs.

CD) Experiment Word recognition was experimented using the recognition system 1 described above.

The input speech was learned using pack propagation.
Single stories ("Shoumei", "Air Conditioner", "Curtain",
``television'', ``door'').

(a) Recognition rate As a result, the recognition rate was found to be 100%.

(b) Processing speed The processing speed (the time required to recognize the utterance of one word) was within 1 second, indicating extremely rapid processing.

That is, in the recognition system 1, the recognition rate is extremely high, as shown in the result (a) above.

Further, in the recognition system 1, as shown in the result (b) above, word recognition processing can be performed quickly without using a complicated processing device, and can be easily processed in real time.

[Effects of the Invention] As described above, according to the present invention, it is possible to obtain a word recognition method that secures a high recognition rate and can easily perform real-time processing.

[Brief explanation of drawings]

Fig. 1 is a schematic diagram showing an example of a word recognition system to which the present invention is applied, Fig. 2 is a schematic diagram showing a neural network, Fig. 3 is a schematic diagram showing a hierarchical neural network, and Fig. 4 is a schematic diagram showing a unit. It is a schematic diagram showing the full structure of. DESCRIPTION OF SYMBOLS 1... Recognition system, 10... Band pass filter, 15... Averaging circuit, 20... Neural network, 21... Input layer 22... Output layer, 30... Judgment circuit. Patent applicant Sekisui Chemical Co., Ltd. Representative Hiroshi 1) Kaoru Figure 1 Figure 2 Figure 3 ↑ Input pattern

Claims (2)

[Claims] (1) A word recognition method that uses a neural network to recognize a word from input speech, and uses the average frequency characteristics of one word of speech as input to the neural network. (2) The word recognition method according to claim 1, wherein the neural network is a hierarchical neural network.