JPH02309398A - Illumination control device by voice - Google Patents

Abstract

PURPOSE:To obtain the illumination control device by ordinary voice by using the average frequency characteristics of voice determined by words as the voice input to a neural network in the case of controlling illumination by the above-mentioned voice input. CONSTITUTION:The input voice is passed through a BPF 21 of the n-channel of a voice recognizing circuit 15 via a microphone 11 and an A/D converter 14 and is then average by an averaging circuit 22. This output is inputted to 3 layers of the hierarchical neural network 23. The respective corresponding units of the words to be learned, such as ''turn on'' and ''turn out'' are provided in the output layer 23C and the output thereof is inputted to a decision section 24, by which the words of the voice are recognized. The network to assure a specified recognition rate is built by inputting the words to be learned by changing speaker until the error of the output corresponding to the input converges to a specified level. The control of the lighting, putting out, etc., by ordinary voice is possible according to this method within one sec.

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Applications] The present invention relates to an audio lighting control device that controls the lighting state of a lighting fixture using human voice input.

[Prior art] Conventionally, as a lighting control device using audio, there is
The method described in Japanese Patent No. 71781 has been proposed.

In order to prevent malfunctions, the lighting control device described in Japanese Patent Application Laid-open No. 61-271781 uses (1) resonant fricative sounds in the mouth as a sound source instead of normal voices using the vocal cords;
■ Limiting the frequency input to the control circuit to 5kHz to 8kHz, ■ Lighting when the audio signal based on the above ■ and ■ continues for a predetermined period of time (1 second), and ■ After a certain period of lighting according to the above @ has elapsed. The gist is to turn off the lights.

[Problem M to be Solved by the Invention] However, the lighting control device described in Japanese Unexamined Patent Publication No. 61-271781 has the following problems (1) to (4).

■It requires sound in a special frequency range that is not used in spoken language, and requires a special method of vocalization.

(2) It reacts to all sounds in the above (2) range that last longer than a predetermined time (1 second) (for example, the sound of continuous hitting on something).

■Even if you want to turn off the light, it will not turn off unless a certain period of time has passed after it was turned on.

The present invention allows the user to make a special utterance without continuing for more than a predetermined time.
It is an object of the present invention to provide a lighting control device that can recognize lighting control commands from normal speech with a high recognition rate and can process turning on, turning off, or dimming in real time.

[Means for Solving the Problems] The present invention according to claim 1 recognizes a lighting control command from an input voice using a neural network, and controls the lighting state of a lighting fixture based on the lighting control command. This is a voice-based lighting control device that uses the average frequency characteristics of voices determined by words as input to a neural network.

3i'l The present invention described in claim 2 is such that the neural network is a hierarchical neural network.

[Action] According to the present invention as set forth in claim 1, there are the following effects (1) to (2).

■Since the lighting control command is recognized from the input voice using a neural network, the input lighting control command can be recognized from the normal voice without having to continue special utterance for more than a predetermined time.

(1) Various controls such as turning on or off the lights can be performed by defining words such as ``chindo'' for a lighting command or ``shotoj'' for a lights-off command as the input voice for the lighting control command. Therefore, dimming can also be controlled.

■It is relatively low due to the deterioration of recognition rate over time. This means that
It is presumed that this is because it is possible for the neural network to adopt a structure that is less susceptible to fluctuations due to differences in speech timing.

■As a human resource for the neural network, ``Since we use the average frequency characteristic J of speech determined by words, the preprocessing to obtain input is simple, and the time required for this preprocessing is short.

■Neural networks are, in principle, capable of simple and quick arithmetic 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) According to (1) to (2) above, the recognition process of lighting control commands can be easily processed 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 (hack propagation) as described below has been established, and it is possible to easily create a neural network that achieves a high recognition rate.

[Embodiment] Fig. 1 is a diagram showing a lighting control device according to an embodiment of the present invention, Fig. 2 is a block diagram showing an example of a voice recognition circuit, and Fig. 3 is a schematic diagram showing a neural network system. ,
FIG. 4 is a schematic diagram showing a hierarchical neural network, and FIG. 5 is a schematic diagram showing the structure of a 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 are
It can be roughly divided into two types: a hierarchical network shown in FIG. 3(A) and an interconnected network shown in FIG. 3(B). Although the present invention may be constructed 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 has a hierarchical structure consisting of an input layer, an intermediate layer, and an output layer, as shown in FIG.

Each layer is composed of one or more units. The connections are forward-looking, from the human power 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 (Hack propagation) Learning of a network is to bring the actual output closer to the target value C (desired output), and generally changes the conversion function and weight of each unit shown in Figure 5. Let them learn.

Further, as a learning algorithm, for example, Rumel
hart, D.E., McClelland, J.
L, and thaPDP Re5earch Gr.
oup, PARALLEL DISTRIBIJTE
DPROCESSING, the! IIIT Pr
Pack propagation can be used as described in J. ess, 1986;

Hereinafter, specific examples of the present invention will be described.

As shown in FIG. 1, the lighting control device 10 includes a microphone 11, a microphone amplifier 12, a low-pass filter 13, and an A/
D converter 14, voice recognition circuit 15, and lighting control section 16
and controls the lighting equipment 17.

Here, the voice recognition circuit 15 includes a microphone 11, a microphone amplifier 12, a low-pass filter 13, and an A/D converter 14.
Recognizes lighting control commands from input audio input via
Based on the lighting control command, the lighting state I5 of the lighting fixture 17 is controlled via the lighting control unit 16.

At this time, the speech recognition circuit 15 is constituted by a combination of an n-channel bandpass filter 21, an averaging circuit 22, a neural network 23, and a determining section 24 (see FIG. 2).

(A) Learn the words "chindo", "shoto", "mado open", "mado close", "flo", "kagi"
, and "Oyasuminasai", and the input words for the lighting control command were two single words, "chindo" and "sho 1 ~ tsu".

(B) Preprocessing ■ Input audio detected by the microphone 11 and A/D converted by the A/D converter 14 (each of the 7 words for learning and 2 words for the lighting control command), As shown in FIG. 2, it passes through a bandpass filter 21 having a plurality of (n) channels (n=8 in this embodiment).

At this time, the output of the band pass filter 21 is averaged by the averaging circuit 22 for each block.

(C) Processing and judgment by neural network ■Preprocessing results (output of band pass filter 21)
As shown in FIG. 2, the input signal is input to a three-layer hierarchical neural network 23. The human power layer 23A has n units (n=8 in this embodiment) corresponding to n channels of preprocessing.
It consists of 8 units). Out cuff 123 C is 7
A unit corresponding to each word is provided, and the whole is composed of 7 units.

- The output of the neural network 23 is input to the determination unit 24, and the words of the human voice are recognized this time.

■Using the hack propagation of the learning algorithm described above, three speakers each performed 1,000 times (each speaker took turns once, each 1,000 times) until the output error for input converged to a certain level. (assuming that each speaker utters all seven words in one input), and constructs a network that can guarantee a constant recognition rate. The output was learned to be "1" for units corresponding to each registered word, and "0" for units corresponding to other words.

(D) Experiment In the lighting control device 10 described above, f of the voice recognition circuit 15
=I The lighting control command is recognized and understood by the II fixed part 24, and the lighting equipment 17 is controlled by the lighting control part 16 to which the recognition result is transferred.
The lights were turned on/off.

The input speech was learned using pack propagation.
Two of the words are two words for lighting control commands, "chindo" and "shouto."

(a) Recognition rate As a result, the recognition rate was found to be 99% or higher.

The number of samples is 5,000 times [(200 times/person) × (
25 people).

(b) Recognition processing speed Also, the recognition processing speed (the time required to recognize one word uttered) was within 1 second, indicating extremely rapid processing.

That is, as shown in the result (a) above, the lighting control device 10 recognizes the lighting control command from normal speech with a high recognition rate without continuing special utterances for more than a predetermined period of time, and recognizes the lighting control command from the normal voice. The lighting/extinguishing of the fixture 17 can be controlled.

Further, in the lighting control device 10, as shown in the result (b) above, the recognition processing of lighting control commands can be quickly processed 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, a lighting control command can be recognized from normal speech with a high recognition rate, and the lighting control command can be turned on, turned off, or dimmed without continuing a special utterance for more than a predetermined time. You can get a lighting control device that can handle time.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing a lighting control device according to an embodiment of the present invention, FIG. 2 is a block diagram showing an example of a voice recognition circuit, and FIG. 3 is a schematic diagram showing a neural network.
FIG. 4 is a schematic diagram showing a hierarchical neural network, and FIG. 5 is a schematic diagram showing the structure of a unit. DESCRIPTION OF SYMBOLS 10... Lighting control device, 15... Voice recognition circuit, 16... Lighting control unit, 17... Lighting fixture, 21... Band pass filter, 22... Averaging circuit, 23... - Neural network, 24...determination section. Patent applicant: Sekisui Chemical Co., Ltd. Representative Hiroshi 1) Kaoru Figure 1 Figure 2 Figure 3 Figure 4 Output cover turn Figure 5

Claims (2)

[Claims] (1) A voice-based lighting control device that recognizes a lighting control command from an input voice using a neural network and controls the lighting state of a lighting fixture based on the lighting control command, and as an input to the neural network, A voice-based lighting control device that uses the average frequency characteristics of voices determined by words. (2) The audio lighting control device according to claim 1, wherein the neural network is a hierarchical neural network.