JPS6239747B2 - - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION The present invention relates to an audio output control device that controls the audio output level of an audio device that itself outputs audio, such as a television, various audio products, or a car radio, to another audio device, such as a direct audio device. This is a voice output control device that is controlled by human voice, and in particular has a function to prevent voice input for control from being mistakenly recognized as output voice generated by an audio device. .

Voice recognition technology has made remarkable progress in recent years, and is now used in control signal input units that are connected to various electrical devices to control the operations of the devices. but,
If you use this type of technology to recognize human speech and use the judgment output formed based on the recognized content to control various operations on equipment such as televisions and car radios, the recognition target In addition to human voice input, there is output voice from TVs, car radios, etc., and this output voice mixes with the input voice, making the probability of correctly recognizing the target voice extremely high. The disadvantage was that it decreased.

In response to these drawbacks, it is technically difficult to create a device that distinguishes between the voice to be recognized and the voice of a TV, car radio, etc., selects only the voice to be recognized, and correctly recognizes it. Even if it is possible to do so, there is a problem in that it requires a complicated speech recognition circuit and is very expensive.

Therefore, the main purpose of the present invention is to control the volume of the audio equipment using a simple circuit when the input audio to be recognized is given to the audio equipment for various operations, etc., so as to prevent erroneous recognition of the input audio. An object of the present invention is to provide an audio output control device that can prevent such problems.

The above objects and other objects and features of the invention will become more apparent from the following detailed description with reference to the drawings.

To summarize this invention, the level of the input voice to be recognized given to the microphone is detected,
It is determined whether the level of this input voice has reached a predetermined level, and the input voice given to the microphone at a predetermined level or higher is determined to be an audio signal to be recognized, and the content of the input voice is determined. Therefore, the volume of the audio device on which the operation is performed is set to zero or low, and the level of the audio output of the audio device is controlled so that the input audio is given preferentially to the microphone.

FIG. 1 is a block diagram of one embodiment of the present invention. In the figure, reference numeral 1 denotes an audio device such as a television, a car radio, etc., which outputs its own audio, and the audio output processed through a conventionally known audio output means is outputted from a speaker 3 via an amplifier 2. This audio equipment 1 is provided with a muting circuit 4, for example, at a stage upstream of an amplifier 2, and controls the volume to be output by a signal given from an audio output control device, which will be described below.

The audio output control device is provided with a microphone 5 for converting audio input into an electrical signal,
The audio input converted into an electrical signal is applied to the microphone amplifier 6 for conversion to an appropriate level. The audio input output from the microphone amplifier 6 is given to the audio recognition circuit 7 which recognizes the content of the audio input and forms an output signal A corresponding to the recognized determination content, and also detects the level of the audio input. and is applied to a circuit that forms a signal for controlling the mutating circuit 4.

That is, the audio input derived from the microphone amplifier 6 is applied to a detector 8 that performs envelope detection of the audio, and the envelope-detected output is applied to one input terminal of a comparator 9. The other input terminal of the comparator 9 is supplied with a signal formed from the audio output of the audio device 1 and serving as a reference for comparison. This reference signal is, for example, the amplifier 2 of the audio equipment 1.
A buffer amplifier 10 that branches the audio output given to the speaker 3 and leads it to a buffer amplifier 10 whose gain can be changed, and where appropriate gain control is performed.
The output is applied to a detector 11 that performs envelope detection in the same way as in the processing of the audio input, formed as an output of this detector 11, and applied to the other input terminal of the comparator 9. The comparator 9 performs a comparison between both input signals, and provides the comparison result to the muting voltage generation circuit 12. The output of this muting voltage generation circuit 12 is given to the muting circuit 4 provided in the audio equipment 1.
This signal is used to control the muting operation of the

Here, the output voltage output from the comparator 9 is the output level of the detector 8 without sound or noise applied to the microphone 5, and the output level of the audio equipment 1 side applied from the detector 11. If the signal level is smaller than the signal level formed by the gain control of the muting voltage generating circuit 12.
Derive a voltage that does not generate a muting voltage. On the other hand, when the level of the sound applied to the microphone 5 becomes higher than the reference level formed from the sound from the audio equipment 1 side as a result of the comparison result of the comparator 9, the output voltage of the comparator 9 Then, the muting voltage generation circuit 12 generates a muting voltage for a preset time, and operates the muting circuit 4 of the audio device 1 to change the sound from the speaker 3 to zero or a small level. Therefore, in a state where the surrounding noise is small and there is no sound to be input, even if sound is output from the speaker 3, no muting voltage is generated from the muting voltage generation circuit 12, and the volume output from the speaker 3 does not change at all. However, when a sound with a level sufficient to invert the output of the comparator 9 is applied to the microphone 5, a muting voltage is generated from the muting voltage generation circuit 12, and sound is output from the speaker 3 for a preset time. During this time, the microphone 5 is provided with the audio to be input without being mixed with the audio from the speaker 3. Since the input audio has no unnecessary sounds, it is sent to the microphone amplifier 6 as a signal with an extremely good S/N ratio.
Then, the speech recognition circuit 7 determines the content of the input speech. A control signal A for various operations on the audio device 1 is generated according to the determined content, and is applied to the audio device 1, so that the device 1 performs a desired operation. The input signal given to the speech recognition circuit 7 has an S/N ratio without unnecessary sounds as described above.
Since the speech input is given in a good condition, the speech input can be taken in correctly, and the probability of speech recognition is extremely high. In the above embodiment, the signal formed from the output of the audio device 1 was used as the reference input of the comparator 9, but a preset signal that is always kept at a constant level is input to one input terminal of the comparator 9. It can also be configured by giving

FIG. 2 is a block diagram showing another embodiment of the present invention. In this embodiment, before giving voice input, the sound output from the audio device is reduced in advance, and then the voice input is accepted. This prevents erroneous voice recognition. In the figure, parts that are the same as those in FIG. 1 are indicated by reference numerals. In this embodiment, the input to the muting voltage generating circuit 12 is not given from the comparator, but is given as the muting command signal B immediately before the audio is input from electrical means or manual means, and is first input by the muting voltage. and operates the muting circuit 4 to reduce or reduce the volume output from the speaker 3 of the audio device 1,
Thereafter, the voice to be recognized is input to the microphone 5.

As described above, according to the present invention, by providing a simple means of automatically or manually reducing the output sound of the audio device for a certain period of time while the speech to be recognized is being uttered, the sound can be reduced. It is possible to increase the recognition probability of a voice recognition circuit used in combination with the device, prevent erroneous recognition, and increase the reliability of operation control of the voice device based on voice input.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing one embodiment of the present invention. FIG. 2 is a block diagram showing another embodiment of the invention. In the figure, 1 is an audio device, 3 is a speaker, and 4 is an audio device.
1 is a mutating circuit, 5 is a microphone, 7 is a voice recognition circuit, 8 and 11 are detectors, 9 is a comparator, and 12 is a muting voltage generation circuit.

Claims (1)

[Scope of Claims] 1. A voice that controls the level of audio output from an audio device that has a function of receiving an input audio signal having operation control information, converting it into an electrical signal, and performing operation control corresponding to the operation control information. An output control device, comprising: a command signal generation means for generating a command signal for reducing the level of the audio output of the audio device in response to the input of the audio signal; and a command signal from the command signal generation means. an audio output control device, comprising: an output level lowering means for responsively lowering the audio output level of the audio device. 2. The command signal generation means includes: a comparison means that receives the input audio signal converted into the electrical signal and the audio output signal from the audio device and compares the signal levels of the two; and the input audio from the comparison means. active signal generating means for generating a signal to activate the output level reducing means for a predetermined period of time in response to a signal indicating that the signal level is higher than the audio output signal level. The audio output control device according to item 1. 3. The command signal generation means includes a comparison means for comparing the electrically converted input audio signal level with a level of a signal having a predetermined level, and the input audio signal level from the comparison means is set to the predetermined level. and active signal generating means for generating a signal that activates the output level reducing means for a predetermined period of time in response to a signal indicating that the output level is higher than a predetermined level. Audio output control device. 4. The audio output control device according to claim 1, wherein the command signal generated by the command signal generating means is given from the outside prior to inputting the input audio signal. 5. The output level reducing means includes: a muting circuit that reduces the level of a given audio signal; and a muting voltage generating circuit that generates a voltage signal that activates the muting circuit in response to a signal from the command signal generating means. An audio output control device according to any one of claims 1 to 4, comprising: