JP2000132200A - Audio/video device with voice recognizing function and voice recognizing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make performable the input of human voice to a voice recognizing device even if a sound is outputted from the speaker of an audio/video device nearby. SOLUTION: This device is provided with a band pass attenuator 3 for attenuating the sound of the frequency band extending from several 100 Hz to several kHz, which corresponds to human voice, of the sounds outputted from the speakers 8-11 of the audio/video device. The sound pressure level of the sound outputted from each speaker is detected by a voice recognizing device 13 through a microphone 12, and when the sound pressure level disturbs the input of human voice to the voice recognizing device 13, since a control means 14 controls the band pass attenuator 3 to attenuate the sound of the above frequency band, the input of human voice to the voice recognizing device 13 can be performed while listening to the music of the audio/video device.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to an audio / video device with a voice recognition function and a voice recognition method.

[0002]

2. Description of the Related Art A speech recognition device is a device for recognizing a voice uttered by a human and outputting necessary commands to the device, and is used as one of remote controllers. For example, if you say "hot" to the indoor air conditioner, it will output a command to lower the temperature by recognizing it, and if you say "warm", it will output a command to raise the temperature and output the air conditioner. The temperature control of the shocker can be performed without manual operation. Such a voice recognition device is also used in home appliances, personal computers, and in-vehicle devices mounted on vehicles. A navigation device, which is one of the in-vehicle devices, automatically selects and displays a recommended route to a destination when uttering a destination, and displays a list of facilities when uttering a facility name. Can be. In the case of an in-vehicle device, remote control using a voice recognition device is particularly useful so as not to hinder the driver's driving operation.

[0003]

However, in the conventional voice recognition device, when voice is input through a microphone, the voice recognition device is used for an audio / video device such as a radio, a television, a cassette tape, a CD, and an MD. If it is attached to or attached to another device located near the audio / video device, the sound of human voice or music output from the audio / video device will be an obstacle, Unless the volume is reduced or turned off by manual operation, a voice for remote control cannot be input to the voice recognition device.

The present invention solves such a conventional problem. Even when sound is output from a speaker of an audio / video device nearby, a human voice is input to a voice recognition device. It is an object of the present invention to provide an audio / video device with a voice recognition function and a voice recognition method.

[0005]

SUMMARY OF THE INVENTION In order to achieve the above-mentioned object, the present invention aims to achieve a sound output from a speaker of an audio / video apparatus, for example, several hundred Hz, which hinders voice recognition by a human voice input. And a means for attenuating sound in a frequency band from up to several kHz, and a sound pressure level of sound output from a speaker is detected by a speech recognition device, and the sound pressure level is used to prevent speech recognition by human voice input. In such a case, a control means for controlling the attenuation means to attenuate the sound in the frequency band is provided. Thus, it is possible to input a human voice to the voice recognition device while listening to music or the like with the audio / video device.

[0006]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The invention according to claim 1 of the present invention is directed to an audio / video device for outputting sound, and a sound output from a speaker of the audio / video device, the sound being input by a human voice. Attenuating means for attenuating sound in a specific frequency band that hinders recognition; and recognizing an input human voice and outputting a predetermined command, and detecting a sound pressure level of the sound output from the speaker. Audio with a voice recognition function, comprising: a voice recognition device; and control means for controlling the attenuating means based on the detected sound pressure level to output sound with the specific frequency band attenuated from the speaker. / Video device, which has the effect that a human voice can be input to the voice recognition device while listening to music or the like with the audio / video device.

According to a second aspect of the present invention, there is provided the apparatus according to the first aspect, comprising a plurality of speakers and a plurality of attenuating means, wherein the control unit individually controls the amount of attenuation of each attenuating means. Audio / video device with voice recognition function,
For example, when speakers are arranged at the front and rear, the front speakers mainly interfere with human voice input, so that the volume of the front speakers is attenuated while listening to music or the like from the rear speakers. This has the effect that human voice input to the voice recognition device becomes possible.

According to a third aspect of the present invention, the audio / video device is a vehicle-mounted audio / video device mounted on a vehicle. It is an audio / video device, and has an effect that the present invention can be applied to a vehicle-mounted device.

According to a fourth aspect of the present invention, in the audio / video apparatus with a voice recognition function according to the third aspect, the voice recognition apparatus is used in common with the audio / video apparatus and another apparatus. For example, when the in-vehicle audio / video device is integrated with the in-vehicle navigation device, the voice recognition device
This has the effect that the video device and the navigation device can be shared.

According to a fifth aspect of the present invention, the specific frequency band is several hundred Hz to several kHz.
4. The audio / video device with a voice recognition function according to any one of items 1 to 4, which has an effect of reliably attenuating a frequency band that hinders human voice input.

[0011] The invention according to claim 6 of the present invention is characterized in that when a voice is input to a voice recognition device while sound is being output from a speaker of an audio / video device nearby,
This is a voice recognition method characterized by attenuating the sound of a specific frequency band that hinders the voice input, and enables a human voice input to the voice recognition device while listening to music or the like with an audio / video device. It has the action of:

According to a seventh aspect of the present invention, when the audio / video device has a plurality of channels, the sound of a specific frequency band is attenuated for each channel. This is a recognition method, and has the effect of attenuating only the sound of a channel that interferes with voice input.

According to an eighth aspect of the present invention, the specific frequency band is several hundred Hz to several kHz.
Or the voice recognition method according to 7, which has an effect of reliably attenuating a frequency band that hinders human voice input.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. (Embodiment 1) FIG. 1 shows a configuration of a 4-channel in-vehicle audio device with a voice recognition function according to a first embodiment of the present invention. In FIG. 1, 1 is an antenna, 2 is a radio receiver, 3 is several hundred Hz to several k.
Band-pass attenuators for attenuating frequencies in a specific frequency band up to Hz, amplifiers for each channel, 4, 5, 6, and 7; amplifiers for each channel; 8, 9, 10, and 11 for speakers for each channel; Is a voice recognition device, and 14 is a control unit. The audio device is integrally formed with the navigation device, and is disposed in a dashboard in the front of the vehicle cabin. The voice recognition device 13 is shared by the audio device and the navigation device. The speakers 8 and 9 are arranged on the left and right sides in front of the vehicle interior, and the speakers 10 and 11 are arranged on left and right sides behind the interior of the vehicle interior.
The microphone 12 is embedded in the wheel handle.

Next, the operation of this embodiment will be described with reference to the flow chart of FIG. Radio FM radio waves received through the antenna 1 are tuned and detected by the radio receiving unit 2, output as four-channel audio signals, and amplified by the amplifiers 4, 5, 6, and 7, respectively. It is output from 10, 11 (step S1).
At this time, the microphone 12 converts the sound output from each of the speakers 8 to 11 into an electric signal and inputs the electric signal to the speech recognition device 13. In this state, when the driver performs a voice input through the microphone 12 to change the operation of the audio device or the navigation device (step S2), the voice recognition device 1
2 determines whether or not the voice signal input from the driver can be clearly recognized (step S3), and the speakers 8 to 11 are determined.
When the sound signal input from the driver disturbs the voice signal input from the driver, an error signal is output to the control unit 14. Based on the error signal, the control unit 14 calculates the number 10 in the band-pass attenuator 3
The frequency in the specific frequency band from 0 Hz to several kHz is attenuated (step S4). Thereby, each speaker 8
11 to 11 output a sound in which the frequency of the specific frequency band is attenuated. Since the sound signal in this band is only the sound signal input by the driver through the microphone 12, the sound recognition device 13 Can be clearly recognized.

As described above, according to the first embodiment, the sound output from the speakers 8 to 11, for example, the sound pressure level of music is detected by the voice recognition device 13 through the microphone 12, and in this state, the driver If the voice input through the microphone 12 cannot be clearly recognized, the control unit 1
4 controls the band-pass attenuator 3 so that the frequency of the music output from the speakers 8 to 11 is several hundred Hz.
Attenuates frequencies in a specific band from to several kHz, so that the driver can listen to music in other frequency bands,
Voice input to the voice recognition device 13 can be performed.

(Embodiment 2) FIG. 3 shows a configuration of a vehicle-mounted 4-channel audio device with a voice recognition function according to a second embodiment of the present invention, and is shown in FIG. 1 is the bandpass attenuator 3,
That is, it is divided into four channels.
4, each band pass attenuator 3a, 3b, 3c,
3d can be controlled individually.

Therefore, in the second embodiment, the sound output from each of the speakers 8 to 11, for example, the sound pressure level of music is detected by the voice recognition device 13 through the microphone 12, and in this state, the driver operates the microphone 12 If the voice input through the input unit cannot be recognized clearly,
Controls only the band-pass attenuators 3a and 3b to attenuate the frequency of a specific band from several hundred Hz to several kHz from the frequency of the music output from the front speakers 8 and 9 close to the microphone 12. The user can perform voice input to the voice recognition device 13 while listening to music from the rear speakers 10 and 11 that are not attenuated.

In each of the above embodiments, the voice recognition device 13 detects the recognition rate of the driver's voice input through the microphone 12 and outputs it to the control unit 14.
4 may control the attenuation rate in the band-pass attenuator according to the input recognition rate. Further, the voice recognition device 13 may be dedicated to an audio / video device. Further, the audio / video device may be for household use other than for in-vehicle use.

[0020]

As described above, according to the present invention, of the sound output from the speaker of the audio / video device, the frequency range from several hundred Hz to several kHz, for example, which hinders voice recognition by human voice input. With means for attenuating the sound in the frequency band, the sound pressure level of the sound output from the speaker is detected by a speech recognition device, and when the sound pressure level hinders speech recognition by human voice input, Since the control means for controlling the attenuating means to attenuate the sound in the frequency band is provided, there is an effect that a human voice can be input to the speech recognition device while listening to music or the like with the audio / video device.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of a vehicle-mounted 4-channel audio device with a voice recognition function according to a first embodiment of the present invention.

FIG. 2 is a flowchart showing an operation in the first embodiment.

FIG. 3 is a block diagram showing a configuration of a vehicle-mounted 4-channel audio device with a voice recognition function according to a second embodiment of the present invention;

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 Antenna 2 Radio receiving part 3, 3a, 3b, 3c, 3d Bandpass attenuator 4, 5, 6, 7 Amplifier 8, 9, 10, 11 Speaker 12 Microphone 13 Voice recognition device 14 Control part

Claims (8)

[Claims] 1. An audio / video device for outputting sound, and a sound of a specific frequency band which interferes with voice recognition by a human voice input among sounds output from a speaker of the audio / video device is attenuated. Damping means;
A voice recognition device for recognizing the input human voice and outputting a predetermined command, and detecting a sound pressure level of the sound output from the speaker; and detecting the attenuation based on the detected sound pressure level. Control means for controlling means for outputting sound with the specific frequency band attenuated from the speaker. 2. The audio / video apparatus with a voice recognition function according to claim 1, further comprising a plurality of speakers and a plurality of attenuating means, wherein the control unit controls the amount of attenuation of each attenuating means individually. 3. The audio / video device with a voice recognition function according to claim 1, wherein the audio / video device is a vehicle-mounted audio / video device mounted on a vehicle. 4. The apparatus according to claim 3, wherein the voice recognition device is shared by the audio / video device and another device.
An audio / video device with a voice recognition function according to the above. 5. The audio / video device with a voice recognition function according to claim 1, wherein the specific frequency band is several hundred Hz to several kHz. 6. When sound is input to a speech recognition device while sound is being output from a speaker of an audio / video device nearby, sound in a specific frequency band that hinders the sound input is attenuated. A speech recognition method characterized by the following. 7. The speech recognition method according to claim 6, wherein when the audio / video device has a plurality of channels, the sound of a specific frequency band is attenuated for each channel. 8. The speech recognition method according to claim 6, wherein the specific frequency band is from several hundred Hz to several kHz.