JP2014202808A - Input/output device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an input/output device capable of changing and outputting a response to an input in accordance with surrounding conditions.SOLUTION: In a voice recognition device 1, the level of a voice signal to be output from a microphone 2 is detected by a level check part 31, and a use case determination part 33 determines whether or not the detected voice signal level is smaller than a predetermined voice signal level. Then, when it is determined that the detected voice signal level is smaller than the predetermined voice signal level, a sound to be output from a speaker is reduced, and the luminance of a display device is decreased.

Description

  The present invention relates to an input / output device used for a speech recognition device that recognizes spoken speech.

  In recent years, in-vehicle devices, portable devices, and the like often have a built-in speech recognition device (speech recognition function) so that the operation of buttons or the like is not necessary and the operation can be easily performed only by voice.

  In this type of speech recognition apparatus, the processing result corresponding to the input speech is output as a response with display information such as speech information or an image as a response to the input speech, or a response such as acceptance of the input or a recognition result is sent. Output as audio information or display information. Such a response method has been performed in a predetermined manner such as a constant voice level and a constant luminance without considering the situation around the speaker.

  As a method of operating in consideration of the situation around the speaker in the speech recognition apparatus, the method described in Patent Document 1 can be cited as an example. The speech recognition apparatus described in Patent Document 1 amplifies the input speech level according to the usage state of the portable information terminal device to an appropriate level, thereby preventing the recognition rate from being lowered.

Japanese Patent No. 4299768

  In the conventional speech recognition apparatus, the response is always made in a predetermined manner without considering the situation around the speaker, so the speaker does not want to see or see the response content by the surrounding people. If you don't want to use it, you can't cope with it and you have to refrain from using the voice recognition device. Therefore, in such a situation, there is a problem that it is inconvenient to operate with a button or the like.

  The speech recognition apparatus described in Patent Document 1 controls the input speech level in order to prevent the recognition rate from being lowered, and does not consider any response from the speech recognition apparatus as described above.

  Therefore, in view of the above-described problems, an object of the present invention is to provide an input / output device capable of changing and outputting a response to an input according to a surrounding situation.

  In order to solve the above-mentioned problem, the invention according to claim 1 is characterized in that the first sound collecting means for collecting the uttered input sound and the input sound collected by the first sound collecting means for the sound recognition means. A first output means for outputting; a response acquisition means for acquiring a response from the voice recognition means; a second output means for outputting the response acquired by the response acquisition means; and the first sound collection means for collecting sound. An input voice level that is a voice level of the input voice is detected, and the input voice level compared with the voice level comparison means that compares the input voice level with a predetermined voice level determined in advance. And control means for changing the output of the second output means so that the response is difficult to recognize from the surroundings when the sound level is lower than the predetermined sound level.

  According to a seventh aspect of the present invention, the first sound collecting means for collecting spoken input sound, the second sound collecting means for collecting ambient sound other than the input sound, and the first sound collecting means are collected. A first output means for outputting the sung input sound to a voice recognition means; an ambient sound level detection means for detecting an ambient sound level that is an ambient sound level collected by the second sound collection means; and the sound A response acquisition means for acquiring a response from the recognition means; a second output means for outputting the response acquired by the response acquisition means; and an input that is a sound level of the input sound collected by the first sound collection means A ratio calculating means for detecting a sound level and calculating a ratio between the input sound level and the ambient sound level detected by the ambient sound level detecting means; and the ratio calculated by the ratio calculating means is a predetermined value determined in advance. If the value is smaller than the There is characterized by and a control means for changing the output of said second output means to be hard to recognize.

  The invention according to claim 8 is an input / output method in an input / output device for outputting a response from the voice recognition means to the spoken input voice, wherein the first sound collecting means for collecting the input voice collects the input voice. An input sound level that is a sound level of the sound that has been sounded is detected, and the input sound level that is compared in the sound level comparing step is compared with a sound level comparing step that compares the input sound level with a predetermined sound level that is determined in advance. And a control step of changing the output of the response so that the response of the voice recognition means is difficult to recognize from the surroundings when the level is lower than a predetermined voice level.

  The invention according to claim 9 is characterized in that the speech recognition method according to claim 8 is executed by a computer.

  The invention described in claim 10 is characterized in that the voice recognition program described in claim 9 is stored.

  The invention according to claim 11 is an input / output method in an input / output device for outputting a response from the voice recognition means to the spoken input voice, wherein the first sound collection means for collecting the input voice is collected. Detecting an input sound level that is a sound level of the sound that has been sounded, and detecting an ambient sound level that is a sound level of the ambient sound collected by the second sound collecting means for collecting the ambient sound other than the input sound; When the ratio calculated in the ratio between the input voice level and the ambient sound level and the ratio compared in the ratio calculating step is smaller than a predetermined value, the response of the voice recognition means from the surroundings And a control step of changing the output of the response so as to be difficult to recognize.

  The invention described in claim 12 is characterized in that the input / output method described in claim 11 is executed by a computer.

  The invention described in claim 13 is characterized in that the input / output program described in claim 12 is stored.

1 is a configuration diagram of an input / output device according to a first embodiment of the present invention. 2 is a flowchart of the operation of the input / output device shown in FIG. 1. It is a block diagram of the input / output apparatus concerning the 2nd Example of this invention. It is a flowchart of operation | movement of the input / output device shown by FIG. It is a block diagram of the input / output device concerning the other Example of this invention. It is a block diagram of the input / output device concerning the other Example of this invention.

  Hereinafter, an input / output device according to an embodiment of the present invention will be described. An input / output device according to an embodiment of the present invention includes a first sound collecting unit that collects spoken input sound, and a first output unit that outputs the input sound collected by the first sound collecting unit to the sound recognition unit. And a response acquisition unit that acquires a response from the voice recognition unit, and a second output unit that outputs the response acquired by the response acquisition unit. A voice level comparing means for detecting an input voice level that is a voice level of the input voice collected by the first sound collecting means and comparing the input voice level with a predetermined voice level; a voice level comparing means; And a control means for changing the output of the second output means so that the response is difficult to recognize from the surroundings when the input sound level compared with is lower than the predetermined sound level. By doing so, when the voice level of the input voice is low, it is determined that the user does not want to hear or see the voice recognition response, and recognizes the output of the second output means from the surroundings. It can be changed to be difficult. Therefore, the response to the input can be changed according to the surrounding situation and output.

  The second output means has audio output means for outputting the response as sound, and the control means outputs from the audio output means when the result of comparison by the audio level comparison means is smaller than a predetermined audio level. The sound to be played may be reduced. By doing so, it is possible to reduce the sound output from the sound output means such as a speaker when it is not desired to hear the voice recognition response in the surroundings.

  The second output means further includes display means for displaying the response as an image, and the control means displays the display means when the result of comparison by the sound level comparison means is smaller than a predetermined sound level. While stopping, you may make the sound output from an audio | voice output means small. In this way, when both the audio output means and the display means are provided, it is possible to stop the display of the display means and reduce the sound output from the audio output means such as a speaker.

  The second output means further includes an output interface for outputting a response as a sound from the external sound output means, and the control means is a case where the result of comparison by the sound level comparison means is smaller than a predetermined sound level. In addition, the response may be output only to the output interface. By doing so, it is possible to output sound only from an external sound output means such as an earphone when it is not desired to hear a voice recognition response in the surroundings.

  The second output means has display means for displaying the response as an image, and the control means recognizes the image from the surroundings when the result of comparison by the sound level comparison means is smaller than a predetermined sound level. You may make it change the display of a display means so that it may become difficult. In this way, when it is not desired to see a voice recognition response in the surroundings, for example, the brightness or viewing angle of a display means such as a liquid crystal display can be changed.

  The second output means further includes an audio output means for outputting the response as a sound, and the control means outputs the response of the audio output means when the result of comparison by the audio level comparison means is smaller than a predetermined audio level. While stopping the output, the display of the display means may be changed so that the image is difficult to recognize from the surroundings. In this way, when both the audio output means and the display means are provided, the sound output from the audio output means can be stopped to make it difficult to recognize the display on the display device.

  An input / output apparatus according to an embodiment of the present invention includes a first sound collecting unit that collects spoken input sound, a second sound collecting unit that collects ambient sounds other than the input sound, and a first collection. A first output means for outputting the input sound collected by the sound means to the voice recognition means; an ambient sound level detection means for detecting an ambient sound level that is the sound level of the ambient sound collected by the second sound collection means; Response acquisition means for acquiring a response from the voice recognition means, and second output means for outputting the response acquired by the response acquisition means. Then, a ratio calculating unit that detects an input sound level that is a sound level of the input sound collected by the first sound collecting unit and calculates a ratio between the input sound level and the ambient sound level detected by the ambient sound level detecting unit. And a control means for changing the output of the second output means so that the response is difficult to recognize from the surroundings when the ratio calculated by the ratio calculating means is smaller than a predetermined value. ing. In this way, the situation around the speaker can be determined from the ratio between the input voice and the ambient sound. In other words, when the ratio of the spoken input voice level to the ambient sound level (S / N ratio) is small, it can be determined that there are many people around and the voice is spoken with low voice, It is possible to change the output of the output means so that the user does not want to be heard or wants to be seen.

  An input / output method according to an embodiment of the present invention is an input / output method in an input / output device that outputs a response from speech recognition means to spoken input speech, and is a first method for collecting input speech. A voice level comparison step of detecting an input voice level that is a voice level of the voice collected by the sound collecting means and comparing the input voice level with a predetermined voice level, and an input voice compared in the voice level comparison step And a control step of changing the output of the response so that the response of the voice recognition means is difficult to recognize from the surroundings when the level is lower than the predetermined voice level. In this way, when the voice level of the input voice is small, it is possible to change the output of the response by determining that the voice recognition response is not desired to be heard or viewed. Therefore, the response to the input can be changed according to the surrounding situation and output.

  The input / output method described above may be configured as an input / output program that is executed by a computer. In this way, if the input speech level is low, it is determined that you do not want to hear the voice recognition response in the surroundings or you do not want to see it, and change the response output. Can be made. Therefore, the response to the input can be changed according to the surrounding situation and output.

  Further, the above-described voice recognition program may be stored in a computer-readable recording medium. In this way, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades can be easily performed.

  An input / output method according to an embodiment of the present invention is an input / output method in an input / output device that outputs a response from speech recognition means to spoken input speech, and is a first method for collecting input speech. The input sound level that is the sound level of the sound collected by the sound collecting means is detected, and the ambient sound level that is the sound level of the ambient sound collected by the second sound collecting means that collects ambient sounds other than the input sound is obtained. When the ratio calculation step for detecting and calculating the ratio between the input voice level and the ambient sound level and the ratio compared in the ratio calculation step is smaller than a predetermined value, the response of the voice recognition means is recognized from the surroundings. And a control step of changing the output of the response so as to be difficult to perform. In this way, the situation around the speaker can be determined from the ratio between the input voice and the ambient sound. In other words, when the ratio of the spoken input voice level to the ambient sound level (S / N ratio) is small, it can be determined that there are many people around and the voice is spoken with low voice, It is possible to change the output of the output means so that the user does not want to be heard or wants to be seen.

  The input / output method described above may be configured as an input / output program that is executed by a computer. By doing so, when the S / N ratio is small, it is determined that the user does not want to hear the voice recognition response in the surroundings or does not want to see it, and changes the response output. be able to. Therefore, the response to the input can be changed according to the surrounding situation and output.

  Further, the above-described voice recognition program may be stored in a computer-readable recording medium. In this way, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades can be easily performed.

  A speech recognition apparatus having an input / output device according to a first embodiment of the present invention will be described with reference to FIGS. As shown in FIG. 1, the voice recognition device 1 includes a microphone 2, a control device 3, and an external output device 4.

  The microphone 2 as the first sound collecting means collects the voice (input voice) uttered by the user, converts it into an electrical signal, and outputs it as an audio signal to the control device 3.

  The control device 3 includes a level check unit 31, a speech recognition engine unit 32, and a use case determination unit 33. The control device 3 is constituted by, for example, a microcomputer, a digital signal processor (DSP), or an ASIC (Application Specific Integrated Circuit).

  The level check unit 31 serving as the first output unit and the voice level comparison unit outputs the voice signal input from the microphone 2 to the voice recognition engine unit 32. In other words, the input voice collected by the first sound collecting means is output to the voice recognition means. The level check unit 31 detects the level of the audio signal input from the microphone 2 and outputs it to the use case determination unit 33 as the input audio level. That is, the input sound level that is the sound level of the input sound collected by the first sound collecting means is detected. Note that the level of the audio signal in this specification indicates the volume of the target sound, for example, the maximum value or average value of the amplitude of the audio signal.

  The voice recognition engine unit 32 converts the voice signal input from the level check unit 31 into a digital signal and performs voice recognition processing (the level check unit 31 may convert the signal into a digital signal). The speech recognition processing is not particularly limited as long as a known method such as a statistical method, a dynamic time expansion / contraction method, a hidden Markov model, or the like is used. The voice recognition engine unit 32 outputs a response related to the result of the voice recognition process to the external output device 4. The response related to the result of the speech recognition process is not limited to the speech information and display information related to the response to the spoken speech content, but the speech information and display information indicating that the speech has been recognized, or the speech could not be recognized. This also includes voice information and display information indicating that, or voice information and display information that prompts input of the next command or the like.

  In addition, when the voice recognition engine unit 32 is a command for another processing device (not shown) as a result of voice recognition, the voice recognition engine unit 32 outputs a command to the other processing device. The other processing device is not limited to the one configured integrally with the voice recognition device 1, but may be detachable or communicated wirelessly or via a network or the like. In the case of the configuration shown in FIG. 1, since the speech recognition engine unit 32 is included in the control device 3, the speech recognition engine unit 32 includes a speech recognition unit and a response acquisition unit that acquires a response from the speech recognition unit. Doubles as

  The use case determination unit 33 as the sound level comparison unit and the control unit, when the input sound level detected by the level check unit 31 is smaller than a predetermined sound signal level (predetermined predetermined sound level). Control is made so that the external output device 4 is changed to an output corresponding to the private mode by determining that the private mode is a mode indicating a situation in which it is not desired to hear or recognize a voice recognition response. Output a signal. That is, the input voice level is compared with a predetermined voice level. Then, when the input sound level compared by the sound level comparison means is smaller than the predetermined sound level, the output of the second output means is changed so that the response is difficult to recognize from the surroundings.

  Note that if the input speech level is low, the recognition rate in the speech recognition engine unit 32 may decrease. Therefore, the predetermined predetermined speech signal level is determined within a range in which the recognition rate in the speech recognition engine unit 32 does not decrease. Is desirable. Alternatively, the speech recognition processing may be performed after performing processing that reduces the influence of ambient noise such as the processing described in Patent Document 1.

  In FIG. 1, the control device 3 includes a level check unit 31, a speech recognition engine unit 32, and a use case determination unit 33, but is not limited thereto. For example, it may be configured by individual components (microcomputer, DSP, ASIC, etc.).

  The external output device 4 as the second output means includes an audio output unit 41 as an audio output means and a display unit 42 as a display means. The voice output unit 41 includes a speaker that outputs, as a voice, a response that is input as voice information among responses related to the result of the voice recognition process output from the voice recognition engine unit 32, an amplifier that controls a volume output to the speaker, and the like. have. The display unit 42 is a liquid crystal display or an organic EL (an organic EL) that displays a response input as display information as an image (including text-only information) among responses related to the result of the speech recognition process output from the speech recognition engine unit 32. Electro Luminescence) A display device such as a display and a driver circuit for controlling display of the display device. That is, the external output device 4 outputs the response acquired by the response acquisition means.

  When the use case determination unit 33 determines that the private mode is selected and a control signal that changes the output is input, the audio output unit 41 causes the amplifier or the like to increase the amplification factor so that the sound output from the speaker is reduced. To change. That is, when the result of comparison by the sound level comparison means is smaller than a predetermined sound level, the sound output from the sound output means is reduced. The display unit 42 is controlled by a driver circuit so as to reduce the luminance of the display device. That is, when the result of comparison by the sound level comparison means is smaller than a predetermined sound level, the display of the display means is changed so that the image is difficult to recognize from the surroundings.

  As is clear from the above description, the microphone 2, the level check unit 31, the use case determination unit 33, and the external output device 4 constitute the input / output device 10 according to the first embodiment of the present invention.

  Next, the operation of the input / output device 10 configured as described above will be described with reference to the flowchart of FIG. The flowchart shown in FIG. 2 is executed by the control device 3.

  First, in step S11, the voice signal of the input voice is input from the microphone 2 to the level check unit 31, and the process proceeds to step S12.

  Next, in step S12, the level check unit 31 detects the input sound level of the sound signal of the input sound input from the microphone 2 and outputs it to the use case determination unit 33, and the process proceeds to step S13.

  Next, in step S13, the use case determination unit 33 compares the input audio level detected by the level check unit 31 with a predetermined audio signal level that is determined in advance, and if it is smaller than the predetermined audio signal level (YES) In the case of (1), the process proceeds to step S14, and in the case of a predetermined audio signal level or higher (in the case of NO), the process proceeds to step S15. That is, in steps S12 and S13, it functions as an audio level comparison process.

  Next, in step S14, since it is determined in step S13 that the level is lower than the predetermined audio signal level, the use case determination unit 33 changes the output of the external output device 4 as a private mode so that it is difficult to recognize from the surroundings. (Output control). Specifically, as described above, the audio output unit 41 changes the amplification factor to an amplifier or the like so that the sound output from the speaker is smaller than the default volume, and the display unit 42 adjusts the luminance of the display device. The driver circuit is controlled to lower the default brightness. That is, this step functions as a control process. Here, the default volume and luminance are the volume and luminance of the voice recognition device 1 in the initial state.

  On the other hand, in step S15, since it is determined that the level is equal to or higher than the predetermined level in step S13, the use case determination unit 33 sets the default volume and luminance as the normal mode. That is, if the default volume and brightness before the execution of this step are not changed. If the volume and brightness are lower than the default volume before executing this step, the default volume and brightness are restored.

  According to the present embodiment, in the voice recognition device 1, the level check unit 31 detects the input voice level output from the microphone 2, and the use case determination unit 33 sets the detected input voice level to a predetermined value. It is determined whether or not the audio signal level is lower. When the input sound level is smaller than a predetermined sound signal level, the sound output from the speaker is reduced and the luminance of the display device is decreased. In this way, when the input voice level is low, it may be judged that the voice recognition response is not desired to be heard around or is not desired to be seen, and the sound is reduced or the luminance is reduced. it can. Therefore, the response to the input can be changed according to the surrounding situation and output.

  Next, a speech recognition apparatus 1 according to a second embodiment of the present invention will be described with reference to FIGS. The same parts as those in the first embodiment described above are denoted by the same reference numerals and description thereof is omitted.

  In the input / output device 10 according to the present embodiment, a microphone 5 is added to the voice recognition device 1 shown in FIG. The microphone 5 as the second sound collecting unit collects sounds around the voice recognition device 1 (ambient sounds), not collecting voices uttered by the user. That is, ambient sounds other than the spoken input voice are collected.

  The level of the ambient sound collected by the microphone 5 is detected by the level check unit 31, and the level of the audio signal (ambient sound level) is output to the use case determination unit 33. That is, the level check unit 31 functions as an ambient sound level detection unit that detects an ambient sound level that is the sound level of the ambient sound collected by the second sound collection unit.

  The use case determination unit 33 calculates the ratio (S / N ratio) between the input sound level collected by the microphone 2 detected by the level check unit 31 and the ambient sound level. Here, the S / N ratio in the present embodiment is a value obtained by dividing the input sound level by the ambient sound level (input sound level / ambient sound level). If the calculated S / N ratio is smaller than a predetermined value, the private mode is determined and a control signal is output to the external output device 4 so as to change the output to the private mode. That is, the use case determination unit 33 functions as a ratio calculation unit.

  That is, when the S / N ratio is small, it means that the ambient sound is relatively loud with respect to the user's utterance, so that it can be assumed that the utterance is uttered in a loud situation in a situation where there are many people around. . Therefore, when the S / N ratio is small, it is determined that the user does not want to hear the response of the voice recognition engine unit 32 or does not want to see the response, and the private mode operation is performed. The operation of the external output device 4 in the private mode is the same as that in the first embodiment. That is, the sound output from the speaker is reduced, and the brightness is lowered so that the image displayed on the display device is difficult to recognize from the surroundings.

  Next, the operation of the speech recognition apparatus 1 in this embodiment will be described with reference to the flowchart of FIG. The flowchart shown in FIG. 4 is executed by the control device 3.

  First, in step S21, an audio signal is input from the microphone 2 and the microphone 5 to the level check unit 31, and the process proceeds to step S12.

  Next, in step S22, the level check unit 31 detects the input sound level of the sound signal input from the microphone 2, detects the ambient sound level of the sound signal input from the microphone 5, and determines each use case. The data is output to the unit 33, and the process proceeds to step S23.

  Next, in step S23, the use case determination unit 33 calculates a ratio (S / N ratio) between the input sound level detected by the level check unit 31 and the ambient sound level, and the S / N ratio is determined from a predetermined value. If it is smaller (in the case of YES), the process proceeds to step S24. If it is equal to or greater than the predetermined value (in the case of NO), the process proceeds to step S25. That is, it functions as a ratio calculation process in steps S22 and S23.

  Steps S24 and S25 are the same as steps S14 and S15 in FIG.

  According to the present embodiment, in the speech recognition apparatus 1, the level check unit 31 detects the input sound level and the level of the ambient sound output from the microphone 5 (ambient sound level), and the use case determination unit 33 detects the input sound level. It is determined whether the ratio between the level and the ambient sound level (S / N ratio) is smaller than a predetermined value. When the S / N ratio is smaller than a predetermined value, for example, the sound output from the speaker is reduced and the luminance of the display device is decreased. In this way, when the S / N ratio is small, it may be judged that the user does not want to hear the voice recognition response in the surroundings or does not want to see it, so that the sound is reduced or the luminance is lowered. it can. Therefore, the response to the input can be changed according to the surrounding situation.

  In the above-described two embodiments, the brightness of the display device included in the display unit 42 is reduced so that the displayed image is difficult to recognize from the surroundings. The viewing angle may be narrowed. In this case, for example, a filter that changes the polarization direction by changing the alignment state of the liquid crystal by applying a voltage to the liquid crystal element may be provided on the surface of the display device.

  In the two embodiments described above, the control of both the audio output unit 41 and the display unit 42 is changed, but only one of them may be used.

  Further, as in the second embodiment described above, when both the speaker (sound output unit 41) and the display device (display unit 42) are included, when the private mode is determined, the display device display is performed. May be stopped (screen is turned off), and the sound output from the speaker may be reduced. Or conversely, the output of sound from the speaker may be stopped to reduce the brightness of the display device or narrow the viewing angle. That is, when both the audio output means and the display means are provided, stopping one operation includes changing the output so that the response is difficult to recognize from the surroundings.

  The speech recognition engine unit 32 is not limited to the form included in the control device 3 as shown in FIGS. 1 and 3, and is provided in, for example, an external server that communicates wirelessly or via a network or the like. Also good. An example is shown in FIG. In FIG. 5, a communication unit 34 is provided in the control device 3. The communication unit 34 outputs the voice signal input from the level check unit 31 to the voice recognition engine unit 21 provided in the server 20 connected to the Internet 30. Then, the communication unit 34 outputs the response input from the speech recognition engine unit 21 to the external output device 4 or another processing device. In the case shown in FIG. 5, the communication unit 34 functions as a first output unit and a response acquisition unit.

  Further, as shown in FIG. 6, a terminal for connecting an external audio output means 6 such as an earphone or a headphone, a circuit for performing wireless communication with the external audio output means 6 and Bluetooth (registered trademark), an antenna, or the like Output interface 43 may be provided.

  The output interface 43 shown in FIG. 6 can be switched by an audio output unit 41 and a changeover switch 44. That is, when earphones or headphones are connected, the changeover switch 44 is switched to the output interface 43 side so that no sound is output from the speaker of the audio output unit.

  In the case of having the output interface 43 shown in FIG. 6, when the private mode is determined, the display of the display device is stopped, and the sound (voice signal) that responds to the response of the voice recognition engine unit 32 only from the output interface. ) May be output. By doing so, it is possible to output only sound from an external sound output means such as an earphone or a headphone when it is not desired to see a voice recognition response in the surroundings.

  Further, if the level check unit 31 and the use case determination unit 33 are configured by a computer such as a microcomputer and the flowcharts shown in FIGS. 2 and 4 are computer programs, they can be configured as input / output programs.

  Further, the present invention is not limited to the above embodiment. That is, those skilled in the art can implement various modifications in accordance with conventionally known knowledge without departing from the scope of the present invention. Of course, such modifications are included in the scope of the present invention as long as the configuration of the input / output device of the present invention is provided.

2 Microphone (first sound collecting means)
31 Level check section (first output means, sound level comparison means, ambient sound level detection means)
32 Voice recognition engine (response acquisition means)
33 Use case determination unit (voice level comparison means, control means, ratio calculation means)
4 External output device (second output means)
41 Audio output unit (second output means, audio output means)
42 display section (second output means, display means)
5 Microphone (second sound collecting means)
6 External audio output means 10 Input / output device S12 Level check (audio level comparison process)
S13 Smaller than predetermined audio signal level (audio level comparison process)
S14 Private mode (control process)
S22 Level check (ratio calculation process)
S23 Smaller than a predetermined value (ratio calculation step)
S24 Private mode (control process)

Claims (13)

A first sound collecting means for collecting the spoken input sound;
First output means for outputting the input voice collected by the first sound collection means to voice recognition means;
Response acquisition means for acquiring a response from the voice recognition means;
Second output means for outputting the response acquired by the response acquisition means;
Voice level comparison means for detecting an input voice level that is a voice level of the input voice collected by the first sound collecting means and comparing the input voice level with a predetermined voice level;
Control means for changing the output of the second output means so that the response is difficult to recognize from the surroundings when the input voice level compared by the voice level comparing means is smaller than the predetermined voice level; An input / output device comprising: The second output means has voice output means for outputting the response as sound,
The said control means reduces the sound output from the said audio | voice output means, when the result compared with the said audio | voice level comparison means is smaller than the said predetermined audio | voice level, The said output means is characterized by the above-mentioned. I / O device. The second output means further includes display means for displaying the response as an image,
The control means stops the display of the display means and reduces the sound output from the sound output means when the result of the comparison by the sound level comparison means is smaller than the predetermined sound level. The input / output device according to claim 2. The second output means further includes an output interface for outputting the response as sound from an external sound output means,
4. The input / output according to claim 3, wherein the control means causes only the output interface to output the response when a result of comparison by the sound level comparison means is smaller than the predetermined sound level. apparatus. The second output means has display means for displaying the response as an image,
The control means changes the display of the display means so that the image is difficult to recognize from the surroundings when the result of the comparison by the sound level comparison means is smaller than the predetermined sound level. The input / output device according to claim 1. The second output means further includes sound output means for outputting the response as sound,
The control means stops the output of the sound output means when the result of comparison by the sound level comparison means is smaller than the predetermined sound level, and makes the image difficult to recognize from the surroundings. 6. The input / output device according to claim 5, wherein the display of the display means is changed. A first sound collecting means for collecting the spoken input sound;
Second sound collecting means for collecting ambient sounds other than the input sound;
First output means for outputting the input voice collected by the first sound collection means to voice recognition means;
Ambient sound level detection means for detecting an ambient sound level that is the sound level of the ambient sound collected by the second sound collection means;
Response acquisition means for acquiring a response from the voice recognition means;
Second output means for outputting the response acquired by the response acquisition means;
A ratio for detecting an input sound level that is a sound level of the input sound collected by the first sound collecting means and calculating a ratio between the input sound level and the ambient sound level detected by the ambient sound level detecting means A calculation means;
Control means for changing the output of the second output means so that it is difficult to recognize the response from the surroundings when the ratio calculated by the ratio calculation means is smaller than a predetermined value. An input / output device characterized by An input / output method in an input / output device that outputs a response from speech recognition means to spoken input speech,
A voice level comparison step of detecting an input voice level, which is a voice level of the voice collected by the first sound collecting means for collecting the input voice, and comparing the input voice level with a predetermined voice level;
A control step of changing the output of the response so that the response of the speech recognition means is difficult to recognize from the surroundings when the input speech level compared in the speech level comparison step is smaller than the predetermined speech level; The input / output method characterized by including.   An input / output program that causes a computer to execute the input / output method according to claim 8.   A computer-readable recording medium storing the input / output program according to claim 9. An input / output method in an input / output device that outputs a response from speech recognition means to spoken input speech,
The surroundings collected by the second sound collecting means for detecting the input sound level, which is the sound level of the sound collected by the first sound collecting means for collecting the input sound, and collecting ambient sounds other than the input sound A ratio calculating step of detecting an ambient sound level that is a sound level of sound and calculating a ratio between the input sound level and the ambient sound level;
A control step of changing the output of the response so that the response of the voice recognition means is difficult to recognize from the surrounding when the ratio compared in the ratio calculation step is smaller than a predetermined value set in advance. An input / output method comprising:   An input / output program that causes a computer to execute the input / output method according to claim 11.   A computer-readable recording medium storing the input / output program according to claim 12.

Images