JP2018129678A - Information processing apparatus, method of using microphone, program to be executed by computer - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an easy-to-use information processing apparatus according to a user's environment when using a voice assistant, method of using a microphone, and a program to be executed by a computer.SOLUTION: The information processing apparatus including a plurality of microphones, includes: mode setting means that selects and sets one of a first mode having directivity and a second mode having no directivity as a mode of use of the plurality of microphones on the basis of a state of the information processing apparatus and ambient sound; voice processing means for performing signal processing on sounds input from the plurality of microphones in accordance with the mode set by the mode setting means; and voice assistant means for performing voice assist by voice recognition of the sound processed by the voice processing means.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing apparatus, a microphone usage method thereof, and a program executed by a computer.

  Recently, in information processing apparatuses such as notebook PCs, smartphones, and tablets, an increasing number of people use voice assistant functions such as “Cortana”, “Siri”, “OK Google”, and “Talking Concierge”. Such a voice assistant is a function in which an information processing apparatus interprets a user's utterance and executes various operations instructed by voice. A voice assistant generally interprets what the user has spoken using techniques such as voice recognition and natural language processing.

  Many information processing apparatuses include a plurality of microphones. Multiple microphones are frequently used in VOIP and voice assistants. Some information processing apparatuses perform noise cancellation by performing beam forming processing when a plurality of microphones are used, and this beam forming is often enabled by default. In such beam forming, first, a plurality of microphones are used, and a voice at a specified angle is extracted by calculating and correcting a difference in the arrival time of sound at each microphone at the specified angle.

  However, for example, there are cases where the user wants to use the voice assistant when the information processing apparatus is out of reach or at a distance. More specifically, for example, the user may ask the voice assistant, “Do you need an umbrella today?” From a location away from the information processing apparatus and ask for an answer. On the other hand, since the voice assistant needs to be uttered by the user, it is often not used because it is embarrassed and annoyed by others in general where there are many people around. Therefore, when using a voice assistant, a user-friendly system is desired according to the use environment of the user.

Japanese Patent Laying-Open No. 2014-4270

  The present invention has been made in view of the above, and when using a voice assistant, an information processing device that is easy to use according to a user's usage environment, a method of using the microphone, and a program executed by a computer The purpose is to provide.

  In order to solve the above-described problems and achieve the object, the present invention provides an information processing apparatus including a plurality of microphones, the state of the plurality of microphones based on the state of the information processing apparatus and surrounding sounds. Mode setting means for selecting and setting one of the first mode having directivity and the second mode having no directivity as use modes, and signal processing is performed on sound input from the plurality of microphones Voice processing means and voice assistant means for performing voice assist by recognizing the sound signal-processed by the voice processing means, wherein the plurality of modes have a directivity first mode, and directivity And a second mode having no.

  Further, according to a preferred aspect of the present invention, the mode setting means sets the second mode when the information processing apparatus is in an idle state when the first mode is set. It is desirable to set.

  Further, according to a preferred aspect of the present invention, it is desirable that the mode setting means sets the first mode when the second mode is set and there are a plurality of surrounding sound sources. .

  According to a preferred aspect of the present invention, when the second mode is set and the surrounding sound source is one, the mode setting means sets the speaker volume to be larger than the sound source. The voice assistant means preferably waits for the voice input of the utterance command from the user.

  According to a preferred aspect of the present invention, when the second mode is set and the surroundings are silent, the mode setting means maintains the second mode, and the voice assistant means It is desirable to wait for the voice input of the utterance command from the user.

  According to a preferred aspect of the present invention, in the first mode, beam forming processing is performed to extract only sound in the front direction from the information inputted from the plurality of microphones. The mode is desirable.

  Further, according to a preferred aspect of the present invention, in the second mode, the sensitivity of the plurality of microphones is set higher than that in the first mode, and the sound in all directions is spread over a wide range with respect to the information processing apparatus. It is desirable to be in a sound collecting mode.

  According to a preferred aspect of the present invention, in the second mode, the information processing apparatus collects sounds in all directions and performs a process of extracting the loudest sound among the collected sounds. The mode is desirable.

  Moreover, according to a preferable aspect of the present invention, it is desirable that the mode setting means sets the first mode by default.

  According to a preferred aspect of the present invention, it is desirable that the information processing apparatus is a notebook PC.

  In order to solve the above-described problems and achieve the object, the present invention provides a method of using a microphone of an information processing apparatus including a plurality of microphones, based on the state of the information processing apparatus and surrounding sounds. According to a mode setting step of selecting and setting one of the first mode having directivity and the second mode having no directivity as the use modes of the plurality of microphones, and the mode set in the mode setting step A voice processing step for performing signal processing on sound input from the plurality of microphones; and a voice assistant step for performing voice assist by recognizing the sound signal-processed in the voice processing step. It is characterized by.

  In order to solve the above-described problems and achieve the object, the present invention is a program installed in an information processing apparatus including a plurality of microphones, and is based on the state of the information processing apparatus and surrounding sounds. The mode setting step of selecting and setting one of the first mode having directivity and the second mode having no directivity as the use modes of the plurality of microphones, and the mode set in the mode setting step And a voice processing step for performing signal processing on sounds input from the plurality of microphones, and a voice assistant step for performing voice assist by recognizing the sound processed in the voice processing step and performing voice assist. It is made to perform.

  According to the present invention, when a voice assistant is used, there is an effect that it is possible to provide an information processing apparatus that is easy to use according to the use environment of the user.

FIG. 1 is a schematic external view of a notebook PC to which an information processing apparatus according to the present invention is applied. FIG. 2 is a diagram illustrating a schematic hardware configuration example of the notebook PC of FIG. FIG. 3 is a schematic functional configuration diagram related to voice input / output of the notebook PC of FIG. FIG. 4 is an explanatory diagram for explaining a use mode of the microphone. FIG. 5 is a flowchart for explaining an example of processing for switching the use mode of the microphone according to the state of the notebook PC and surrounding sounds.

  Hereinafter, an embodiment of a computer system to which an information processing apparatus according to the present embodiment, a method of using the microphone, and a program to be executed by a computer are applied will be described. Although the components of the present invention are generally illustrated in the drawings herein, it can be readily understood that they may be arranged and designed in a wide variety of configurations with various configurations. Accordingly, the following more detailed description of the apparatus, method and program embodiments of the present invention is not intended to limit the scope of the invention as set forth in the appended claims, but merely to implement selected embodiments of the invention. It is intended as an example only, and is merely illustrative of selected embodiments of an apparatus, system and method consistent with the present invention as set forth in the claims herein. Those skilled in the art will appreciate that the present invention may be practiced without one or more of the specific details or with other methods, components, or materials.

(Embodiment 1)
FIG. 1 is a schematic external view of a notebook PC 1 to which an information processing apparatus according to the present invention is applied. As shown in the figure, the notebook PC 1 includes a main body side housing 2 and a display side housing 3 which are substantially rectangular parallelepipeds. The main body side housing 2 includes an input unit 4 having a keyboard and a touchpad, and left and right speakers 6a and 6b. The display-side housing 3 is arranged on the LCD (Liquid Crystal Display) 7, on the display surface side of the LCD 7, approximately at the upper center thereof, and on the both sides of the camera 8, with the camera 8 capable of imaging a front subject. Left and right microphones 5a and 5b. Although the number of microphones is two, it may be three or more.

  The main body side housing 2 and the display side housing 3 are connected to each other by a pair of left and right connecting portions (hinge portions) 9a and 9b at the respective ends, and the connecting portions 9a and 9b open and close these housings. Supports freely.

  FIG. 2 is a diagram illustrating a schematic hardware configuration example of the notebook PC 1 of FIG. As shown in the figure, the notebook PC 1 includes a CPU 11, a ROM 12, a memory 13, a storage 14, an LCD 7, an input unit 4, a camera device 15, an audio device 17, a communication device 19, a battery 21, a DC-DC converter 22, and an AC adapter. 23, each part is connected directly or indirectly via a bus.

  The CPU 11 controls the entire notebook PC 1 by the OS 30 stored in the storage 14 connected via the bus, and manages the function of executing processing based on various programs stored in the storage 14. The ROM 12 stores a BIOS (Basic Input / Output System: basic input / output system) 12a, data, and the like.

  The memory 13 is composed of a cache memory and a RAM, and is a writable memory used as a work area for writing processing data of the execution program as a read area for the execution program of the CPU 11.

  The storage 14 is configured by a non-volatile storage device such as an HDD (hard disk) or SDD, for example. For example, the entire notebook PC 1 such as Windows (registered trademark) XP, Vista, 7, 8, 8.1, 10 or the like. OS 30 for performing control, various drivers 31 for operating peripheral devices including an audio driver 31a, and voice assistant application program (hereinafter, “application program” is referred to as “application”). 32, a VOIP application 33, and other applications 34 including a browser, a mail application, and the like.

  The LCD 7 converts display information into a video signal under the control of the CPU 11 and displays various information corresponding to the converted video signal on the display screen.

  In this embodiment, an LCD is used as a display. However, the present invention is not limited to this, and another display such as an organic EL display or a CRT may be used.

  The input unit 4 is a user interface for a user to perform an input operation, and includes a keyboard composed of various keys for inputting characters, commands, etc., a touch pad for moving a cursor on the screen, and selecting various menus. Etc.

  The camera device 15 includes a camera 8 and a camera processing circuit 16. The camera 8 includes a lens and an imaging unit (CCD or CMOS). The lens forms subject light, and the imaging unit outputs the imaged subject light as R, G, and B image signals. The camera processing circuit 16 includes an A / D converter, an image processing LSI, a memory, and the like. The camera processing circuit 16 performs drive timing and exposure control of the imaging unit, and performs data processing (A / D conversion, etc.) and output to the CPU 11.

  The audio device 17 includes microphones 5a and 5b, speakers 6a and 6b, and an audio processing circuit 18. The microphones 5 a and 5 b collect sound and output sound data to the sound processing circuit 18. The speakers 6 a and 6 b output sound corresponding to the sound data output from the sound processing circuit 18. The audio processing circuit 18 includes an A / D converter, a D / A converter, an amplifier, an audio processing LSI including various filters, a memory, and the like, and receives audio input from the microphones 5a and 5b. Audio processing is performed after A / D conversion, and audio data (digital data) after audio processing is output to the CPU 11, or audio data (digital) input from the CPU 11 is audio processed after A / D conversion, and audio The processed audio data is D / A converted and output from the speakers 6a and 6b.

  The communication device 19 is for transmitting and receiving data via a network, and transmits image data and audio data to the network, and receives image data and audio data transmitted via the network.

  The AC adapter 23 is connected to a commercial power supply, converts an AC voltage into a DC voltage, and outputs the DC voltage to the DC-DC converter 22. The DC-DC converter 22 converts the DC voltage supplied from the AC adapter 23 into a predetermined voltage, supplies power to each unit, and charges the battery 21. The battery 21 is charged by the DC-DC converter 22 and supplies the charged voltage to each unit. The battery 21 is used when the AC adapter 23 is not connected to a commercial power source.

  FIG. 3 is a schematic functional configuration diagram related to audio input / output of the notebook PC 1 of FIG. FIG. 4 is an explanatory diagram for explaining a private mode (beam forming), a conference mode (Far Field Pick up), and a multi-angle mode.

  In FIG. 3, the OS 30 installed in the storage 14, the driver 31 including the audio driver 31a, the voice assistant application 32, the VOIP application 33 (Skype (registered trademark), Windows (registered trademark) Live messenger), and other applications 34 are as follows: It is read into the memory 13 and executed by the CPU 11. The OS 30 intervenes in transmission / reception of data or commands between each application and driver.

  The OS 30 controls basic operations of the notebook PC 1, manages various resources, and transmits, for example, instructions generated by application programs to the driver 31 and the BIOS 12a. The OS 30 has a multi-task function and a multi-window function, and is an application program execution context (a register set used by a certain application program, a main memory image, a file handle, etc.) and a software resource such as a GUI component. Management is also done. The OS 30 performs low power consumption control of the notebook PC 1, and when the notebook PC 1 enters an idle state from a normal state (when no user operation is performed for a predetermined period), the OS 30 shifts to a standby (sleep) or hibernation state. When a user operation is performed in the standby (sleep) or hibernation state, the normal state is restored.

  The audio driver 31a functions as a mode setting unit that sets the use mode of the microphones 5a and 5b, and controls the audio device 17 in accordance with an instruction from the OS 30. The audio driver 31a selects one of the first mode having directivity and the second mode having no directivity as the use mode of the microphones 5a and 5b based on the state of the notebook PC 1 and surrounding sounds. Set to device 17. The first mode is, for example, a private mode (beam forming mode). The second mode is, for example, a conference mode (Far Field Pick up) and a multi-angle mode.

  As shown in FIG. 4A, the private mode is a mode in which the directivities of the microphones 5a and 5b are increased. Of the sounds input from the microphones 5a and 5b, the private mode is used for the notebook PC 1 (the microphones 5a and 5b). This is a mode for performing beam forming processing for extracting only the sound in the front direction. The private mode is suitable when the user uses the voice assistant application 32 or the VOIP application 33 while sitting in front of the notebook PC 1.

  In the multi-angle mode, as shown in FIG. 4 (B), the sound in all directions is collected with respect to the notebook PC 1 and the loudest sound is extracted from the collected sounds without performing beam forming processing. This is the mode for processing. The multi-angle mode is suitable, for example, when the user uses the voice assistant application 32 from a slightly distant place, and can recognize the user's voice even if the user is not in front of the notebook PC 1.

  In the conference mode, as shown in FIG. 4C, the sensitivity of the microphones 5a and 5b is set higher than that in the private mode and the multi-angle mode without performing beam forming processing, and sound in all directions with respect to the notebook PC 1 is set. Is a mode to collect sound in a wide range. The conference mode can be preferably used even when the user uses the voice assistant application 32 from a remote location, and the user can recognize the voice even when the user is not in front of the notebook PC 1.

  The voice assistant application 32 is an application executed on the OS 30, and recognizes voice data input through the microphones 5a and 5b and the voice processing circuit 18 to interpret the user's utterance content (included in the utterance content). Utterance commands are extracted and the utterance contents are interpreted), and various operations instructed by voice are instructed to be executed by another application 34 or the like (for example, the browser application is searched for the search) Voice the results or send an email to the email app). The voice assistant application 32 can be activated by voice input of a user's predetermined activation utterance command (for example, hello, OO), pressing of an icon (not shown) of the voice assistant application 32 displayed on the LCD 7, or the like. The voice assistant application 32 may be configured by a client-server system. For example, the voice assistant application 32 sends voice data to the server, and the server interprets the content of the user's utterance and the result. You may reply to the voice assistant application 32.

  The VOIP application 33 is an application executed on the OS 30 and is used for making a call with an opponent terminal using an image and voice. In addition, the VOIP application 33 causes the communication device 19 to establish a link with the counterpart terminal via the OS 30 to transmit an image captured by the camera 8 or sound collected by the microphones 5a and 5b, or to be transmitted from the counterpart terminal. The incoming image and sound are displayed on the LCD 7 and output from the speakers 6a and 6b.

  When the private mode is set, the audio processing circuit 18 of the audio device 17 performs beam forming processing that extracts only the sound in the front direction (predetermined direction) from the sounds input from the microphones 5a and 5b. Further, when the conference mode is set, the audio processing circuit 18 does not perform the beam forming process, sets the sensitivity of the microphones 5a and 5b high (sets the gain of the amplifier high), and moves far away. Performs processing to collect sound. Further, when the multi-angle mode is set, the audio device 17 performs a process of extracting the loudest sound from the sounds input from the microphones 5a and 5b without performing the beam forming process.

  FIG. 5 is a flowchart for explaining an example of processing for switching the use mode of the microphones 5a and 5b in accordance with the state of the notebook PC 1 and surrounding sounds. In the following description, the case where the conference mode is used as the second mode will be described, but the multi-angle mode may be used.

  In FIG. 5, first, when the notebook PC 1 is powered on, the audio driver 31a sets the private mode (step S1). That is, the audio driver 31a sets the private mode by default. Since the user usually uses the notebook PC 1 while sitting in front of the user, by default, the private mode is set and voices from the front of the notebook PC 1 are set with the microphones 5a and 5b (audio device 17). It is desirable to collect sound.

  Next, the audio driver 31a determines whether or not the notebook PC 1 is in an idle state (a state in which no user operation is performed for a predetermined period) (step S2). As described above, when the notebook PC 1 is in an idle state, the OS 30 shifts to a standby (sleep) or hibernation state to reduce power consumption. The OS 30 may be in a state in which the voice assistant application 32 can be activated by supplying power to the audio device 17 to enable voice input even when the OS 30 enters the standby (sleep) or hibernation state.

  If the audio driver 31a is in the idle state (“Yes” in step S2), the audio driver 31a sets the conference mode (step S3). In the idle state, since it is assumed that the user is away from the desk, the conference mode is set, and sounds from all directions of the notebook PC 1 are collected by the microphones 5a and 5b (audio device 17). Is desirable.

  Next, the audio driver 31a checks surrounding sounds via the audio device 17 (step S4). If there are a plurality of noise sources, the process returns to step S1 to set the private mode. This is because when there are multiple noise sources (when the surroundings are noisy), there is a risk of misrecognizing the user's voice in the conference mode. is there.

  In step S4, when there is only one noise source (for example, TV, stereo, etc.), the audio driver 31a maintains the conference mode and sets the volume of the speakers 6a and 6b to be larger than the volume of the noise source. (Step S5), the process proceeds to step S6. This is to make it easier for the user to hear the voice guidance from the voice assistant application 32. In step S4, when there is no noise source (silent), the process proceeds to step S6.

  In step S6, the voice assistant application 32 waits for the voice input of the user's utterance command (step S6). For example, the voice assistant application 32 starts an operation when a user's predetermined activation utterance command (for example, hello, OO) is input, interprets the content of the subsequent user's utterance, and is instructed by voice. The operation content may be executed. Thereby, when the user uses the voice assistant application 32 at a location away from the notebook PC 1, the user can preferably use the voice assistant application 32 without erroneously recognizing the voice even if the user is not in front of the notebook PC 1. In addition, when there is one noise source or silent, it is not an environment where there are many people in the surroundings, so the user is not shy and does not bother others, and from a distance from the notebook PC 1 The voice assistant application 32 can be used. In the conference mode, when there is no noise source, the user's voice is not erroneously recognized, and even when there is only one noise source, if the user speaks with a voice higher than the noise source, the voice is erroneously recognized. Can be prevented.

  Next, the audio driver 31a determines whether or not the notebook PC 1 is in an idle state (step S7). If it is in the idle state (“Yes” in step S7), the process returns to step S4. If it is not in the idle state (“No” in step S7), that is, if the notebook PC 1 is operated, the process returns to step S1 and returns to the private mode.

  As described above, according to the present embodiment, based on the state of the notebook PC 1 and surrounding sounds, the first mode having directivity and the directivity are not used as the use modes of the plurality of microphones 5a and 5b. An audio driver 31a that selects and sets one of the second modes, an audio device 17 that performs signal processing on sounds input from the plurality of microphones 5a and 5b according to the mode set by the audio driver 31a, And a voice assistant application 32 that performs voice assist by recognizing the sound signal-processed by the audio device 17. Therefore, when the voice assistant is used, information that is easy to use according to the use environment of the user. A processing device can be provided.

  In addition, since the first mode is a private mode in which beam forming processing for extracting only the sound in the front direction from the sound input from the plurality of microphones 5a and 5b is performed with respect to the notebook PC 1, When the voice assistant application 32 is used while sitting in front of the PC 1, it is possible to perform voice recognition suitably.

  In addition, the second mode is a conference mode in which the sensitivity of the plurality of microphones 5a and 5b is set higher than that in the first mode, and the sound is collected in a wide range with respect to the notebook PC 1 in a wide range. Even when the user uses the voice assistant application 32 at a location away from the notebook PC 1, the user can use the voice assistant application 32 without being in front of the notebook PC 1.

  In addition, since the second mode is a multi-angle mode in which sound is collected in all directions with respect to the notebook PC and processing for extracting the loudest sound among the collected sounds is performed, Even when the voice assistant application 32 is used at a location slightly away from the notebook PC 1, it can be suitably used without being in front of the notebook PC 1.

  The audio driver 31a sets the second mode when the notebook PC 1 is in an idle state when the first mode is set, so that the user leaves the notebook PC 1. The voice assistant application 32 can be preferably used even at a place.

  Also, the audio driver 31a sets the first mode when the second mode is set and there are a plurality of surrounding sound sources. Recognition can be prevented.

  Also, when the second mode is set and the surrounding sound source is one, the audio driver 31a maintains the second mode and sets the volume of the speakers 6a and 6b to be larger than that of the sound source. Since the voice assistant application 32 waits for the voice input of the utterance command from the user, the voice assistant application 32 can perform voice guidance with a voice larger than that of the surrounding sound source.

  Further, when the second mode is set and the surroundings are silent, the audio driver 31 maintains the second mode, and the voice assistant application 32 waits for the voice input of the utterance command from the user. Therefore, when the user uses the voice assistant application 32 at a location away from the notebook PC 1, the user can use the voice assistant application 32 without erroneously recognizing the voice even if the user is not in front of the notebook PC 1.

  In the above embodiment, the case where the present invention is applied to a notebook PC has been described. However, the present invention is not limited to this, and the present invention is applied to information processing apparatuses such as a smartphone, a tablet, a mobile phone, a PDA, and a desktop PC. Is also applicable.

  In the above embodiment, the voice recognition is performed by the voice assistant application 32. However, the voice recognition may be performed by the audio device 17, the audio driver 31a, and / or the OS 30.

  Also, some or all of the functions of the audio processing circuit 18 of the audio device 17 may be performed by software.

  The audio driver 31a may switch between the conference mode and the multi-angle mode in the second mode according to the distance between the notebook PC 1 and the user. For example, the distance between the notebook PC 1 and the user may be changed. When it is smaller than the threshold value, the multi-angle mode may be set, and when it is equal to or larger than the threshold value, the conference mode may be set.

  Further, although the audio driver 31a sets the use mode of the microphones 5a and 5b, the OS 30 and / or the voice assistant application 32 may set them.

1 Notebook PC
2 Main Body Side Housing 3 Display Side Housing 4 Input Unit 5a, 5b Microphone 6a, 6b Speaker 7 LCD (Liquid Crystal Display)
8 Camera 9a, 9b Connecting part (hinge part)
11 CPU
12 ROM
13 Memory 14 Storage 15 Camera Device 16 Camera Processing Circuit 17 Audio Device 18 Audio Processing Circuit 19 Communication Device 21 Battery 22 DC-DC Converter 23 AC Adapter 30 OS
31 Driver 31a Audio Driver 32 Voice Assistant Application 33 VOIP Application 34 Other Applications

Claims (12)

An information processing apparatus having a plurality of microphones,
Mode setting for selecting and setting one of the first mode having directivity and the second mode having no directivity as the use mode of the plurality of microphones based on the state of the information processing apparatus and surrounding sounds Means,
Sound processing means for performing signal processing on sound input from the plurality of microphones according to the mode set by the mode setting means;
A voice assistant means for performing voice assist by recognizing the sound signal-processed by the voice processing means;
An information processing apparatus comprising:   The mode setting means sets the second mode when the information processing apparatus is in an idle state when the first mode is set. The information processing apparatus described.   The mode setting means sets the first mode when the second mode is set and there are a plurality of surrounding sound sources. Information processing device. When the second mode is set and the surrounding sound source is one, the mode setting means maintains the second mode and sets the volume of the speaker to be larger than the sound source,
The information processing apparatus according to claim 1, wherein the voice assistant unit waits for a voice input of an utterance command from a user. The mode setting means maintains the second mode when the second mode is set and the surroundings are silent,
The information processing apparatus according to claim 1, wherein the voice assistant unit waits for a voice input of an utterance command from a user.   2. The mode according to claim 1, wherein the first mode is a mode in which beam forming processing is performed to extract only sound in a front direction from the information inputted from the plurality of microphones. The information processing apparatus according to any one of claims 5 to 6.   The second mode is a mode in which sensitivity of the plurality of microphones is set higher than that in the first mode, and sound in all directions is collected over a wide range with respect to the information processing apparatus. The information processing apparatus according to any one of claims 1 to 6.   The second mode is a mode in which the information processing apparatus collects sounds in all directions and performs a process of extracting the loudest sound among the collected sounds. The information processing apparatus according to any one of claims 6 to 6.   The information processing apparatus according to claim 1, wherein the mode setting unit sets the first mode by default.   The information processing apparatus according to claim 1, wherein the information processing apparatus is a notebook PC. A method of using a microphone of an information processing apparatus including a plurality of microphones,
Mode setting for selecting and setting one of the first mode having directivity and the second mode having no directivity as the use mode of the plurality of microphones based on the state of the information processing apparatus and surrounding sounds Process,
An audio processing step for performing signal processing on sound input from the plurality of microphones according to the mode set in the mode setting step;
A voice assistant step of performing voice assist by recognizing the sound signal-processed in the voice processing step;
A method of using a microphone, comprising: A program installed in an information processing apparatus having a plurality of microphones,
Mode setting for selecting and setting one of the first mode having directivity and the second mode having no directivity as the use mode of the plurality of microphones based on the state of the information processing apparatus and surrounding sounds Process,
An audio processing step for performing signal processing on sound input from the plurality of microphones according to the mode set in the mode setting step;
A voice assistant step of performing voice assist by recognizing the sound signal-processed in the voice processing step;
A computer-executable program characterized by causing a computer to execute.