Voice control system, voice control method, and program

Abstract

An audio control system (1) comprises: an acquisition unit (110) that acquires sound data indicating a sound picked up by a microphone (12) disposed in a second space (202) around a first space (201) used by a person; a storage unit (130) in which sound source data is stored; and a control unit (120) whereby a speaker device (30) disposed in the first space (201) or the second space (202) is controlled so that audio obtained from the sound source data is played back louder in the second space (202) than in the first space (201). The control unit (120) identifies the loudness of the sound indicated by the acquired sound data and performs an adjustment so that the volume of the audio output from the speaker device (30) is reduced in proportion to the loudness of the identified sound.

Description

[Technical Field]

[0001] The present disclosure relates to a voice control system, a voice control method, and a program. [Background technology]

[0002] Patent Document 1 discloses a method for preventing overhearing of private conversations in public spaces, specifically by adapting the degree of sound masking to suit the social situation of people in the public space. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2011-528445 Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a voice control system and the like that can efficiently mask sounds generated in a space used by people. [Means for solving the problem]

[0005] A voice control system according to one embodiment of the present disclosure includes an acquisition unit that acquires sound data indicating sound picked up by a microphone placed in a second space surrounding a first space used by a person, a memory unit that stores sound source data, and a control unit that controls one or more speakers placed in the first space or the second space so that the sound obtained from the sound source data is played louder in the second space than in the first space, and the control unit identifies the volume of the sound indicated by the acquired sound data and adjusts the volume of the sound output from the one or more speakers so that the louder the identified volume of the sound is, the lower the volume is.

[0006] Also, an audio control system according to another aspect of the present disclosure includes an acquisition unit that acquires number information regarding the number of people present in a second space around a first space used by a person, a storage unit that stores sound source data, and a control unit that controls one or more speakers arranged in the first space or the second space so that the sound obtained from the sound source data is reproduced louder in the second space than in the first space. The control unit adjusts the volume of the sound output from the one or more speakers to be smaller as the number of people obtained from the acquired number information is larger.

[0007] Also, an audio control method according to one aspect of the present disclosure acquires sound data indicating sound picked up by a microphone arranged in a second space around a first space used by a person, controls one or more speakers arranged in the first space or the second space so that the sound obtained from the sound source data stored in a storage device is reproduced louder in the second space than in the first space, identifies the loudness of the sound indicated by the acquired sound data, and adjusts the volume of the sound output from the one or more speakers to be smaller as the identified loudness of the sound is larger.

[0008] Also, an audio control method according to another aspect of the present disclosure acquires number information regarding the number of people present in a second space around a first space used by a person, controls one or more speakers arranged in the first space or the second space so that the sound obtained from the sound source data stored in a storage device is reproduced louder in the second space than in the first space, and adjusts the volume of the sound output from the one or more speakers to be smaller as the number of people obtained from the acquired number information is larger.

[0009] Note that these general or specific aspects may be implemented by an apparatus, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or may be implemented by any combination of an apparatus, an integrated circuit, a computer program, and a non-transitory recording medium.

Effects of the Invention

[0010] An audio control system or the like in the present disclosure can efficiently mask sounds generated in the space where a person is using.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

DETAILED DESCRIPTION OF THE INVENTION

[0012] A voice control system according to an aspect of the present disclosure includes an acquisition unit that acquires sound data indicating sound collected by a microphone disposed in a second space around a first space used by a person, a storage unit that stores sound source data, and a control unit that controls one or more speakers disposed in the first space or the second space so that the sound obtained from the sound source data is reproduced louder in the second space than in the first space. The control unit specifies the loudness of the sound indicated by the acquired sound data, and adjusts so that the louder the specified loudness of the sound, the smaller the volume of the sound output from the one or more speakers.

[0013] According to this, the louder the sound collected by the microphone in the second space, the smaller the volume of the sound for masking the sound generated in the first space is adjusted. Therefore, the sound generated in the first space can be efficiently masked. Thus, since the louder the sound in the second space, the more the power consumption required for masking can be reduced, the power consumption required for masking the sound generated in the first space can be reduced.

[0014] Also, an audio control system according to another aspect of the present disclosure includes an acquisition unit that acquires population information regarding the number of people in a second space surrounding a first space used by a person, a storage unit that stores sound source data, and a control unit that controls one or more speakers arranged in the first space or the second space so that the sound obtained from the sound source data is reproduced louder in the second space than in the first space. The control unit adjusts so that the louder the number of people obtained from the acquired population information, the lower the volume of the sound output from the one or more speakers.

[0015] According to this, the larger the number of people in the second space, the volume of the sound for masking the sound generated in the first space is adjusted to be smaller, so that the sound generated in the first space can be efficiently masked. Therefore, since the power consumption required for masking can be reduced as the number of people in the second space increases, the power consumption required for masking the sound generated in the first space can be reduced.

[0016] Also, the population information may include a first detection result by one or more human sensors that target the second space for detection, and the control unit may specify the number of people present in the second space based on the first detection result.

[0017] Also, the population information is a planned action of one or more people and includes a planned action to use the second space. The control unit may specify the number of people who have a planned use of the second space currently based on the planned action included in the population information by counting the number of people.

[0018] Also, the acquisition unit further acquires presence / absence information regarding the presence or absence of a person in the first space. When the control unit specifies that no person is present in the first space based on the presence / absence information, the control unit may not output the sound from the speaker.

[0019] According to this, when there is no person in the first space, since the voice is not output toward the second space, power consumption can be reduced.

[0020] Further, the presence / absence information includes a second detection result by a human presence sensor that detects the first space, and when the second detection result indicates that there is no person in the first space, the control unit may not output the voice from the speaker.

[0021] Further, the presence / absence information is the action plan of one or more persons and includes an action plan to use the first space. When the control unit specifies that there is no current usage plan for the first space based on the action plan of the one or more persons included in the presence / absence information, the control unit may not output the voice from the speaker.

[0022] Further, the acquisition unit acquires sound data indicating the sound collected by a microphone that collects sound in the second space, and the control unit stores the sound data as the sound source data in the storage unit, and may generate the voice output from the one or more speakers using the sound source data stored in the storage unit.

[0023] According to this, in order to generate the voice output from one or more speakers using the collected sound as the sound source, it is possible to output a masking sound with less discomfort given to people.

[0024] Further, the acquisition unit acquires first sound data indicating the sound collected by the microphone in the first time period and second sound data indicating the sound collected by the microphone in the second time period. The control unit stores the first sound data and the second sound data as the sound source data in the storage unit, generates the voice output from the one or more speakers in the first time period using the first sound data, and generates the voice output from the one or more speakers in the second time period using the second sound data.

[0025] According to this, since the sound picked up for each time zone is used as the sound source of the voice output in that time zone, it is possible to output masking sound that gives less discomfort to people according to the time zone.

[0026] In addition, the acquisition unit acquires space information for specifying the first space from among a plurality of spaces including the first space and the second space, and the control unit sets each of the plurality of spaces as either the first space or the second space based on the space information, and controls the one or more speakers so that the voice is reproduced louder in one or more spaces set as the second space than in one or more spaces set as the first space among the plurality of spaces.

[0027] According to this, even when the first space and the second space are dynamically set, as the sound volume in the second space is larger, the volume of the voice for masking the sound generated in the first space used by the person is adjusted to be smaller. For this reason, the sound generated in the first space can be efficiently masked.

[0028] In addition, a voice control method according to an aspect of the present disclosure acquires sound data indicating sound picked up by a microphone arranged in a second space around a first space used by a person, and controls one or more speakers arranged in the first space or the second space so that the voice obtained from the sound source data stored in the storage device is reproduced louder in the second space than in the first space, specifies the volume of the sound indicated by the acquired sound data, and adjusts the volume of the voice output from the one or more speakers to be smaller as the specified volume of the sound is larger.

[0029] According to this, the greater the magnitude of the sound picked up by the microphone in the second space, the more the volume of the voice for masking the sound generated in the first space is adjusted to be smaller. Therefore, the sound generated in the first space can be efficiently masked. Thus, since the greater the magnitude of the sound in the second space, the more the power consumption required for masking can be reduced, the power consumption required for masking the sound generated in the first space can be reduced.

[0030] Moreover, the voice control method according to another aspect of the present disclosure acquires number information regarding the number of people present in a second space around a first space used by a person, and controls one or more speakers arranged in the first space or the second space so that the voice obtained from the sound source data stored in the storage device is reproduced louder in the second space than in the first space. The greater the number of people obtained based on the acquired number information, the more the volume of the voice output from the one or more speakers is adjusted to be smaller.

[0031] According to this, the greater the number of people present in the second space, the more the volume of the voice for masking the sound generated in the first space is adjusted to be smaller. Therefore, the sound generated in the first space can be efficiently masked. Thus, since the greater the number of people in the second space, the more the power consumption required for masking can be reduced, the power consumption required for masking the sound generated in the first space can be reduced.

[0032] Note that these general or specific aspects may be implemented by an apparatus, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or may be implemented by any combination of an apparatus, an integrated circuit, a computer program, and a non-transitory recording medium.

[0033] Hereinafter, embodiments will be described in detail with reference to the drawings as appropriate. However, detailed descriptions that are more than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted. This is to avoid making the following description unnecessarily redundant and to facilitate the understanding of those skilled in the art.

[0034] Note that the inventors provide the accompanying drawings and the following description for those skilled in the art to fully understand the present disclosure, and do not intend to limit the subject matter described in the claims thereby.

[0035] (Embodiment) [1. Configuration] FIG. 1 is a diagram for explaining a space to which the voice control system according to the embodiment is applied. FIG. 2 is a diagram showing a usage example of the voice control system according to the embodiment. Note that FIG. 2 includes a schematic view of the space in which the voice control system is used as seen from above.

[0036] FIGS. 1 and 2 show a first space 201 surrounded by a wall 301 and a second space 202 around the first space 201. At the boundary between the first space 201 and the second space 202, a speaker device 30 is arranged facing the second space 202. The first space 201 is a space used, for example, as a meeting space. The second space 202 is a space such as a lobby used, for example, for people to come and go or take a temporary break.

[0037] FIG. 2 shows a voice control system 1 including a voice control device 100, microphones 11 and 12, human sensors 21 and 22, and a speaker device 30. Also, in FIG. 2, it is shown that the voice control device 100 and the server 40 are communicably connected to each other via a network 50.

[0038] The microphone 11 is disposed in the first space 201 and detects the sound generated within the first space 201. The microphone 11 is disposed, for example, on the ceiling of the first space 201. Note that the microphone 11 is not limited to being disposed on the ceiling of the first space 201 as long as it can detect the sound generated in the first space 201, and it may be disposed on the surface of the wall 301 on the first space 201 side, on the floor of the first space 201, or on a desk disposed in the first space 201. That is, the microphone 11 may be disposed anywhere as long as it is disposed on a structure within the first space 201.

[0039] The microphone 12 is disposed in the second space 202 and detects the sound generated within the second space 202. The microphone 12 is disposed, for example, on the ceiling of the second space 202. Note that the microphone 12 is not limited to being disposed on the ceiling of the second space 202 as long as it can detect the sound generated in the second space 202, and it may be disposed on the surface of the wall 301 on the second space 202 side, on the floor of the second space 202, or on a desk disposed in the second space 202. That is, the microphone 12 may be disposed anywhere as long as it is disposed on a structure within the second space 202.

[0040] The human presence sensor 21 is disposed in the first space 201 and detects the presence of a person within the first space 201. That is, the human presence sensor 21 targets the first space 201 for detection. The human presence sensor 21 outputs, for example, infrared rays, ultrasonic waves, visible light, etc., and detects the reflected waves of the output infrared rays, ultrasonic waves, visible light, etc. by a person to detect the presence of a person. The human presence sensor 21 is disposed, for example, on the ceiling of the first space 201. Note that the human presence sensor 21 is not limited to being disposed on the ceiling of the first space 201 as long as it can detect the presence of a person within the first space 201, and it may be disposed on the surface of the wall 301 on the first space 201 side.

[0041] The human presence sensor 22 is disposed in the second space 202 and detects the presence of people in the second space 202. That is, the human presence sensor 22 targets the second space 202 for detection. The human presence sensor 22 may be capable of detecting the presence of a plurality of people, and may also detect the number of one or more people present in the second space 202. The human presence sensor 22 is, for example, disposed on the ceiling of the second space 202, outputs infrared rays, visible light, etc., and detects reflected waves of the output infrared rays, visible light, etc. by people, thereby generating, as a detection result, a two-dimensional image showing the distribution of the received light intensity of infrared rays, visible light, etc. on the plane when viewed from above. Further, the human presence sensor 22 may analyze the two-dimensional image obtained as the detection result to identify the number of people, and generate the identified number of people as the detection result. In this way, the human presence sensor 22 may be an image-type human presence sensor that detects the position and number of people on the plane from the two-dimensional image. Note that the human presence sensor 22 is not limited to being disposed on the ceiling of the second space 202 as long as it can detect the presence of people in the second space 202, and may be disposed on the surface of the wall 301 on the side of the second space 202. When disposed on the wall 301, it may be disposed at a position close to the ceiling at the upper part of the wall 301 in order to easily detect all one or more people present in the second space 202.

[0042] The speaker device 30 outputs, toward the second space 202, a voice (masking sound) for making the sound generated in the first space 201 inaudible to people present in the second space 202. Here, the sound generated in the first space 201 is, for example, the sound from the conversation of the user using the first space 201. The conversation of the user using the first space 201 may be a conversation between a plurality of users using the first space 201, or may be a conversation by a voice call using a communication terminal conducted between the user using the first space 201 and a user outside the first space 201. The speaker device 30 includes, for example, one speaker unit and an amplifier, amplifies the input voice signal by the amplifier, and outputs the amplified voice signal as sound from the speaker unit. Note that the speaker device 30 may include a speaker array composed of a plurality of speaker units arranged in a specific direction, and may be capable of controlling the directivity in a specific direction.

[0043] Note that the positions or orientations of the microphones 11 and 12 and the speaker device 30 may be adjusted so that it is difficult for the microphones 11 and 12 to pick up the sound output from the speaker device 30, or the volume of the speaker device 30 or the sensitivities of the microphones 11 and 12 may be adjusted.

[0044] The server 40 receives a reservation for using the first space 201 or the second space 202 from the user and manages the reservation. Specifically, the server 40 receives reservation requests 401 and 402 as shown in, for example, FIG. 3 from a user's terminal (not shown), and stores the received reservation requests 401 and 402 as reservation information 400. FIG. 3 is a diagram showing an example of the reservation information according to the embodiment.

[0045] Each of the reservation requests 401 and 402 included in the reservation information 400 includes, as shown in FIG. 3, space identification information for identifying the space to be used, time zone information indicating the time zone of the day (i.e., a specific day) when the space is to be used, and user information indicating the user who is scheduled to use the space. The space identification information may be any information that can identify the space, such as the name of the space or a space ID for identifying the space. The user information includes a user ID for identifying the user who reserved the space. The user information may include the user IDs of all the users who are scheduled to use the space, or may include the number of users who are scheduled to use the space. The server 40 stores the received reservation request in a storage unit (storage) provided in the server 40. The server 40 accepts a new reservation request so as not to overlap with the space and time zone for which a reservation has already been made. Note that the reservation for using the space can also be referred to as the user's planned action because it indicates the user's plan to use the reserved space.

[0046] The voice control device 100 acquires the detection results from the microphones 11 and 12 and the human presence sensors 21 and 22, and controls the voice output from the speaker device 30 according to the acquired detection results. Further, the voice control device 100 acquires information from the server 40, and controls the voice output from the speaker device 30 according to the acquired information.

[0047] Next, the specific configuration of the voice control device 100 will be described.

[0048] FIG. 4 is a block diagram showing an example of the hardware configuration of the voice control device according to the embodiment.

[0049] As shown in FIG. 4, the voice control device 100 includes, as a hardware configuration, a processor 101, a main memory 102, a storage 103, and a communication IF (Interface) 104. The voice control device 100 may further include an input IF (Interface) 105 and a display 106.

[0050] The processor 101 is a processor that executes a program stored in the storage 103 or the like.

[0051] The main memory 102 is a volatile storage area that is used to temporarily store data generated in the process of processing by the processor 101, used as a work area when the processor 101 executes a program, or used to temporarily store data received by the communication IF 104. The data generated in the process of processing by the processor 101 includes, for example, voice data indicating the voice generated by the processor 101. The data received by the communication IF 104 includes, for example, voice data acquired from the microphones 11 and 12, detection results acquired from the human presence sensors 21 and 22, and the like.

[0052] Storage 103 is a non-volatile memory area that holds various data such as programs. Storage 103 stores, for example, various data generated as a result of processing by processor 101, audio data received by communication IF 104, or data including detection results. Also, storage 103 stores sound source data. Storage 103 may store the sound source data received by communication IF 104.

[0053] Communication IF 104 is a communication interface for data transmission between the external devices such as smartphones, tablets, PCs (Personal Computers), and server 40. Communication IF 104 may be, for example, an interface for wireless communication such as a wireless LAN interface or a Bluetooth (registered trademark) interface. Communication IF 104 may be an interface for wired communication such as USB (Universal Serial Bus) or a wired LAN interface. Note that communication IF 104 is not limited to the above and may be a communication interface for data transmission between external devices via a communication network. Communication IF 104 receives, for example, audio data from microphones 11 and 12 and detection results from human presence sensors 21 and 22.

[0054] Input IF 105 is an interface for receiving input from a person. Input IF 105 may be a pointing device such as a mouse, touch pad, touch panel, trackball, or a keyboard.

[0055] Display 106 is a liquid crystal display, an organic EL display, or the like.

[0056] FIG. 5 is a block diagram showing an example of the functional configuration of the voice control device according to the embodiment.

[0057] As shown in FIG. 5, the voice control device 100 includes an acquisition unit 110, a control unit 120, and a storage unit 130.

[0058] The acquisition unit 110 acquires volume information regarding the loudness of sound in the second space 202. The acquisition unit 110 sequentially acquires the volume information. The volume information is information used to specify the loudness of sound in the second space 202. The acquisition unit 110 is realized by, for example, the communication IF 104 or the like.

[0059] The control unit 120 generates sound for masking the sound generated in the first space 201 from the sound source data stored in the storage unit 130. The control unit 120 controls the speaker device 30 so that the generated sound is reproduced louder in the second space 202 than in the first space 201. In the present embodiment, since the speaker device 30 is arranged facing the second space 202, if the control unit 120 performs control to output the sound to the speaker device 30, the loudness of the sound will be greater in the second space 202 than in the first space 201.

[0060] Further, the control unit 120 adjusts so that the louder the loudness of the sound in the second space 202 obtained based on the acquired volume information, the smaller the volume of the sound output from the speaker device 30. The control unit 120 sequentially processes the volume information sequentially acquired by the acquisition unit 110. That is, the control unit 120 adjusts the volume of the sound output from the speaker device 30 in real time using the volume information obtained in real time.

[0061] Note that the volume information may indicate an index value in an index regarding the loudness of sound in the second space 202. The volume information may indicate that the louder the sound in the second space 202, the larger the index value. The volume information may be, for example, a measurement result obtained by directly measuring the loudness of sound in the second space 202, or may indicate an index value in another measurement index having a correlation with the loudness of sound. Thus, when the volume information indicates an index value in an index regarding the loudness of sound in the second space 202, the control unit 120 adjusts so that the larger the volume information, the smaller the volume of the sound output from the speaker device 30.

[0062] The control unit 120 is realized, for example, by the processor 101 executing a program stored in the storage 103 using the main memory 102.

[0063] The storage unit 130 stores sound source data. The sound source data is used by the control unit 120 to generate the sound output from the speaker device 30. The sound source data may be pre-prepared sound source data. The pre-prepared sound source data may be, for example, environmental sounds pre-recorded in nature, in the city, around roads, etc., or colored noise including white noise. Also, the pre-prepared sound source data may be sound data indicating sound pre-recorded by the microphone 12. The storage unit 130 is realized, for example, by the storage 103.

[0064] Note that the sound source data does not have to be pre-prepared sound source data, and may be sound source data acquired by the acquisition unit 110 from an external device via the network 50. The sound source data acquired by the acquisition unit 110 from an external device is stored in the storage unit 130.

[0065] <Volume information, and control according to volume information> Here, specific examples of volume information and specific control examples by the control unit 120 for each specific example of volume information will be described.

[0066] (First example) The first example of volume information is sound data indicating sound picked up by the microphone 12 arranged in the second space 202. That is, the acquisition unit 110 acquires sound data from the microphone 12 as volume information. Then, the control unit 120 analyzes the sound data to identify the loudness of the sound indicated by the sound data, and adjusts so that the louder the identified loudness of the sound, the lower the volume of the sound output from the speaker device 30.

[0067] The loudness of the sound indicated by the sound data may be, for example, the amplitude at the peak of the audio waveform within a predetermined period of the sound data. When there are multiple peaks within the predetermined period, the loudness of the sound indicated by the sound data may be the maximum value of the amplitudes of the multiple peaks, or may be the average value. This predetermined period is, for example, the period from a time that is a predetermined time before the current time (the latest time) to the current time. The predetermined period indicates a time interval and may be, for example, a time of 100 seconds or less. Also, the loudness of the sound indicated by the sound data may be the amplitude at the current time of the envelope line that connects multiple peaks of the audio waveform of the sound data in contact with each other, or may be the maximum value within a predetermined period, or may be the average value.

[0068] Note that the loudness of the sound indicated by the sound data may be specified by a measuring device separate from the voice control device 100. This measuring device is a device that measures the loudness of the sound of the sound data obtained by the microphone 12. In this case, the volume information is information indicating the loudness of the sound in the second space 202 measured by the measuring device. That is, the acquisition unit 110 may acquire information indicating the loudness as the volume information from the measuring device. Then, the control unit 120 may adjust so that the volume of the sound output from the speaker device 30 becomes smaller as the loudness indicated by the information indicating the loudness is larger.

[0069] (Second example) The second example of the volume information is the number of people information including the detection result by the presence sensor 22 arranged in the second space 202. That is, the acquisition unit 110 acquires the number of people information from the presence sensor 22 as the volume information. Then, the control unit 120 adjusts so that the volume of the sound output from the speaker device 30 becomes smaller as the number of people obtained from the detection result by the presence sensor 22 included in the number of people information is larger.

[0070] The number information may be a two-dimensional image showing the distribution of received light intensities such as infrared rays and visible light on a plane, or may be information indicating the number of people identified by analyzing the two-dimensional image. When the number information is a two-dimensional image, the control unit 120 identifies the number of people by analyzing the two-dimensional image. For example, the control unit 120 may identify the number of people by counting the set of pixels that satisfy a predetermined condition. The predetermined condition is, for example, that in the case of an infrared image, the number of pixels in the set of pixels having a pixel value corresponding to the body temperature of a person is within the range of the number of pixels corresponding to the area where one person appears. Also, for example, the control unit 120 may identify the number of people in the two-dimensional image using a machine learning model. The machine learning model is, for example, a model for identifying the number of people shown in the two-dimensional image, and may be a model obtained by machine learning a plurality of learning two-dimensional images and correct data indicating the number of people shown in each learning two-dimensional image. Also, the machine learning model is, for example, a model for identifying the area where people appear in the two-dimensional image, and may be a model obtained by learning a plurality of learning two-dimensional images and correct data indicating the area where people exist in each learning two-dimensional image. When the control unit 120 identifies the area where people appear, the control unit 120 identifies the number of people by counting the identified area. In this way, the control unit 120 identifies the number of people present in the second space 202 based on the detection result of the human presence sensor 22.

[0071] (Third example) A third example of the volume information is number information that is the action plan of one or more people and includes an action plan to use the second space 202. Specifically, the action plan of one or more people is indicated by a reservation for using the space managed by the server 40. The acquisition unit 110 acquires reservation information indicating the reservation for using the space from the server 40. The reservation information indicates the action plan of one or more people and includes an action plan to use the second space 202. Therefore, it can be said that the reservation information is a kind of number information.

[0072] Then, the control unit 120 identifies the number of people present in the second space 202 at present by counting the number of people who have a reservation to use the second space 202 at present based on the reservation information acquired from the server 40. The control unit 120 adjusts so that the volume of the sound output from the speaker device 30 becomes smaller as the identified number of people present in the second space 202 is larger.

[0073] Note that the reservation information may include the number of people who plan to use the space. In this case, the control unit 120 may identify the number of people who plan to use the second space 202 included in the reservation information as the number of people present in the second space 202.

[0074] <Presence / absence information and control according to the presence / absence information> The control unit 120 may further control the output of the sound from the speaker device 30 according to the presence or absence of people in the first space 201. Specifically, when there are people in the first space 201, the control unit 120 outputs sound from the speaker device 30, and when there are no people in the first space 201, the control unit 120 does not output sound from the speaker device 30.

[0075] In this case, the acquisition unit 110 further acquires presence / absence information regarding the presence or absence of people in the first space 201. Then, the control unit 120 determines whether there are people in the first space 201 based on the presence / absence information. When the control unit 120 determines that there are no people in the first space 201 (that is, when it is identified that there are no people in the first space 201), the control unit 120 does not output sound from the speaker device 30. For example, when the control unit 120 identifies that there are no people in the first space 201 while the sound is being output from the speaker device 30, the control unit 120 stops the output of the sound from the speaker device 30. For example, when the control unit 120 identifies that there are no people in the first space 201 while the sound is not being output from the speaker device 30, the control unit 120 continues not to output sound from the speaker device 30.

[0076] On the contrary, when the control unit 120 determines that a person is present in the first space 201 (that is, when it identifies that a person is present in the first space 201), it outputs voice from the speaker device 30. For example, when the control unit 120 identifies that a person is present in the first space 201 while voice is being output from the speaker device 30, it continues to output the voice from the speaker device 30. For example, when the control unit 120 identifies that a person is present in the first space 201 while voice is not being output from the speaker device 30, it starts to output voice from the speaker device 30.

[0077] Note that the presence / absence information may include the detection result by the human presence sensor 21 arranged in the first space 201. That is, the acquisition unit 110 acquires the detection result by the human presence sensor 21 from the human presence sensor 21 as the presence / absence information. Then, when the detection result acquired by the acquisition unit 110 indicates that no person is present in the first space 201, the control unit 120 does not output voice from the speaker device 30.

[0078] Also, the presence / absence information may be the action plan of one or more persons and may include the action plan to use the first space 201. That is, the acquisition unit 110 acquires reservation information indicating the reservation of the use of the space from the server 40. The reservation information indicates the action plan of one or more persons and includes the action plan to use the first space 201. Therefore, it can be said that the reservation information is a kind of presence / absence information. Then, the control unit 120 determines whether there is a current use plan for the first space 201 based on the reservation information acquired from the server 40. When the control unit 120 identifies that there is a use plan for the first space 201, it identifies that a person is present in the first space 201. Therefore, in this case, the control unit 120 outputs voice from the speaker device 30. On the other hand, when the control unit 120 identifies that there is no use plan for the first space 201, it identifies that no person is present in the first space 201. Therefore, in this case, the control unit 120 does not output voice from the speaker device 30.

[0079] [2. Operation] Next, the operation of the voice control device 100 according to the embodiment will be described.

[0080] FIG. 6 is a flowchart showing an example of a voice control method by the voice control device according to the embodiment.

[0081] First, the acquisition unit 110 acquires volume information regarding the loudness of sound in the second space 202 (S11).

[0082] Next, the control unit 120 adjusts so that the louder the loudness of the sound in the second space 202 obtained based on the acquired volume information, the lower the volume of the voice output from the speaker device 30 (S12).

[0083] Next, the control unit 120 outputs voice from the speaker device 30 at the adjusted volume (S13).

[0084] Next, specific examples (the first example to the third example) of the control for adjusting the volume in step S12 will be described.

[0085] FIG. 7 is a flowchart showing a first example of the control for adjusting the volume according to the embodiment. The first example is an example where the volume information is sound data indicating the sound picked up by the microphone 12. That is, in the first example, in step S11, it is assumed that the acquisition unit 110 acquires, as the volume information, sound data indicating the sound picked up by the microphone 12.

[0086] In the first example, in step S12, the control unit 120 first identifies the loudness of the sound indicated by the sound data by analyzing the sound data (S21).

[0087] Then, the control unit 120 adjusts so that the louder the identified loudness of the sound, the lower the volume of the voice output from the speaker device 30 (S22).

[0088] FIG. 8 is a flowchart showing a second example of control for adjusting the volume according to an embodiment. The second example is a case where the volume information is the number of people information including the detection result by the human presence sensor 22 arranged in the second space 202. That is, in the second example, in step S11, it is assumed that the acquisition unit 110 acquires the number of people information from the human presence sensor 22 as the volume information.

[0089] In the second example, in step S12, the control unit 120 first identifies the number of people present in the second space 202 by analyzing the two-dimensional image which is the detection result by the human presence sensor 22 (S31).

[0090] Then, the control unit 120 adjusts so as to reduce the volume of the voice output from the speaker device 30 as the number of people present in the second space 202 increases (S32).

[0091] FIG. 9 is a flowchart showing a third example of control for adjusting the volume according to an embodiment. The third example is a case where the volume information is the number of people information including the action plan of one or more people and the action plan using the second space 202. That is, in the third example, in step S11, it is assumed that the acquisition unit 110 acquires the reservation information from the server 40 as the volume information.

[0092] In the third example, in step S12, the control unit 120 first identifies the number of people present in the second space 202 at present by counting the number of people who have a reservation to use the second space 202 at present based on the reservation information (S41).

[0093] Then, the control unit 120 adjusts so as to reduce the volume of the voice output from the speaker device 30 as the number of people present in the second space 202 increases (S42).

[0094] Next, the output control of the voice according to the presence / absence information will be described. The output control of the voice is performed in parallel while the voice control method is being executed.

[0095] FIG. 10 is a flowchart showing an example of output control of voice according to the presence / absence information according to the embodiment.

[0096] First, the acquisition unit 110 acquires presence / absence information regarding the presence / absence of a person in the first space 201 (S51).

[0097] Next, the control unit 120 determines whether a person exists in the first space 201 based on the presence / absence information (S52).

[0098] When the control unit 120 determines that a person exists in the first space 2 (Yes in S52), the control unit 120 does not output voice from the speaker device 30 (S53). That is, when the voice is being output from the speaker device 30, the control unit 120 stops the output of the voice from the speaker device 30. Also, when the voice is not being output from the speaker device 30, the control unit 120 continues not to output voice from the speaker device 30.

[0099] When the control unit 120 determines that no person exists in the first space 201 (No in S52), the control unit 120 outputs voice from the speaker device 30 (S54). Note that the voice output from the speaker device 30 in step S54 is adjusted to the volume adjusted in step S12. That is, when the voice is being output from the speaker device 30, the control unit 120 continues the output of the voice from the speaker device 30. Also, when the voice is not being output from the speaker device 30, the control unit 120 starts the output of the voice from the speaker device 30.

[0100] [3. Effects, etc.] According to the voice control system 1 according to this embodiment, as the sound volume in the second space 202 increases, the volume of the voice for masking the sound generated in the first space 201 is adjusted to decrease. Therefore, the sound generated in the first space 201 can be efficiently masked. Thus, as the sound volume in the second space 202 increases, the power consumption required for masking can be reduced, and the power consumption required for masking the sound generated in the first space 201 can be reduced.

[0101] Further, in the voice control system 1 according to this embodiment, the acquisition unit 110 acquires sound data indicating the sound picked up by the microphone 12 disposed in the second space 202 as volume information. The control unit 120 identifies the volume of the sound indicated by the sound data, and adjusts the volume of the voice for masking the sound generated in the first space 201 to decrease as the identified volume of the sound increases. According to this, as the volume of the sound picked up by the microphone 12 in the second space 202 increases, the volume of the voice for masking the sound generated in the first space 201 is adjusted to decrease. Therefore, the sound generated in the first space 201 can be efficiently masked.

[0102] Further, in the voice control system 1 according to this embodiment, as the number of people present in the second space 202 increases, the volume of the voice for masking the sound generated in the first space 201 is adjusted to decrease. Therefore, the sound generated in the first space can be efficiently masked.

[0103] Further, in the voice control system 1 according to this embodiment, the acquisition unit 110 further acquires presence information regarding the presence or absence of people in the first space 201. When the control unit 120 identifies that there is no person in the first space 201 based on the presence information, the control unit 120 does not output the voice for masking the sound generated in the first space 201 from the speaker device 30. According to this, when there is no person in the first space 201, the voice for masking is not output toward the second space 202, so that the power consumption can be reduced.

[0104] [4. Variations of the Embodiment] (Variation 1) In the above embodiment, the sound source data is assumed to be pre - prepared sound source data, but it is not limited to this. The sound source data may be updated to sound data indicating the sound periodically picked up by the microphone 12.

[0105] Specific processing will be described.

[0106] The acquisition unit 110 acquires sound data indicating the sound picked up by the microphone 12. The timing at which the acquisition unit 110 acquires the sound data from the microphone 12 may be a periodic timing such as every one month or every two months, or may be the timing when receiving an instruction from the user.

[0107] The control unit 120 causes the storage unit 130 to store the sound data acquired by the acquisition unit 110 as sound source data. In addition to the sound source data stored in the storage unit 130, the control unit 120 may further cause the storage unit 130 to store the newly acquired sound data by the acquisition unit 110 as sound source data. Also, the control unit 120 may update the sound source data stored in the storage unit 130 with the newly acquired sound data by the acquisition unit 110. When the control unit 120 further causes the storage unit 130 to store the newly acquired sound data by the acquisition unit 110 as sound source data in addition to the sound source data stored in the storage unit 130, the new sound data may be stored as sound source data, and the old sound source data stored in the storage unit 130 may be deleted in order.

[0108] The control unit 120 generates the sound output from the speaker device 30 using the sound source data stored in the storage unit 130.

[0109] When updating the sound data, the sound may be picked up for each time period, and the picked - up sound data may be stored in the storage unit 130 as the sound source data used when generating the sound output in that time period.

[0110] The acquisition unit 110 acquires first sound data indicating the sound picked up by the microphone 12 in the first time period and second sound data indicating the sound picked up by the microphone 12 in the second time period. The first time period and the second time period are, for example, time periods in a day. The first time period is, for example, the time period from 8:00 am to 10:00 am. The second time period is, for example, the time period from 10:00 am to noon. Note that the time periods in a day may be defined other than these time periods. That is, the time periods in a day may include not only two or more time periods but also three or more time periods. Further, these time periods may be non-overlapping time periods.

[0111] The control unit 120 causes the storage unit 130 to store the first sound data and the second sound data as sound source data. Specifically, the control unit 120 causes the storage unit 130 to store the first sound data as first sound source data of the sound output in the first time period and causes the storage unit 130 to store the second sound data as second sound source data of the sound output in the second time period.

[0112] Further, the control unit 120 generates a sound to be output from the speaker device 30 in the first time period using the first sound data, and outputs the generated sound from the speaker device 30 in the first time period. Also, the control unit 120 generates a sound to be output from the speaker device 30 in the second time period using the second sound data, and outputs the generated sound from the speaker device 30 in the second time period.

[0113] Next, the sound collection control of the sound control device 100 according to Modification 1 of the embodiment will be described.

[0114] FIG. 11 is a flowchart showing an example of the sound collection control of the sound control device according to Modification 1 of the embodiment.

[0115] First, the control unit 120 determines whether the current time is the first time (S61). The first time is a time included in the first time period. The first time may be, for example, 8:00 am.

[0116] When the control unit 120 determines that the current time is the first time (Yes in S61), it starts the sound collection by the microphone 12 (S62). When the control unit 120 determines that the current time is not the first time (No in S61), it returns to step S61.

[0117] The control unit 120 determines whether the current time is the second time (S63). The second time is the time that is one hour after the first time among the times included in the first time zone. The second time may be, for example, 9:00 am. The first hour is the time of the first length.

[0118] When the control unit 120 determines that the current time is the second time (Yes in S63), it ends the sound collection by the microphone 12 (S64). Thereby, the acquisition unit 110 acquires first sound data indicating the sound collected by the microphone 12 in the first time zone. When the control unit 120 determines that the current time is not the second time (No in S63), it returns to step S63.

[0119] Next, the control unit 120 stores the acquired first sound data in the storage unit 130 as first sound source data (S65).

[0120] In this way, the control unit 120 causes the acquisition unit 110 to acquire the detection result by the microphone 12 from the first time to the second time. Thereby, the acquisition unit 110 acquires first sound data from the microphone 12, and the control unit 120 stores the first sound data in the storage unit 130. The control unit 120 manages the first sound data stored in the storage unit 130 as first sound source data.

[0121] Next, the control unit 120 determines whether the current time is the third time (S66). The third time is the time included in the second time zone. The third time may be, for example, 10:00 am.

[0122] When the control unit 120 determines that the current time is the third time (Yes in S66), it starts the sound collection by the microphone 12 (S67). When the control unit 120 determines that the current time is not the third time (No in S66), it returns to step S66.

[0123] The control unit 120 determines whether the current time is the fourth time (S68). The fourth time is the time that is two hours later than the third time among the times included in the second time zone. The fourth time may be, for example, 11:00 am. Note that the first time and the second time indicate time intervals and may be the same length of time as each other or different lengths of time from each other.

[0124] When the control unit 120 determines that the current time is the fourth time (Yes in S68), it ends the sound collection by the microphone 12 (S69). Thereby, the acquisition unit 110 acquires second sound data indicating the sound collected by the microphone 12 in the second time zone. When the control unit 120 determines that the current time is not the fourth time (No in S68), it returns to step S68.

[0125] Next, the control unit 120 stores the acquired second sound data in the storage unit 130 as second sound source data (S70).

[0126] In this way, the control unit 120 causes the acquisition unit 110 to acquire the detection result by the microphone 12 from the third time to the fourth time. Thereby, the acquisition unit 110 acquires second sound data from the microphone 12, and the control unit 120 stores the second sound data in the storage unit 130. The control unit 120 manages the second sound data stored in the storage unit 130 as second sound source data.

[0127] Next, the output control of the voice control device 100 according to the first modification of the embodiment will be described.

[0128] FIG. 12 is a flowchart showing an example of the output control of the voice control device according to the first modification of the embodiment.

[0129] First, the control unit 120 determines whether the current time is included in the first time zone (S71).

[0130] When the current time is included in the first time zone (Yes in S71), the control unit 120 generates a voice for masking the sound generated in the first space 201 using the first sound data managed as the first sound source data in the storage unit 130, and outputs the generated voice from the speaker device 30 (S72). Note that in step S72, although it is assumed that the voice is generated in the first time zone, it is not limited to this. The control unit 120 may generate first voice data indicating the voice using the first sound data in advance, store it in the storage unit 130, and output the voice based on the first voice data to the speaker device 30 in the first time zone.

[0131] When the current time is not included in the first time zone (No in S71), the control unit 120 determines whether the current time is included in the second time zone (S73).

[0132] When the current time is included in the second time zone (Yes in S73), the control unit 120 generates a voice for masking the sound generated in the first space 201 using the second sound data managed as the second sound source data in the storage unit 130, and outputs the generated voice from the speaker device 30 (S74). Note that in step S74, although it is assumed that the voice is generated in the second time zone, it is not limited to this. The control unit 120 may generate second voice data indicating the voice using the second sound data in advance, store it in the storage unit 130, and output the voice based on the second voice data to the speaker device 30 in the second time zone.

[0133] When the current time is not included in the second time zone (No in S73), the control unit 120 ends the output control.

[0134] (Modification Example 2) When sound data indicating sound picked up by the microphone 12 arranged in the second space 202 is used as sound source data, human conversations may be picked up in the second space 202. If a human conversation is picked up as sound source data, there is a risk that the human conversation picked up in the second space 202 may be output from the speaker device 30. Therefore, when the sound data includes a human conversation, the sound data may be processed so that it cannot be recognized that a human conversation is included, and the processed sound data may be stored in the storage unit 130 as sound source data.

[0135] A specific example of the processing of the sound data will be described.

[0136] The control unit 120 analyzes the sound data indicating the sound picked up by the microphone 12 and executes a process of detecting a human conversation from the sound data. For example, the control unit 120 determines whether a portion where the sound pressure exceeds a predetermined threshold is included in the waveform in the frequency band of the human voice in the sound data (for example, a frequency band of 150 Hz to 1 kHz). When the control unit 120 determines that a portion where the sound pressure exceeds the predetermined threshold is included in this waveform, the control unit 120 detects the portion where the sound pressure exceeds the predetermined threshold as a portion including a human conversation. Note that the control unit 120 may execute a speech recognition process and detect a portion including a sound recognized as words in the sound data as a portion including a human conversation.

[0137] The control unit 120 reduces the sound pressure in the voice band of the portion including the human conversation in the sound data by a predetermined sound pressure or to a predetermined sound pressure, and synthesizes noise including at least the voice band into the portion. Thereby, sound data processed so that a human conversation cannot be recognized is obtained. The control unit 120 stores the synthesized sound data in the storage unit 130 as sound source data.

[0138] (Modification 3) In the above embodiment, the first space 201 to be masked and the surrounding second space 202 are fixed spaces, but the present invention is not limited to this, and the first space and the second space may be dynamically changed.

[0139] FIG. 13 is a diagram showing a usage example of the voice control system according to Modification Example 3 of the embodiment. Note that FIG. 13 includes a schematic view of the space in which the voice control system is used, as seen from above.

[0140] FIG. 13 shows a voice control system 1A including a voice control device 100, speakers 31 to 39, microphones 51 to 59, and switches 61, 63, 65, 67, 69 arranged on a table. Also, in FIG. 13, it is shown that the voice control device 100 and the server 40 are communicably connected to each other via the network 50.

[0141] In FIG. 13, the space is divided into a plurality (for example, nine) of spaces 211 to 219. A speaker 31 and a microphone 51 are arranged on the ceiling of the space 211, and a switch 61 is provided on the table arranged in the space 211. Also, a speaker 32 and a microphone 52 are arranged on the ceiling of the space 212. A speaker 33 and a microphone 53 are arranged on the ceiling of the space 213, and a switch 63 is provided on the table arranged in the space 213. Also, a speaker 34 and a microphone 54 are arranged on the ceiling of the space 214. A speaker 35 and a microphone 55 are arranged on the ceiling of the space 215, and a switch 65 is provided on the table arranged in the space 215. Also, a speaker 36 and a microphone 56 are arranged on the ceiling of the space 216. A speaker 37 and a microphone 57 are arranged on the ceiling of the space 217, and a switch 67 is provided on the table arranged in the space 217. Also, a speaker 38 and a microphone 58 are arranged on the ceiling of the space 218. A speaker 39 and a microphone 59 are arranged on the ceiling of the space 219, and a switch 69 is provided on the table arranged in the space 219.

[0142] The voice control device 100 determines, based on the sound data indicating the sound picked up by microphones 51 to 59 or the on / off information obtained from switches 61, 63, 65, 67, and 69, the space to be set as the first space and the space to be set as the second space from among spaces 211 to 219. Then, the voice control device 100 controls speakers 31 to 39 so that the voice is output louder in the second space than in the set first space.

[0143] Hereinafter, the specific functions of each processing unit will be described.

[0144] The acquisition unit 110 acquires space information for specifying the first space from among spaces 211 to 219. Specifically, the acquisition unit 110 may acquire, as the space information, sound data indicating the sound picked up by microphones 51 to 59. Further, the acquisition unit 110 may acquire, as the space information, on / off information obtained from switches 61, 63, 65, 67, and 69. The on / off information is information indicating whether each switch is on or off.

[0145] The control unit 120 executes a process of detecting a portion including a human conversation from the sound data by analyzing the sound data acquired by the acquisition unit 110. This process is the same as the process of Modification Example 2. The control unit 120 may set, as the first space, the space in which the microphone that picked up the sound data in which a portion including a human conversation is detected is arranged, among spaces 211 to 219.

[0146] Further, the control unit 120 may set, as the first space, the space in which the table provided with the switch indicating on is arranged, among spaces 211, 213, 215, 217, and 219, based on the on / off information acquired by the acquisition unit 110. [[ID=?]]

[0147] Further, the control unit 120 may set, as the second space, the spaces among the spaces 211 to 219 excluding the space set as the first space. Alternatively, the control unit 120 may set, as the second space, the space in which the microphone that has picked up the sound data in which no part including human conversation is detected among the spaces 211 to 219 is arranged. Further, the control unit 120 may set, as the second space, the space in which the table provided with the switch indicating off is arranged among the spaces 211, 213, 215, 217, 219 based on the on / off information acquired by the acquisition unit 110.

[0148] The control unit 120 outputs sound from one or more speakers arranged in the space set as the second space among the spaces 211 to 219, and does not output sound from one or more speakers arranged in the space set as the first space. Thereby, the control unit 120 controls the speakers 31 to 39 so that the sound is output louder in one or more spaces set as the second space than in one or more spaces set as the first space among the spaces 211 to 219.

[0149] Note that the control unit 120 may make the volume of the sound output from one or more speakers arranged in the space set as the second space among the spaces 211 to 219 larger than the volume of the sound output from one or more speakers arranged in the space set as the first space.

[0150] FIG. 14 is a flowchart showing an example of control for setting a space by the voice control device according to Modification Example 3 of the embodiment.

[0151] First, the acquisition unit 110 acquires space information from the microphones 51 to 59 and the switches 61, 63, 65, 67, 69 (S81).

[0152] Next, based on the spatial information, the control unit 120 sets each of the spaces 211 to 219 as either the first space or the second space (S82). For example, when the control unit 120 detects human conversation from the microphones 51 and 58, it sets the spaces 211 and 218 as the first space. Also, for example, when the switch 61 is on, the control unit 120 sets the space 211 as the first space.

[0153] Next, the control unit 120 controls the speakers 31 to 39 so that the sound is output louder in one or more spaces set as the second space than in one or more spaces set as the first space among the plurality of spaces 211 to 219 (S83). For example, the control unit 120 outputs masking sound from the speakers 32 to 37 and 39 arranged in the spaces 212 to 217 and 219 set as the second space, and does not output sound from the speakers 31 and 38 arranged in the spaces 211 and 218 set as the first space.

[0154] Even in this case, the control unit 120 controls the volume of the speakers arranged in one or more spaces set as the second space among the speakers 31 to 39 according to the volume information, as in the embodiment.

[0155] According to this, even when the first space and the second space are dynamically set, the larger the sound volume in the second space, the smaller the volume of the sound for masking the sound generated in the first space used by the person is adjusted. Therefore, the sound generated in the first space can be efficiently masked.

[0156] In addition, in Modification 3, although the voice control device 100 was described as acquiring spatial information from the microphones 51 to 59 and the switches 61, 63, 65, 67, and 69, it is not limited to this. When a human presence sensor capable of detecting the number of people, such as the human presence sensor 22, is arranged in each of the spaces 211 to 219, the control unit 120 may set the space in which the human presence sensor detecting a plurality of people is arranged as the first space. Further, when the server 40 has accepted a reservation for each of the spaces 211 to 219, the space scheduled for use by a plurality of people may be set as the first space.

[0157] (Modification 4) In the above embodiment, the human presence sensor 22 arranged in the second space 202 is an image type human presence sensor capable of detecting the number of people present in the second space 202, and it was described that the number of people is specified by analyzing the two-dimensional image as the detection result. However, it is not limited to this. For example, a plurality of human presence sensors may be arranged corresponding to a plurality of regions into which the second space 202 is divided, and the number of people present in the second space 202 may be detected by detecting the presence or absence of people in each of the plurality of regions. That is, the control unit 120 may specify the number of human presence sensors that have detected the presence of people among the plurality of human presence sensors as the number of people present in the second space 202.

[0158] Further, the human presence sensor arranged in the second space 202 may be a camera. The control unit 120 may identify the people reflected in the two-dimensional image by performing image recognition processing on the two-dimensional image captured by the camera. Thereby, the control unit 120 may specify the number of people present in the second space 202.

[0159] (Modification 5) In the above embodiment, the voice control system 1 includes the voice control device 100, the microphones 11 and 12, the human presence sensors 21 and 22, and the speaker device 30. However, it is not limited to this, and at least the voice control device 100 may be included, and the microphones 11 and 12, the human presence sensors 21 and 22, and the speaker device 30 do not have to be included.

[0160] In the above-described embodiment, each component may be configured by dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

[0161] Also, each component may be a circuit (or an integrated circuit). These circuits may constitute one circuit as a whole or may be separate circuits respectively. Further, each of these circuits may be a general-purpose circuit or a dedicated circuit.

[0162] Also, the general or specific aspects of the present disclosure may be realized by a system, an apparatus, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM. Further, the present disclosure may be realized by any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a computer-readable non-transitory recording medium.

[0163] For example, the present disclosure may be realized as an image processing method executed by an image processing apparatus (a computer or a DSP), or may be realized as a program for causing a computer or a DSP to execute the above-described image processing method.

[0164] In the above-described embodiment, the processing executed by a specific processing unit may be executed by another processing unit. Also, the order of a plurality of processes in the operation of the voice control system described in the above-described embodiment may be changed, or the plurality of processes may be executed in parallel.

[0165] In addition, forms obtained by applying various modifications that can be conceived by those skilled in the art to each embodiment, or forms realized by arbitrarily combining the components and functions in each embodiment without departing from the spirit of the present disclosure are also included in the present disclosure.

Industrial Applicability

[0166] The present disclosure is useful as an audio control system, an audio control method, a program, etc. that can efficiently mask sounds generated in a space used by a person.

Explanation of Signs

[0167] 1, 1A Audio control system 11, 12 Microphone 21, 22 Human sensor 30 Speaker device 31~39 Speaker 40 Server 50 Network 51~59 Microphone 61, 63, 65, 67, 69 Switch 100 Audio control device 101 Processor 102 Main memory 103 Storage 104 Communication IF 105 Input IF 106 Display 110 Acquisition unit 120 Control unit 130 Storage unit 201 First space 202 Second space 211~219 Space 301 Wall 400 Reservation information 401, 402 Usage reservation

Claims

1. An acquisition unit that acquires sound data indicating sound picked up by a microphone disposed in a second space around a first space used by a person; A storage unit that stores sound source data; A control unit that controls one or more speakers disposed in the first space or the second space so that the sound obtained from the sound source data is reproduced louder in the second space than in the first space, comprising: The control unit identifies the loudness of the sound indicated by the acquired sound data, and adjusts so that the louder the identified loudness of the sound, the lower the volume of the sound output from the one or more speakers An audio control system.

2. An acquisition unit that acquires number information regarding the number of people present in a second space around a first space used by a person; A storage unit that stores sound source data; A control unit that controls one or more speakers disposed in the first space or the second space so that the sound obtained from the sound source data is reproduced louder in the second space than in the first space, comprising: The control unit adjusts so that the larger the number of people obtained based on the acquired number information, the lower the volume of the sound output from the one or more speakers An audio control system.

3. The number information includes a first detection result by one or more human sensors that target the second space for detection, The control unit identifies the number of people present in the second space based on the first detection result The audio control system according to claim 2.

4. The number information is a planned action of one or more people and includes a planned action to use the second space, The control unit identifies the number of people present in the second space currently by counting the number of people who have a planned use of the second space currently based on the planned action included in the number information The audio control system according to claim 2.

5. The acquisition unit further acquires presence / absence information regarding the presence or absence of a person in the first space, When the control unit identifies that no person is present in the first space based on the presence / absence information, the control unit does not output the sound from the speaker The audio control system according to any one of claims 1 to 4.

6. The presence / absence information includes a second detection result by a human sensor that targets the first space for detection, When the second detection result indicates that no person is present in the first space, the control unit does not output the sound from the speaker The voice control system according to claim 5.

7. The presence / absence information is the action plan of one or more people, including the action plan of using the first space, When the control unit specifies that there is no current usage plan for the first space based on the action plan of the one or more people included in the presence / absence information, the control unit does not output the voice from the speaker. The voice control system according to claim 5.

8. The acquisition unit acquires sound data indicating the sound picked up by a microphone that picks up sound in the second space, The control unit stores the sound data as the sound source data in the storage unit, and generates a voice to be output from the one or more speakers using the sound source data stored in the storage unit. The voice control system according to any one of claims 1 to 7.

9. The acquisition unit acquires first sound data indicating the sound picked up by the microphone in the first time period and second sound data indicating the sound picked up by the microphone in the second time period, The control unit stores the first sound data and the second sound data as the sound source data in the storage unit, generates a voice to be output from the one or more speakers in the first time period using the first sound data, and generates a voice to be output from the one or more speakers in the second time period using the second sound data. The voice control system according to claim 8.

10. The acquisition unit acquires space information for specifying the first space from among a plurality of spaces including the first space and the second space, The control unit sets each of the plurality of spaces as either the first space or the second space based on the space information, and controls the one or more speakers so that the voice is reproduced louder in the one or more spaces set as the second space than in the one or more spaces set as the first space among the plurality of spaces. The voice control system according to any one of claims 1 to 9.

11. Acquire sound data indicating the sound picked up by a microphone arranged in a second space surrounding a first space used by a person, Control one or more speakers arranged in the first space or the second space so that the voice obtained from the sound source data stored in the storage device is reproduced louder in the second space than in the first space. Specify the loudness of the sound indicated by the acquired sound data, and adjust so that the louder the specified loudness of the sound, the lower the volume of the voice output from the one or more speakers. Voice control method.

12. Obtain population information regarding the number of people present in a second space around a first space used by people, Control one or more speakers arranged in the first space or the second space so that the voice obtained from the sound source data stored in the storage device is reproduced louder in the second space than in the first space, Adjust so that the larger the number of people obtained based on the acquired population information, the lower the volume of the voice output from the one or more speakers. Voice control method.

13. Obtain sound data indicating the sound picked up by a microphone arranged in a second space around a first space used by people, Control one or more speakers arranged in the first space or the second space so that the voice obtained from the sound source data stored in the storage device is reproduced louder in the second space than in the first space, Specify the loudness of the sound indicated by the acquired sound data, and adjust so that the louder the specified loudness of the sound, the lower the volume of the voice output from the one or more speakers. Program for causing a computer to execute a voice control method.

14. Obtain population information regarding the number of people present in a second space around a first space used by people, Control one or more speakers arranged in the first space or the second space so that the voice obtained from the sound source data stored in the storage device is reproduced louder in the second space than in the first space, Adjust so that the larger the number of people obtained based on the acquired population information, the lower the volume of the voice output from the one or more speakers. Program for causing a computer to execute a voice control method.

Images