Sound reproduction method, sound reproduction device, and sound reproduction program

Abstract

This sound reproduction device acquires information on a plurality of persons in a predetermined space, synchronizes and reproduces a plurality of divided sound signals obtained by dividing a predetermined sound, and outputs the plurality of divided sound signals to a speaker on the basis of information on the plurality of persons, the speaker emitting a plurality of divided sounds, obtained through conversion from the plurality of divided sound signals, into the predetermined space.

Description

Sound reproduction method, sound reproduction device, and sound reproduction program

[0001] The present disclosure relates to technology for reproducing sound.

[0002] For example, Patent Literature 1 discloses a system for preventing overhearing of private conversations in public spaces. In this system, business or leisure groups and individuals are detected. Then, in areas where business or leisure groups are present, the volume of music is reduced and the low-frequency characteristics of the music are reduced. This means that people in the group can clearly hear each other without having to shout above the music, and low-frequency sounds do not mask their conversation. Furthermore, in areas where individuals are present, the volume of music is increased and low-frequency sounds (such as the sound of running water) are added to prevent individuals from clearly hearing the business or leisure group's conversation.

[0003] However, the above-mentioned conventional technology does not take into consideration the situation where multiple people gather in a given space, and further improvement is needed.

[0004] Special Publication No. 2011-528445

[0005] The present disclosure has been made to solve the above problems, and aims to provide a technology that can gather multiple people in a specified space and stimulate conversation among the multiple people in the specified space.

[0006] The sound reproduction method according to the present disclosure is a sound reproduction method in a computer, which includes acquiring information about a plurality of people in a specified space, synchronizing and reproducing a plurality of divided sound signals obtained by dividing the specified sound, and outputting the plurality of divided sound signals based on the information about the plurality of people to a speaker that emits a plurality of divided sounds converted from the plurality of divided sound signals into the specified space.

[0007] According to the present disclosure, it is possible to gather a plurality of people in a predetermined space and stimulate conversation among the plurality of people in the predetermined space.

[0008] FIG. 1 is a diagram illustrating an overall configuration of a sound reproduction system according to the first embodiment. FIG. 2 is a block diagram illustrating a configuration of a sound reproduction device according to the first embodiment. FIG. 3 is a diagram illustrating an example of information stored in a personal information database according to the first embodiment. FIG. 4 is a first flowchart illustrating sound reproduction processing by the sound reproduction device according to the first embodiment of the present disclosure. FIG. 5 is a second flowchart illustrating sound reproduction processing by the sound reproduction device according to the first embodiment of the present disclosure. FIG. 6 is a diagram illustrating an overall configuration of a sound reproduction system according to the second embodiment. FIG. 7 is a block diagram illustrating a configuration of a sound reproduction device according to the second embodiment. FIG. 8 is a first flowchart illustrating sound reproduction processing by the sound reproduction device according to the second embodiment of the present disclosure. FIG. 9 is a second flowchart illustrating sound reproduction processing by the sound reproduction device according to the third embodiment. FIG. 10 is a block diagram illustrating a configuration of a sound reproduction device according to the third embodiment. FIG. 11 is a first flowchart illustrating sound reproduction processing by the sound reproduction device according to the third embodiment of the present disclosure. FIG. 12 is a second flowchart illustrating sound reproduction processing by the sound reproduction device according to the third embodiment of the present disclosure. 13 is a second flowchart illustrating a sound reproduction process performed by the sound reproduction device according to the fourth embodiment of the present disclosure.

[0009] (Findings that Form the Basis of the Present Disclosure) Conventionally, the issue has been how to attract many people to a conference, as well as how to stimulate conversation among the conference participants.

[0010] In the above-mentioned Patent Document 1, when a business or leisure group of customers is in a first area and an individual customer is in a second area adjacent to the first area, the volume of the music in the second area is increased and the sound of running water is added to the second area, thereby masking the conversations of the people in the first area in the second area and preventing private conversations from being overheard in a public place.

[0011] However, in Patent Document 1, people outside the area will not necessarily want to enter the area, and gathering multiple people in a predetermined space is not taken into consideration.

[0012] In order to solve the above problems, the following techniques are disclosed.

[0013] (1) A sound reproduction method according to one aspect of the present disclosure is a sound reproduction method in a computer, which includes acquiring information about a plurality of people in a specified space, synchronizing and reproducing a plurality of divided sound signals obtained by dividing the specified sound, and outputting the plurality of divided sound signals based on the information about the plurality of people to a speaker that emits a plurality of divided sounds converted from the plurality of divided sound signals into the specified space.

[0014] According to this configuration, a plurality of divided sound signals that are reproduced in synchronization are output to a speaker based on information relating to a plurality of people, and a plurality of divided sounds are emitted from the speaker in a predetermined space.

[0015] Therefore, when a plurality of people gather together, the plurality of divided sounds overlap in a predetermined space, and one harmonious sound is heard, so that a plurality of people can be gathered in the predetermined space and conversations among the plurality of people in the predetermined space can be stimulated.

[0016] (2) In the sound reproduction method described in (1) above, the information regarding the plurality of persons may include identification result information identifying each of the plurality of persons, and may further include controlling the volume of each of the plurality of divided sound signals depending on whether each of the plurality of persons has been identified.

[0017] With this configuration, the volume of each of the multiple divided sound signals is controlled depending on whether each of the multiple people is present in the predetermined space. Therefore, when multiple people are present in the predetermined space, a predetermined sound made up of multiple overlapping divided sounds can be played in the predetermined space.

[0018] (3) In the sound reproduction method described in (2) above, the volume control may include, if a person is identified, determining the volume of the divided sound signal associated with the person to a predetermined volume, and, if the person is not identified, determining the volume of the divided sound signal associated with the person to zero.

[0019] According to this configuration, when a person is not in the predetermined space, the volume of the divided sound signal is controlled so that the divided sound associated with the person is not played, and when a person is in the predetermined space, the divided sound associated with the person is played. Therefore, as the number of people in the predetermined space increases, the predetermined space becomes a space with a fun atmosphere where many divided sounds overlap, so it is possible to gather multiple people in the predetermined space.

[0020] (4) In the sound reproduction method described in (1) above, the information about the plurality of people may include audio information indicating an average volume of the voice of each of the plurality of people over a predetermined period of time, and may further include controlling the volume of each of the plurality of divided sound signals in accordance with the average volume of the voice of each of the plurality of people over the predetermined period of time.

[0021] With this configuration, the volume of each of the multiple divided sound signals is controlled according to the average volume of the voices of each of the multiple people over a predetermined period of time. Therefore, the volume of the divided sounds can be changed depending on whether or not a person is speaking, and the presence or absence of divided sounds in a predetermined space can prompt a person who is not speaking to speak.

[0022] (5) In the sound reproduction method described in (4) above, the volume control may include determining the volume of the divided sound signal associated with the person to a predetermined volume when the average volume of the person's voice is smaller than a threshold value, and determining the volume of the divided sound signal associated with the person to zero when the average volume of the person's voice is equal to or greater than the threshold value.

[0023] According to this configuration, when a person speaks little, the divided sounds associated with the person are played, and when the person speaks a lot, the divided sounds associated with the person are not played, so that a person who speaks little can be encouraged to speak.

[0024] (6) In the sound reproduction method described in (1) above, the information about the plurality of people may include posture information about the posture of each of the plurality of people, and may further include controlling the volume of each of the plurality of divided sound signals according to the posture of each of the plurality of people.

[0025] According to this configuration, the volume of each of the plurality of divided sound signals is controlled in accordance with the posture of each of the plurality of people, and therefore it is possible to determine whether or not to emit each of the plurality of divided sounds from the speaker in accordance with the posture of each of the plurality of people.

[0026] (7) In the sound reproduction method described in (6) above, the posture information may indicate whether each of the plurality of people is standing or not, and the volume control may include determining the volume of the divided sound signal to a predetermined volume if the person is standing, and determining the volume of the divided sound signal to zero if the person is not standing.

[0027] According to this configuration, if multiple people are standing, multiple divided sounds are played, thereby creating an environment in the specified space where multiple people can easily gather. Also, if multiple people are sitting, multiple divided sounds are not played, thereby creating an environment in the specified space where multiple people can easily converse.

[0028] (8) In the sound reproduction method described in (7) above, the plurality of divided sound signals may be associated with a plurality of positions in the predetermined space where the plurality of people are located, respectively.

[0029] According to this configuration, it is possible to emit split sounds associated with the position of a person within a predetermined space from the speaker.

[0030] (9) In the sound reproduction method described in (6) above, the posture information indicates whether each of the multiple people is sitting at each of multiple positions within the specified space, and whether at least one of the multiple people is in a posture that makes them feel sleepy. The volume control may include, if a person is sitting, determining the volume of the divided sound signal corresponding to the position where the person is sitting to a predetermined volume, if the person is not sitting, determining the volume of the divided sound signal corresponding to the position where the person is not sitting to zero, if at least one of the multiple people is in a posture that makes them feel sleepy, determining the volume of another divided sound signal for suppressing the drowsiness, different from the multiple divided sound signals corresponding to each of the multiple positions, to a predetermined volume, and if not all of the multiple people are in a posture that makes them feel sleepy, determining the volume of the another divided sound signal to zero.

[0031] According to this configuration, if there is a person in a specified space who is feeling sleepy, a separate divided sound is played to suppress the sleepiness, thereby stimulating the person who is feeling sleepy and allowing them to concentrate on the conversation.

[0032] (10) In the sound reproduction method described in any one of (1) to (9) above, the predetermined sound may be divided according to the height of the frequency.

[0033] With this configuration, multiple divided sound signals for multiple frequency bands can be emitted in a specified space, and by overlapping the multiple divided sounds, a single harmonious sound can be emitted.

[0034] (11) In the sound reproduction method described in any one of (1) to (9) above, the predetermined sound may be music and may be divided according to a plurality of performance parts that make up the music.

[0035] According to this configuration, multiple divided sounds for each of the multiple performance parts that make up the music can be emitted in a specified space, and by overlapping the multiple divided sounds, a single harmonious piece of music can be emitted.

[0036] Furthermore, the present disclosure can be realized not only as a sound reproduction method that executes the characteristic processes described above, but also as a sound reproduction device having a characteristic configuration corresponding to the characteristic processes executed by the sound reproduction method. Furthermore, the present disclosure can also be realized as a computer program that causes a computer to execute the characteristic processes included in such a sound reproduction method. Therefore, the following other aspects can also achieve the same effects as the above sound reproduction method.

[0037] (12) A sound reproduction device according to another aspect of the present disclosure includes an acquisition unit that acquires information about a plurality of people in a specified space, a reproduction unit that synchronizes and reproduces a plurality of divided sound signals obtained by dividing a specified sound, and an output unit that outputs the plurality of divided sound signals based on information about the plurality of people to a speaker that emits a plurality of divided sounds converted from the plurality of divided sound signals into the specified space.

[0038] (13) Another aspect of the present disclosure provides a sound playback program that causes a computer to acquire information about multiple people in a specified space, synchronize and play multiple split sound signals obtained by dividing the specified sound, and output the multiple split sound signals based on the information about the multiple people to a speaker that emits the multiple split sounds converted from the multiple split sound signals into the specified space.

[0039] (14) A non-transitory computer-readable recording medium according to another aspect of the present disclosure records a sound playback program that causes a computer to acquire information about a plurality of people in a specified space, synchronize and play a plurality of split sound signals obtained by dividing the specified sound, and output the plurality of split sound signals based on the information about the plurality of people to a speaker that emits a plurality of split sounds converted from the plurality of split sound signals into the specified space.

[0040] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. Note that each of the embodiments described below represents a specific example of the present disclosure. The numerical values, shapes, components, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in the independent claims that represent the highest concept are described as optional components. Furthermore, in all embodiments, the respective contents can be combined.

[0041] First Embodiment FIG. 1 is a diagram showing the overall configuration of a sound reproduction system according to the first embodiment, and FIG. 2 is a block diagram showing the configuration of a sound reproduction device 2 according to the first embodiment.

[0042] The sound reproduction system includes a camera 1 , a sound reproduction device 2 , an amplifier 3 , and a speaker 4 .

[0043] Camera 1 captures an image of a predetermined space. Camera 1 is a fixed camera such as a surveillance camera, and is placed in a position where it can capture the entire predetermined space. The predetermined space is, for example, a room 100 such as a conference room where multiple people (first person 101, second person 102, third person 103, and fourth person 104) can gather. In the first embodiment, camera 1 captures the image inside room 100. Furthermore, the sound reproduction system may include one camera 1 or multiple cameras 1.

[0044] For example, a conference is held in a room 100 between a first person 101, a second person 102, a third person 103, and a fourth person 104. The conference is a meeting in which each person contributes various ideas. By playing music during the conference, the room 100 becomes a space with a fun atmosphere, and conversations among the conference participants are stimulated.

[0045] The camera 1 is connected by wire or wirelessly to the sound reproduction device 2 itself or to a hub (not shown) such as a communication device or a server so that the captured image can be input to the sound reproduction device 2. The camera 1 may be communicably connected to the sound reproduction device 2 via a network. The camera 1 outputs the captured image to the sound reproduction device 2.

[0046] The images captured by the camera 1 may be output in real time, or may be recorded once in an external storage device such as a memory or a cloud server, and then output from the external storage device.

[0047] The sound reproduction device 2 acquires information about a plurality of people in a specified space, reproduces a plurality of divided sound signals obtained by dividing the specified sound in synchronization with each other, and outputs the plurality of divided sound signals based on the information about the plurality of people to a speaker 4 that emits the plurality of divided sounds converted from the plurality of divided sound signals into the specified space.

[0048] The sound reproduction device 2 detects multiple people (first person 101, second person 102, third person 103, and fourth person 104) present in a predetermined space (room 100) based on an image captured by the camera 1. The sound reproduction device 2 identifies each of the multiple people (first person 101, second person 102, third person 103, and fourth person 104) and controls the volume of each of the multiple divided sound signals depending on whether each of the multiple people (first person 101, second person 102, third person 103, and fourth person 104) has been identified. In other words, the sound reproduction device 2 changes the volume of each of the first to fourth divided sound signals depending on whether each of the multiple people (first person 101, second person 102, third person 103, and fourth person 104) is present in the predetermined space (room 100).

[0049] The sound reproduction device 2 includes at least a computer system including, for example, a control program, a processing circuit such as a processor or logic circuit that executes the control program, and a recording device such as an internal memory or an accessible external memory that stores the control program. Note that the sound reproduction device 2 may be realized, for example, by hardware implementation using the processing circuit, or by execution by the processing circuit of a software program stored in the memory or distributed from an external server, or by a combination of these hardware and software implementations.

[0050] The sound playback device 2 includes a person detection unit 201, a feature extraction unit 202, a personal information database 203, a personal identification unit 204, a memory 205, a sound source playback unit 206, a first volume control unit 207, a second volume control unit 208, a third volume control unit 209, a fourth volume control unit 210, and a mixing unit 211.

[0051] The person detection unit 201 detects people in the room 100 based on the image captured by the camera 1 .

[0052] The feature extraction unit 202 extracts the facial features of the person detected by the person detection unit 201 .

[0053] The personal information database 203 stores facial features of multiple people in association with identification information (user IDs) for identifying the multiple people. Here, a method for registering a person's facial features in the personal information database 203 will be described. First, a person is photographed by a camera. Next, the person is detected from the photographed image, and the facial features of the detected person are extracted. Next, the person's identification information is input by an input device such as a touch panel. Next, the facial features of the person and the person's identification information are stored in association with each other in the personal information database 203.

[0054] The personal information database 203 also stores identification information for identifying a plurality of people and their favorite musical instruments in association with each other.

[0055] FIG. 3 is a diagram showing an example of information stored in personal information database 203 in the first embodiment.

[0056] As shown in Fig. 3, each person's favorite instrument is associated with their user ID (identification information). For example, the user ID "A" is associated with the instrument "drums." The sound reproduction device 2 may accept an input of a user ID and a favorite instrument by the person, and store the accepted user ID and favorite instrument in the personal information database 203 in association with each other. The personal information database 203 is only required to store at least the person's facial features and the person's identification information in association with each other, and the favorite instrument does not have to be registered.

[0057] The individual identification unit 204 outputs a playback start instruction to start playback of a predetermined sound to the sound source playback unit 206. When a person is detected by the person detection unit 201, the individual identification unit 204 outputs the playback start instruction to the sound source playback unit 206. Furthermore, when a person is no longer detected by the person detection unit 201, the individual identification unit 204 may output a playback end instruction to end playback of the predetermined sound to the sound source playback unit 206. Furthermore, when one of a plurality of people is identified, the individual identification unit 204 may output a playback start instruction to the sound source playback unit 206.

[0058] Furthermore, the personal identification unit 204 may select a sound corresponding to the current time period from among a plurality of different types of sounds, and output a playback start instruction to start playing the selected sound to the sound source playback unit 206. For example, the personal identification unit 204 may select a sound corresponding to the current time period from among a first sound corresponding to the morning time period (8:00 AM to 12:00 AM), a second sound corresponding to the afternoon time period (12:00 AM to 6:00 PM), and a third sound corresponding to the evening time period (6:00 PM to 10:00 PM). Note that the time periods are not limited to those described above.

[0059] The individual identification unit 204 acquires information about a plurality of people present in a predetermined space. The individual identification unit 204 identifies each of the plurality of people present in the predetermined space. The individual identification unit 204 controls the volume of each of the plurality of divided sound signals depending on whether each of the plurality of people has been identified.

[0060] The individual identification unit 204 compares the facial feature amount extracted by the feature extraction unit 202 with each of the facial feature amounts of a plurality of persons stored in the personal information database 203. If there is any feature amount that matches the facial feature amount extracted by the feature extraction unit 202 among the facial feature amounts of a plurality of persons stored in the personal information database 203, the individual identification unit 204 reads out the identification information associated with the feature amount from the personal information database 203 and identifies the person from the read identification information.

[0061] The plurality of persons are associated in advance with the plurality of divided sound signals. The individual identification unit 204 refers to the personal information database 203, extracts a favorite instrument corresponding to the user ID of the identified person, and associates the divided sound signal corresponding to the extracted favorite instrument from the plurality of divided sound signals as the divided sound signal of the person.

[0062] In addition, if the personal information database 203 does not register a favorite instrument corresponding to the user ID of the identified person, the personal identification unit 204 may associate any one of the multiple divided sound signals, excluding a divided sound signal that has already been associated as a divided sound signal of any of the people, as the divided sound signal of that person.

[0063] The individual identification unit 204 determines the volume of the first divided sound signal associated with the first person 101 depending on whether or not a first person 101 is present in the room 100, and instructs the first volume control unit 207 about the determined volume. The individual identification unit 204 determines the volume of the second divided sound signal associated with the second person 102 depending on whether or not a second person 102 is present in the room 100, and instructs the second volume control unit 208 about the determined volume. The individual identification unit 204 determines the volume of the third divided sound signal associated with the third person 103 depending on whether or not a third person 103 is present in the room 100, and instructs the third volume control unit 209 about the determined volume. The individual identification unit 204 determines the volume of the fourth divided sound signal associated with the fourth person 104 depending on whether or not a fourth person 104 is present in the room 100, and instructs the fourth volume control unit 210 about the determined volume.

[0064] If a person is identified, the individual identification unit 204 determines the volume of the divided sound signal associated with the person to be a predetermined volume. The predetermined volume is, for example, the maximum volume. If a person is not identified, the individual identification unit 204 determines the volume of the divided sound signal associated with the person to be zero. Note that the predetermined volume is not limited to the maximum volume and may be 50% or 80% of the maximum volume, as long as it is greater than zero.

[0065] When the first person 101 is identified in the room 100, the individual identification unit 204 determines the volume of the first divided sound signal associated with the first person 101 to be a predetermined volume. Furthermore, when the first person 101 is not identified in the room 100, the individual identification unit 204 determines the volume of the first divided sound signal associated with the first person 101 to be zero.

[0066] When the second person 102 is identified in the room 100, the individual identification unit 204 determines the volume of the second divided sound signal associated with the second person 102 to be a predetermined volume. Furthermore, when the second person 102 is not identified in the room 100, the individual identification unit 204 determines the volume of the second divided sound signal associated with the second person 102 to be zero.

[0067] If a third person 103 is identified in the room 100, the individual identification unit 204 determines the volume of the third divided sound signal associated with the third person 103 to be a predetermined volume. Furthermore, if a third person 103 is not identified in the room 100, the individual identification unit 204 determines the volume of the third divided sound signal associated with the third person 103 to be zero.

[0068] If the fourth person 104 is identified in the room 100, the individual identification unit 204 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be a predetermined volume. Furthermore, if the fourth person 104 is not identified in the room 100, the individual identification unit 204 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be zero.

[0069] In the first embodiment, the number of people is four, but the present disclosure is not particularly limited to this, and the number of people may be two or more.

[0070] The memory 205 stores in advance a plurality of divided sound signals obtained by dividing a predetermined sound. The memory 205 stores in advance a first divided sound signal, a second divided sound signal, a third divided sound signal, and a fourth divided sound signal. Note that the memory 205 may store a plurality of sounds in advance. The number of the plurality of divided sound signals may be the same as the number of the plurality of people, or may be different from the number of the plurality of people.

[0071] The predetermined sound is, for example, a series of music played by multiple musical instruments. Note that the predetermined sound is not limited to music as long as it is a series of audio content, and may be, for example, a series of natural sounds made up of multiple sounds such as the sound of wind, the sound of running water, the chirping of insects, or the singing of birds.

[0072] The predetermined sound may also be divided according to the performance parts of the music to be played. For example, the predetermined sound may be divided into a first divided sound signal representing a melody part that plays the main melody, a second divided sound signal representing a harmony part that plays chords or a supporting melody to the melody part, a third divided sound signal representing a rhythm part that is responsible for the rhythm of the music, and a fourth divided sound signal representing a bass part that is responsible for the low-pitched parts.

[0073] The predetermined sound may be divided according to the type of instrument being played, for example, into a first divided sound signal representing a drum sound, a second divided sound signal representing a bass sound, a third divided sound signal representing a keyboard sound, and a fourth divided sound signal representing a guitar sound.

[0074] The predetermined sound may also be divided according to the height of its frequency. For example, the predetermined sound may be divided into a first divided sound signal having a frequency of 50 Hz or less, a second divided sound signal having a frequency between 50 Hz and 500 Hz, a third divided sound signal having a frequency between 500 Hz and 1 kHz, and a fourth divided sound signal having a frequency of 1 kHz or more.

[0075] Furthermore, the predetermined sound may be divided according to a plurality of components that make up the predetermined sound. For example, if the predetermined sound is a series of natural sounds, the predetermined sound may be divided into a first divided sound signal representing the sound of wind, a second divided sound signal representing the sound of running water, a third divided sound signal representing the sound of insects chirping, and a fourth divided sound signal representing the sound of birds chirping.

[0076] The sound source reproducing unit 206 synchronously reproduces a plurality of divided sound signals obtained by dividing a predetermined sound. The sound source reproducing unit 206 is an example of a reproducing unit. The sound source reproducing unit 206 reads a plurality of divided sound signals from the memory 205. When a reproduction start instruction is input from the personal identification unit 204, the sound source reproducing unit 206 starts reproducing the plurality of divided sound signals obtained by dividing the predetermined sound. Furthermore, when a reproduction end instruction is input from the personal identification unit 204, the sound source reproducing unit 206 ends the reproduction of the plurality of divided sound signals obtained by dividing the predetermined sound.

[0077] The sound source reproduction unit 206 synchronously reproduces all of the first to fourth divided sound signals, regardless of whether or not each of the first to fourth persons 101 to 104 is present in the room 100. In other words, as long as at least one of the first to fourth persons 101 to 104 is present in the room 100, the sound source reproduction unit 206 synchronously reproduces all of the first to fourth divided sound signals.

[0078] The sound source playback unit 206 outputs the first divided sound signal to the first volume control unit 207, the second divided sound signal to the second volume control unit 208, the third divided sound signal to the third volume control unit 209, and the fourth divided sound signal to the fourth volume control unit 210.

[0079] The first volume control unit 207 to the fourth volume control unit 210 output the plurality of divided sound signals reproduced by the sound source reproduction unit 206 to the speaker 4, which emits the plurality of divided sounds converted from the plurality of divided sound signals into a predetermined space (room 100). The first volume control unit 207 to the fourth volume control unit 210 are an example of an output unit. Furthermore, the first volume control unit 207 to the fourth volume control unit 210 control the volume of each of the plurality of divided sound signals depending on whether each of the plurality of people is present in the predetermined space.

[0080] The first volume control unit 207 controls the volume of the first divided sound signal depending on the identification result of the first person 101. That is, the first volume control unit 207 controls the volume of the first divided sound signal depending on whether the first person 101 is present in the room 100. The first volume control unit 207 sets the volume of the first divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the person identification unit 204.

[0081] The second volume control unit 208 controls the volume of the second divided sound signal depending on the identification result of the second person 102. That is, the second volume control unit 208 controls the volume of the second divided sound signal depending on whether the second person 102 is present in the room 100. The second volume control unit 208 sets the volume of the second divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the person identification unit 204.

[0082] The third volume control unit 209 controls the volume of the third divided sound signal depending on the identification result of the third person 103. That is, the third volume control unit 209 controls the volume of the third divided sound signal depending on whether the third person 103 is present in the room 100. The third volume control unit 209 sets the volume of the third divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the person identification unit 204.

[0083] The fourth volume control unit 210 controls the volume of the fourth divided sound signal depending on the identification result of the fourth person 104. That is, the fourth volume control unit 210 controls the volume of the fourth divided sound signal depending on whether the fourth person 104 is present in the room 100. The fourth volume control unit 210 sets the volume of the fourth divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the person identification unit 204.

[0084] The mixing unit 211 combines the first divided sound signal input from the first volume control unit 207, the second divided sound signal input from the second volume control unit 208, the third divided sound signal input from the third volume control unit 209, and the fourth divided sound signal input from the fourth volume control unit 210. The mixing unit 211 outputs a combined sound signal obtained by combining the first to fourth divided sound signals to the amplifier 3. The mixing unit 211 combines a plurality of divided sound signals according to the volumes set for each divided sound signal.

[0085] The sound reproducing device 2 is connected by wire or wirelessly to the plurality of amplifiers themselves or to a hub (not shown) such as a communication device or a server so that a synthesized sound signal obtained by synthesizing the plurality of divided sound signals can be input to the amplifier 3. The sound reproducing device 2 may be communicably connected to the amplifier 3 via a network. The sound reproducing device 2 outputs a synthesized sound signal obtained by synthesizing the plurality of divided sound signals to the amplifier 3.

[0086] The amplifier 3 amplifies the synthesized sound signal input from the mixing unit 211 of the sound reproducing device 2 .

[0087] The amplifier 3 may be placed inside the room 100 or outside the room 100 .

[0088] The speaker 4 is disposed in the room 100, converts the composite sound signal amplified by the amplifier 3 into a composite sound, and emits the composite sound into the room 100. When the volume of the first divided sound signal is set to a predetermined volume by the first volume control unit 207, the speaker 4 emits the first divided sound at the predetermined volume. When the volume of the first divided sound signal is set to zero by the first volume control unit 207, the speaker 4 does not emit the first divided sound. When the volume of the second divided sound signal is set to a predetermined volume by the second volume control unit 208, the speaker 4 emits the second divided sound at the predetermined volume. When the volume of the second divided sound signal is set to zero by the second volume control unit 208, the speaker 4 does not emit the second divided sound. When the volume of the third divided sound signal is set to a predetermined volume by the third volume control unit 209, the speaker 4 emits the third divided sound at the predetermined volume. When the volume of the third divided sound signal is set to zero by the third volume control unit 209, the speaker 4 does not emit the third divided sound. When the volume of the fourth divided sound signal is set to a predetermined volume by the fourth volume control unit 210, the speaker 4 emits the fourth divided sound at the predetermined volume. When the volume of the fourth divided sound signal is set to zero by the fourth volume control unit 210, the speaker 4 does not emit the fourth divided sound.

[0089] Next, the sound reproduction process performed by the sound reproduction device 2 according to the first embodiment of the present disclosure will be described.

[0090] Figure 4 is a first flowchart for explaining the sound reproduction processing by the sound reproduction device 2 in embodiment 1 of the present disclosure, and Figure 5 is a second flowchart for explaining the sound reproduction processing by the sound reproduction device 2 in embodiment 1 of the present disclosure.

[0091] First, in step S1, the individual identification unit 204 determines whether or not a person has been detected by the person detection unit 201. If it is determined that a person has not been detected (NO in step S1), the determination process of step S1 is repeated.

[0092] On the other hand, if it is determined that a person has been detected (YES in step S1), in step S2, the personal identification unit 204 determines whether the first to fourth divided sound signals obtained by dividing a specified sound are being played.

[0093] If it is determined that the first to fourth divided sound signals are being reproduced (YES in step S2), the process proceeds to step S4.

[0094] On the other hand, if it is determined that the first to fourth divided sound signals are not being reproduced (NO in step S2), in step S3, the sound source reproduction unit 206 reproduces the first to fourth divided sound signals obtained by dividing the predetermined sound in a synchronized manner. At this time, the personal identification unit 204 outputs a reproduction start instruction to the sound source reproduction unit 206 to start reproduction of the predetermined sound. When the reproduction start instruction is input from the personal identification unit 204, the sound source reproduction unit 206 reads the first to fourth divided sound signals from the memory 205 and reproduces the read first to fourth divided sound signals in a synchronized manner. The sound source reproduction unit 206 outputs the reproduced first to fourth divided sound signals to the first volume control unit 207 to the fourth volume control unit 210, respectively.

[0095] When a conference is held in the room 100, the multiple people who will be participants in the conference are predetermined. This allows the sound source reproduction unit 206 to synchronously reproduce multiple divided sound signals when a person is detected. For example, when accepting a reservation for use of the room 100, the sound reproduction device 2 may accept input of information for identifying each of the multiple people who will use the room 100.

[0096] Next, in step S4, the individual identification unit 204 identifies each of the multiple people in the room 100 based on the image captured by the camera 1. The person detection unit 201 detects people from the image captured by the camera 1. The feature extraction unit 202 extracts facial features of the people detected by the person detection unit 201. The individual identification unit 204 compares the facial features extracted by the feature extraction unit 202 with each of the facial features of the multiple people stored in the personal information database 203. If there is a feature that matches the facial feature extracted by the feature extraction unit 202 among the facial features of the multiple people stored in the personal information database 203, the individual identification unit 204 reads out identification information associated with the feature from the personal information database 203 and identifies the person from the read identification information.

[0097] Next, in step S5, the individual identification unit 204 determines whether or not the first person 101 has been identified in the room 100. That is, the individual identification unit 204 determines whether or not the first person 101 is present in the room 100.

[0098] If it is determined that the first person 101 has been identified (YES in step S5), in step S6, the personal identification unit 204 determines the volume of the first divided sound signal associated with the first person 101 to be a predetermined volume. The predetermined volume is, for example, maximum volume. The personal identification unit 204 instructs the first volume control unit 207 to set the volume of the first divided sound signal determined to be the predetermined volume. The first volume control unit 207 sets the volume of the first divided sound signal to the predetermined volume based on the instruction from the personal identification unit 204. The first volume control unit 207 outputs the first divided sound signal with the volume set to the mixing unit 211.

[0099] On the other hand, if it is determined that the first person 101 has not been identified (NO in step S5), in step S7, the personal identification unit 204 determines the volume of the first divided sound signal associated with the first person 101 to be zero. The personal identification unit 204 instructs the first volume control unit 207 to set the volume of the first divided sound signal determined to be zero. The first volume control unit 207 sets the volume of the first divided sound signal to zero based on the instruction from the personal identification unit 204. The first volume control unit 207 outputs the first divided sound signal with the volume set to the mixing unit 211.

[0100] Next, in step S8, the individual identification unit 204 determines whether or not the second person 102 has been identified in the room 100. In other words, the individual identification unit 204 determines whether or not the second person 102 is present in the room 100.

[0101] If it is determined that the second person 102 has been identified (YES in step S8), in step S9, the personal identification unit 204 determines the volume of the second divided sound signal associated with the second person 102 to be a predetermined volume. The predetermined volume is, for example, maximum volume. The personal identification unit 204 instructs the second volume control unit 208 to set the volume of the second divided sound signal determined to be the predetermined volume. The second volume control unit 208 sets the volume of the second divided sound signal to the predetermined volume based on the instruction from the personal identification unit 204. The second volume control unit 208 outputs the second divided sound signal with the volume set to the mixing unit 211.

[0102] On the other hand, if it is determined that the second person 102 has not been identified (NO in step S8), in step S10, the personal identification unit 204 determines the volume of the second divided sound signal associated with the second person 102 to be zero. The personal identification unit 204 instructs the second volume control unit 208 of the volume of the second divided sound signal determined to be zero. The second volume control unit 208 sets the volume of the second divided sound signal to zero based on the instruction from the personal identification unit 204. The second volume control unit 208 outputs the second divided sound signal with the volume set to the mixing unit 211.

[0103] Next, in step S11, the individual identification unit 204 determines whether or not the third person 103 has been identified in the room 100. That is, the individual identification unit 204 determines whether or not the third person 103 is present in the room 100.

[0104] If it is determined that the third person 103 has been identified (YES in step S11), in step S12, the personal identification unit 204 determines the volume of the third divided sound signal associated with the third person 103 to be a predetermined volume. The predetermined volume is, for example, the maximum volume. The personal identification unit 204 instructs the third volume control unit 209 to set the volume of the third divided sound signal determined to be the predetermined volume. The third volume control unit 209 sets the volume of the third divided sound signal to the predetermined volume based on the instruction from the personal identification unit 204. The third volume control unit 209 outputs the third divided sound signal with the volume set to the mixing unit 211.

[0105] On the other hand, if it is determined that the third person 103 has not been identified (NO in step S11), in step S13, the personal identification unit 204 determines the volume of the third divided sound signal associated with the third person 103 to be zero. The personal identification unit 204 instructs the third volume control unit 209 to set the volume of the third divided sound signal determined to be zero. The third volume control unit 209 sets the volume of the third divided sound signal to zero based on the instruction from the personal identification unit 204. The third volume control unit 209 outputs the third divided sound signal with the volume set to the mixing unit 211.

[0106] Next, in step S14, the individual identification unit 204 determines whether or not the fourth person 104 has been identified in the room 100. In other words, the individual identification unit 204 determines whether or not the fourth person 104 is present in the room 100.

[0107] If it is determined that the fourth person 104 has been identified (YES in step S14), in step S15, the personal identification unit 204 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be a predetermined volume. The predetermined volume is, for example, the maximum volume. The personal identification unit 204 instructs the fourth volume control unit 210 of the volume of the fourth divided sound signal determined to be the predetermined volume. The fourth volume control unit 210 sets the volume of the fourth divided sound signal to the predetermined volume based on the instruction from the personal identification unit 204. The fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to the mixing unit 211.

[0108] On the other hand, if it is determined that the fourth person 104 has not been identified (NO in step S14), in step S16, the personal identification unit 204 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be zero. The personal identification unit 204 instructs the fourth volume control unit 210 of the volume of the fourth divided sound signal determined to be zero. The fourth volume control unit 210 sets the volume of the fourth divided sound signal to zero based on the instruction from the personal identification unit 204. The fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to the mixing unit 211.

[0109] Next, in step S17, the mixing unit 211 outputs a synthesized sound signal obtained by synthesizing the first to fourth divided sound signals, whose volumes have been set, to the amplifier 3. The amplifier 3 amplifies the synthesized sound signal and outputs the amplified synthesized sound signal to the speaker 4. The speaker 4 converts the synthesized sound signal into a synthesized sound, and emits the synthesized sound obtained by synthesizing the first to fourth divided sounds, whose volumes have been set by the first to fourth volume control units 207 to 210, into the room 100.

[0110] As a result, if a first person 101 is present in the room 100, the first divided sound is played from the speaker 4 at a predetermined volume, and if the first person 101 is not present in the room 100, the first divided sound is not played from the speaker 4. Furthermore, if a second person 102 is present in the room 100, the second divided sound is played from the speaker 4 at a predetermined volume, and if the second person 102 is not present in the room 100, the second divided sound is not played from the speaker 4. Furthermore, if a third person 103 is present in the room 100, the third divided sound is played from the speaker 4 at a predetermined volume, and if the third person 103 is not present in the room 100, the third divided sound is not played from the speaker 4. Furthermore, if a fourth person 104 is present in the room 100, the fourth divided sound is played from the speaker 4 at a predetermined volume, and if the fourth person 104 is not present in the room 100, the fourth divided sound is not played from the speaker 4.

[0111] In this way, when multiple people gather in room 100, multiple divided sounds overlap and a single harmonious predetermined sound is played. This allows multiple people to gather in room 100 and stimulate conversation among the multiple people in room 100. For example, when a meeting is held in room 100, it is possible to gather many people to participate in the meeting.

[0112] In the first embodiment, a person in a predetermined space is identified based on facial features of the person extracted from an image captured by camera 1, but the present disclosure is not particularly limited to this, and other identification methods may be used. For example, a person may be identified by a fingerprint, an iris, a voice feature (voiceprint), a hand movement or gesture, a body shape or outline, a beacon device using short-range wireless communication, or an ID card.

[0113] Furthermore, in the first embodiment, the individual identification unit 204 identifies a person in a predetermined space at predetermined intervals (for example, every minute), but is not limited to this. For example, if an ID card is used to identify a person, the person may be identified by reading the information on the ID card using a card reader or the like at the start of a meeting or when the person enters the predetermined space. Then, from the time the person is identified until the information on the ID card is read again using a card reader or the like at the end of the meeting or when the person leaves the predetermined space, the individual identification unit 204 may output a divided sound signal corresponding to the person, assuming that the person has been identified.

[0114] In addition, in a variant of this embodiment 1, the personal identification unit 204 may select one sound from a plurality of sounds of different types (genres), and instruct the sound source playback unit 206 to play multiple split sound signals obtained by splitting the selected sound.

[0115] For example, the types (genres) of sounds include jazz, pop, orchestral, and classical. The sound reproduction device 2 may accept a person's selection of one sound from a plurality of sounds of different types (genres). The individual identification unit 204 may then output a playback start instruction to the sound source reproduction unit 206 to start playing the sound selected by the person. The individual identification unit 204 may also select a sound that corresponds to the current time period from a plurality of sounds of different types (genres), and output a playback start instruction to the sound source reproduction unit 206 to start playing the selected sound.

[0116] Furthermore, each of the multiple sounds may be divided according to the performance part of the music to be played. For example, each of the multiple sounds may be divided into a first divided sound signal representing a melody part that plays the main melody, a second divided sound signal representing a harmony part that plays chords or a supporting melody to the melody part, a third divided sound signal representing a rhythm part that is responsible for the rhythm of the music, and a fourth divided sound signal representing a bass part that is responsible for the low-pitched parts.

[0117] Furthermore, each of the multiple sounds may be divided according to the type of instrument being played. For example, when the sound of "jazz" is selected, a first divided sound representing the sound of a drum, a second divided sound representing the sound of a bass, a third divided sound representing the sound of a keyboard, and a fourth divided sound representing the sound of a guitar may be emitted into the room 100.

[0118] Furthermore, one split sound signal may include sounds of multiple instruments, for example, a first split sound signal may include a bass sound and a guitar sound.

[0119] Furthermore, in the first embodiment, the sound source reproduction unit 206 may constantly reproduce a background sound signal different from the plurality of divided sound signals. The sound source reproduction unit 206 may output the background sound signal to a fifth volume control unit different from the first volume control unit 207 to the fourth volume control unit 210. The fifth volume control unit may set the volume of the background sound signal to a predetermined volume (for example, maximum volume). The mixing unit 211 may output a synthesized sound signal obtained by synthesizing the first divided sound signal, the second divided sound signal, the third divided sound signal, the fourth divided sound signal, and the background sound signal to the amplifier 3. The speaker 4 may constantly emit the background sound, and emit the first to fourth divided sounds superimposed on the background sound.

[0120] The background sound may be a natural sound such as the sound of wind, the sound of running water, the chirping of insects, or the singing of birds. Natural sounds have a calming effect on people, and constantly playing natural sounds in a given space can attract people to the given space.

[0121] The background sound may also be, for example, the sound of an instrument that covers the frequency band of the human voice. The frequency band of the sound of an electronic piano overlaps with the frequency band of the human voice, and the sound source playback unit 206 may constantly play the sound signal of the electronic piano as a background sound signal, separate from the multiple divided sound signals.

[0122] Furthermore, in the first embodiment, when a conference is held in room 100, the multiple people who are conference participants do not need to be predetermined. For example, if a person present in a predetermined space as a conference participant is registered in personal information database 203, a divided sound signal associated with that person is reproduced. On the other hand, if a conference participant is not registered in personal information database 203, one of the multiple divided sound signals, excluding a divided sound signal already associated as a divided sound signal for a person present in the predetermined space, may be reproduced as the divided sound signal for that person. Furthermore, the identification information of that person may be associated with the divided sound signal and registered in personal information database 203. In this case, the registered information of a person who was not initially registered in personal information database 203 may be deleted from personal information database 203 after a predetermined period of time. The predetermined period of time may be, for example, the period during which the conference is held, such as one day or several days.

[0123] (Embodiment 2) In the sound reproduction device 2 shown in embodiment 1, each of the multiple people is identified, and the volume of each of the multiple divided sound signals is controlled depending on whether each of the multiple people is identified or not, but in the sound reproduction device shown in embodiment 2, audio information indicating the average volume of the voice of each of the multiple people over a predetermined period is obtained, and the volume of each of the multiple divided sound signals is controlled depending on the audio information of each of the multiple people.

[0124] FIG. 6 is a diagram showing the overall configuration of a sound reproduction system according to the second embodiment, and FIG. 7 is a block diagram showing the configuration of a sound reproduction device 2A according to the second embodiment.

[0125] The sound reproduction system in the second embodiment includes a microphone 5, a sound reproduction device 2A, an amplifier 3, and a speaker 4. In the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and the description thereof will be omitted.

[0126] The microphone 5 collects sounds within a predetermined space. The microphone 5 is placed at a position where it can collect sounds within the predetermined space. The predetermined space is, for example, a room 100 such as a conference room where multiple people (a first person 101, a second person 102, a third person 103, and a fourth person 104) can gather. In the second embodiment, the microphone 5 collects the voices of the multiple people (the first person 101, the second person 102, the third person 103, and the fourth person 104) within the room 100.

[0127] The microphone 5 is connected by wire or wirelessly to the sound reproducing device 2A itself or to a hub (not shown) such as a communication device or a server so that collected audio can be input to the sound reproducing device 2A. The microphone 5 may be communicably connected to the sound reproducing device 2A via a network. The microphone 5 outputs collected audio to the sound reproducing device 2A.

[0128] The audio collected by the microphone 5 may be output in real time, or the audio may be recorded once in an external storage device such as a memory or a cloud server, and then the image may be output from that external storage device.

[0129] The sound reproduction device 2A acquires information about multiple people in a predetermined space, synchronizes and reproduces multiple divided sound signals obtained by dividing the predetermined sound, and outputs the multiple divided sound signals based on the information about the multiple people to a speaker that emits the multiple divided sounds converted from the multiple divided sound signals into the predetermined space. The sound reproduction device 2A detects the voices of multiple people (first person 101, second person 102, third person 103, and fourth person 104) present in the predetermined space (room 100) based on sounds collected by the microphone 5. The sound reproduction device 2A controls the volume of each of the multiple divided sound signals according to the average volume of the voice of each of the multiple people (first person 101, second person 102, third person 103, and fourth person 104) over a predetermined period. The sound reproduction device 2A changes the volume of each of the first to fourth divided sound signals according to the average volume of the voice of each of the multiple people (first person 101, second person 102, third person 103, and fourth person 104) over a predetermined period.

[0130] The sound reproduction device 2A includes at least a computer system including, for example, a control program, a processing circuit such as a processor or logic circuit that executes the control program, and a recording device such as an internal memory or an accessible external memory that stores the control program. Note that the sound reproduction device 2A may be realized, for example, by hardware implementation using the processing circuit, or by execution by the processing circuit of a software program stored in the memory or distributed from an external server, or by a combination of these hardware and software implementations.

[0131] The sound reproduction device 2A includes a speech detection unit 212, a feature extraction unit 202A, a speaker information database 213, a speaker estimation unit 214, a memory 205, a sound source reproduction unit 206, a first volume control unit 207, a second volume control unit 208, a third volume control unit 209, a fourth volume control unit 210, and a mixing unit 211.

[0132] The voice detection unit 212 detects the voice of a person in the room 100 based on the sound collected by the microphone 5 .

[0133] The feature extraction unit 202A extracts the feature amount of the person's voice detected by the voice detection unit 212.

[0134] The speaker information database 213 stores voice features of multiple people in association with identification information (user IDs) for identifying the multiple people. Here, a method for registering voice features of people in the speaker information database 213 will be described. First, a microphone collects audio containing the person's voice. Next, the person's voice is detected from the collected audio, and the feature values ​​of the detected person's voice are extracted. Next, the person's identification information is input using an input device such as a touch panel. Next, the voice features of the person and the person's identification information are stored in association with each other in the speaker information database 213.

[0135] The speaker information database 213 also stores identification information for identifying a plurality of people and their preferred musical instruments in association with each other.

[0136] The speaker estimation unit 214 outputs a playback start instruction to the sound source reproduction unit 206 to start playing back the predetermined sound. When the voice of a person is detected by the speech detection unit 212, the speaker estimation unit 214 outputs the playback start instruction to the sound source reproduction unit 206. Furthermore, when the voice of a person is no longer detected by the speech detection unit 212, the speaker estimation unit 214 may output a playback end instruction to the sound source reproduction unit 206 to end playing back the predetermined sound. Furthermore, when the voice of one of multiple people is identified, the speaker estimation unit 214 may output the playback start instruction to the sound source reproduction unit 206.

[0137] Furthermore, the speaker estimation unit 214 may select a sound corresponding to the current time period from among a plurality of different types of sounds, and output a playback start instruction to start playback of the selected sound to the sound source playback unit 206. For example, the speaker estimation unit 214 may select a sound corresponding to the current time period from among a first sound corresponding to the morning time period (8:00 AM to 12:00 AM), a second sound corresponding to the afternoon time period (12:00 AM to 6:00 PM), and a third sound corresponding to the evening time period (6:00 PM to 10:00 PM). Note that the time periods are not limited to those described above.

[0138] The speaker estimation unit 214 acquires information about a plurality of people present in a predetermined space. The speaker estimation unit 214 acquires audio information indicating the average volume of the voice of each of the plurality of people over a predetermined period. The speaker estimation unit 214 controls the volume of each of the plurality of divided sound signals in accordance with the audio information of each of the plurality of people.

[0139] The speaker estimation unit 214 estimates who is speaking the voice detected by the voice detection unit 212, and calculates the average volume of the estimated person's voice over a predetermined period of time. The speaker estimation unit 214 compares the voice feature extracted by the feature extraction unit 202A with each of the voice feature amounts of multiple people stored in the speaker information database 213. If there is a feature that matches the voice feature extracted by the feature extraction unit 202A among the voice feature amounts of the multiple people stored in the speaker information database 213, the speaker estimation unit 214 reads out identification information associated with the feature amount from the speaker information database 213, and estimates who is speaking from the read identification information.

[0140] The speaker estimation unit 214 may store the voice data of each of the plurality of people over a predetermined period of time in the past. The speaker estimation unit 214 may also store the voice volume data of each of the plurality of people over a predetermined period of time in the past.

[0141] The plurality of persons are associated in advance with the plurality of divided sound signals. The speaker estimation unit 214 refers to the speaker information database 213, extracts a favorite instrument corresponding to the user ID of the estimated speaker, and associates the divided sound signal corresponding to the extracted favorite instrument from among the plurality of divided sound signals as the divided sound signal of the speaker.

[0142] The speaker estimation unit 214 determines the volume of the first divided sound signal associated with the first person 101, who is speaking, in accordance with the average volume of the voice of the first person 101 over a predetermined period of time, and instructs the first volume control unit 207 about the determined volume. The speaker estimation unit 214 determines the volume of the second divided sound signal associated with the second person 102, who is speaking, in accordance with the average volume of the voice of the second person 102 over a predetermined period of time, and instructs the second volume control unit 208 about the determined volume. The speaker estimation unit 214 determines the volume of the third divided sound signal associated with the third person 103, who is speaking, in accordance with the average volume of the voice of the third person 103 over a predetermined period of time, and instructs the third volume control unit 209 about the determined volume. The speaker estimation unit 214 determines the volume of the fourth divided sound signal associated with the fourth person 104, who is speaking, in accordance with the average volume of the voice of the fourth person 104 over a predetermined period of time, and instructs the fourth volume control unit 210 about the determined volume.

[0143] If the average volume of the speaker's voice over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 determines the volume of the divided sound signal associated with the speaker to be a predetermined volume. The predetermined volume is, for example, maximum volume. Furthermore, if the average volume of the speaker's voice over a predetermined period of time is equal to or higher than a threshold, the speaker estimation unit 214 determines the volume of the divided sound signal associated with the speaker to be zero. Note that the predetermined volume is not limited to maximum volume and may be 50% or 80% of maximum volume, as long as it is greater than zero.

[0144] If the average volume of the voice of the first person 101 over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 determines the volume of the first divided sound signal associated with the first person 101 to be a predetermined volume. Furthermore, if the average volume of the voice of the first person 101 over a predetermined period of time is equal to or higher than a threshold, the speaker estimation unit 214 determines the volume of the first divided sound signal associated with the first person 101 to be zero.

[0145] If the average volume of the voice of the second person 102 over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 determines the volume of the second divided sound signal associated with the second person 102 to be a predetermined volume. Furthermore, if the average volume of the voice of the second person 102 over a predetermined period of time is equal to or higher than a threshold, the speaker estimation unit 214 determines the volume of the second divided sound signal associated with the second person 102 to be zero.

[0146] If the average volume of the voice of the third person 103 over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 determines the volume of the third divided sound signal associated with the third person 103 to be a predetermined volume. Furthermore, if the average volume of the voice of the third person 103 over a predetermined period of time is equal to or higher than a threshold, the speaker estimation unit 214 determines the volume of the third divided sound signal associated with the third person 103 to be zero.

[0147] If the average volume of the voice of the fourth person 104 over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be a predetermined volume. Furthermore, if the average volume of the voice of the fourth person 104 over a predetermined period of time is equal to or higher than a threshold, the speaker estimation unit 214 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be zero.

[0148] In the second embodiment, the number of people is four, but the present disclosure is not particularly limited to this, and the number of people may be two or more.

[0149] The sound source reproducing unit 206 starts reproducing a plurality of divided sound signals obtained by dividing a predetermined sound when a reproduction start instruction is input from the speaker estimation unit 214. Furthermore, the sound source reproducing unit 206 ends the reproduction of a plurality of divided sound signals obtained by dividing the predetermined sound when a reproduction end instruction is input from the speaker estimation unit 214.

[0150] The sound source reproduction unit 206 synchronously reproduces all of the first to fourth divided sound signals regardless of whether or not each of the first to fourth persons 101 to 104 is present in the room 100. In other words, if the voice of at least one of the first to fourth persons 101 to 104 is detected, the sound source reproduction unit 206 synchronously reproduces all of the first to fourth divided sound signals.

[0151] The first volume control section 207 to the fourth volume control section 210 control the volume of each of the plurality of divided sound signals in accordance with the average volume of the voice of each of the plurality of people over a predetermined period of time.

[0152] The first volume control unit 207 controls the volume of the first divided sound signal in accordance with the average volume of the voice of the first person 101 over a predetermined period of time. The first volume control unit 207 sets the volume of the first divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the speaker estimation unit 214.

[0153] The second volume control unit 208 controls the volume of the second divided sound signal in accordance with the average volume of the voice of the second person 102 over a predetermined period of time. The second volume control unit 208 sets the volume of the second divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the speaker estimation unit 214.

[0154] The third volume control unit 209 controls the volume of the third divided sound signal in accordance with the average volume of the voice of the third person 103 over a predetermined period of time. The third volume control unit 209 sets the volume of the third divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the speaker estimation unit 214.

[0155] The fourth volume control unit 210 controls the volume of the fourth divided sound signal in accordance with the average volume of the voice of the fourth person 104 over a predetermined period of time. The fourth volume control unit 210 sets the volume of the fourth divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the speaker estimation unit 214.

[0156] Next, a sound reproduction process performed by the sound reproduction device 2A according to the second embodiment of the present disclosure will be described.

[0157] Figure 8 is a first flowchart for explaining the sound reproduction processing by the sound reproduction device 2A in embodiment 2 of the present disclosure, and Figure 9 is a second flowchart for explaining the sound reproduction processing by the sound reproduction device 2A in embodiment 2 of the present disclosure.

[0158] First, in step S31, the speaker estimation unit 214 determines whether or not a human voice has been detected by the voice detection unit 212. If it is determined that a human voice has not been detected (NO in step S31), the determination process of step S31 is repeated.

[0159] On the other hand, if it is determined that a person's voice has been detected (YES in step S31), in step S32, the speaker estimation unit 214 determines whether the first to fourth divided sound signals obtained by dividing a specified sound are being played back.

[0160] If it is determined that the first to fourth divided sound signals are being reproduced (YES in step S32), the process proceeds to step S34.

[0161] On the other hand, if it is determined that the first to fourth divided sound signals are not being reproduced (NO in step S32), in step S33, the sound source reproduction unit 206 reproduces the first to fourth divided sound signals obtained by dividing the predetermined sound in a synchronized manner. At this time, the speaker estimation unit 214 outputs a reproduction start instruction to the sound source reproduction unit 206 to start reproduction of the predetermined sound. When the reproduction start instruction is input from the speaker estimation unit 214, the sound source reproduction unit 206 reads the first to fourth divided sound signals from the memory 205 and reproduces the read first to fourth divided sound signals in a synchronized manner. The sound source reproduction unit 206 outputs the reproduced first to fourth divided sound signals to the first volume control unit 207 to the fourth volume control unit 210, respectively.

[0162] Next, in step S34, the speaker estimation unit 214 estimates who is speaking the voice detected by the speech detection unit 212. The speaker estimation unit 214 compares the voice feature extracted by the feature extraction unit 202A with each of the voice feature amounts of multiple people stored in the speaker information database 213. If there is a feature amount that matches the voice feature amount extracted by the feature extraction unit 202A among the voice feature amounts of multiple people stored in the speaker information database 213, the speaker estimation unit 214 reads out identification information associated with the feature amount from the speaker information database 213 and estimates who is speaking from the read identification information.

[0163] Next, in step S35, the speaker estimation unit 214 calculates the average volume of the voice of each of the multiple people over a predetermined period of time. For example, the speaker estimation unit 214 calculates the average volume of the voice over a period from the current time to one minute ago.

[0164] Next, in step S36, the speaker estimation unit 214 determines whether the average volume of the voice of the first person 101 over a predetermined period is smaller than a threshold value.

[0165] If it is determined that the average volume of the voice of the first person 101 over the predetermined period is lower than the threshold (YES in step S36), then in step S37 the speaker estimation unit 214 determines the volume of the first divided sound signal associated with the first person 101 to be a predetermined volume. The predetermined volume is, for example, maximum volume. The speaker estimation unit 214 instructs the first volume control unit 207 of the volume of the first divided sound signal determined to be the predetermined volume. The first volume control unit 207 sets the volume of the first divided sound signal to the predetermined volume based on the instruction from the speaker estimation unit 214. The first volume control unit 207 outputs the first divided sound signal with the volume set to the mixing unit 211.

[0166] On the other hand, if it is determined that the average volume of the voice of the first person 101 over the predetermined period is equal to or greater than the threshold value (NO in step S36), then in step S38 the speaker estimation unit 214 sets the volume of the first divided sound signal associated with the first person 101 to zero. The speaker estimation unit 214 instructs the first volume control unit 207 of the volume of the first divided sound signal that has been set to zero. The first volume control unit 207 sets the volume of the first divided sound signal to zero based on the instruction from the speaker estimation unit 214. The first volume control unit 207 outputs the first divided sound signal with the volume set to the mixing unit 211.

[0167] Next, in step S39, the speaker estimation unit 214 determines whether the average volume of the voice of the second person 102 over a predetermined period is smaller than a threshold value.

[0168] If it is determined that the average volume of the voice of the second person 102 over the predetermined period is lower than the threshold (YES in step S39), then in step S40 the speaker estimation unit 214 determines the volume of the second divided sound signal associated with the second person 102 to be a predetermined volume. The predetermined volume is, for example, maximum volume. The speaker estimation unit 214 instructs the second volume control unit 208 of the volume of the second divided sound signal determined to be the predetermined volume. The second volume control unit 208 sets the volume of the second divided sound signal to the predetermined volume based on the instruction from the speaker estimation unit 214. The second volume control unit 208 outputs the second divided sound signal with the volume set to the mixing unit 211.

[0169] On the other hand, if it is determined that the average volume of the voice of the second person 102 over the predetermined period is equal to or greater than the threshold value (NO in step S39), in step S41, the speaker estimation unit 214 determines the volume of the second divided sound signal associated with the second person 102 to be zero. The speaker estimation unit 214 instructs the second volume control unit 208 of the volume of the second divided sound signal determined to be zero. The second volume control unit 208 sets the volume of the second divided sound signal to zero based on the instruction from the speaker estimation unit 214. The second volume control unit 208 outputs the second divided sound signal with the volume set to the mixing unit 211.

[0170] Next, in step S42, the speaker estimation unit 214 determines whether the average volume of the voice of the third person 103 over a predetermined period is smaller than a threshold value.

[0171] If it is determined that the average volume of the voice of the third person 103 over the predetermined period is lower than the threshold (YES in step S42), then in step S43 the speaker estimation unit 214 determines the volume of the third divided sound signal associated with the third person 103 to be a predetermined volume. The predetermined volume is, for example, maximum volume. The speaker estimation unit 214 instructs the third volume control unit 209 to set the volume of the third divided sound signal determined to be the predetermined volume. Based on the instruction from the speaker estimation unit 214, the third volume control unit 209 sets the volume of the third divided sound signal to the predetermined volume. The third volume control unit 209 outputs the third divided sound signal with the volume set to the mixing unit 211.

[0172] On the other hand, if it is determined that the average volume of the voice of the third person 103 over the predetermined period is equal to or greater than the threshold value (NO in step S42), in step S44, the speaker estimation unit 214 determines the volume of the third divided sound signal associated with the third person 103 to be zero. The speaker estimation unit 214 instructs the third volume control unit 209 of the volume of the third divided sound signal determined to be zero. The third volume control unit 209 sets the volume of the third divided sound signal to zero based on the instruction from the speaker estimation unit 214. The third volume control unit 209 outputs the third divided sound signal with the volume set to the mixing unit 211.

[0173] Next, in step S45, the speaker estimation unit 214 determines whether the average volume of the voice of the fourth person 104 over a predetermined period is smaller than a threshold value.

[0174] If it is determined that the average volume of the voice of the fourth person 104 over the predetermined period is lower than the threshold (YES in step S45), then in step S46 the speaker estimation unit 214 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be a predetermined volume. The predetermined volume is, for example, maximum volume. The speaker estimation unit 214 instructs the fourth volume control unit 210 of the volume of the fourth divided sound signal determined to be the predetermined volume. The fourth volume control unit 210 sets the volume of the fourth divided sound signal to the predetermined volume based on the instruction from the speaker estimation unit 214. The fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to the mixing unit 211.

[0175] On the other hand, if it is determined that the average volume of the voice of the fourth person 104 over the predetermined period is equal to or greater than the threshold value (NO in step S45), in step S47, the speaker estimation unit 214 determines the volume of the fourth divided sound signal associated with the fourth person 104 to be zero. The speaker estimation unit 214 instructs the fourth volume control unit 210 of the volume of the fourth divided sound signal determined to be zero. The fourth volume control unit 210 sets the volume of the fourth divided sound signal to zero based on the instruction from the speaker estimation unit 214. The fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to the mixing unit 211.

[0176] Next, in step S48, the mixing unit 211 outputs a synthesized sound signal obtained by synthesizing the first to fourth divided sound signals, whose volumes have been set, to the amplifier 3. The amplifier 3 amplifies the synthesized sound signal and outputs the amplified synthesized sound signal to the speaker 4. The speaker 4 converts the synthesized sound signal into a synthesized sound, and emits the synthesized sound obtained by synthesizing the first to fourth divided sounds, whose volumes have been set by the first to fourth volume control units 207 to 210, into the room 100.

[0177] As a result, if the average volume of the first person's 101 voice over a predetermined period of time is lower than the threshold, the first divided sound is output from the speaker 4 at a predetermined volume, but if the average volume of the first person's 101 voice over a predetermined period of time is equal to or higher than the threshold, the first divided sound is not output from the speaker 4. Also, if the average volume of the second person's 102 voice over a predetermined period of time is lower than the threshold, the second divided sound is output from the speaker 4 at a predetermined volume, but if the average volume of the second person's 102 voice over a predetermined period of time is equal to or higher than the threshold, the second divided sound is not output from the speaker 4. Also, if the average volume of the third person's 103 voice over a predetermined period of time is lower than the threshold, the third divided sound is output from the speaker 4 at a predetermined volume, but if the average volume of the third person's 103 voice over a predetermined period of time is equal to or higher than the threshold, the third divided sound is not output from the speaker 4. Furthermore, if the average volume of the voice of the fourth person 104 in a predetermined period is smaller than the threshold value, the fourth divided sound of a predetermined volume is played from the speaker 4, and if the average volume of the voice of the fourth person 104 in a predetermined period is equal to or larger than the threshold value, the fourth divided sound is not played from the speaker 4.

[0178] The average volume of the voice over a predetermined period can also be said to be the amount of speech a person makes. In this way, if a person speaks little, the divided sounds associated with that person are played, and if a person speaks a lot, the divided sounds associated with that person are not played. This makes it possible to make a person who speaks little aware of their low speech volume and encourage them to speak more.

[0179] The speaker estimation unit 214 may select a predetermined sound according to the average volume of the voices of all of the multiple people over a predetermined period of time. If the average volume of the voices of all of the multiple people over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 may select music with a fast tempo such that the BPM (Beats Per Minute) is equal to or higher than a threshold. This makes it possible to provide a sound environment in which multiple people can easily converse. Furthermore, if the average volume of the voices of all of the multiple people over a predetermined period of time is equal to or higher than a threshold, the speaker estimation unit 214 may select music with a slow tempo such that the BPM is lower than the threshold. This makes it possible to provide a sound environment in which multiple people can converse calmly.

[0180] Note that, if the average volume of the speaker's voice over a predetermined period of time is equal to or greater than a threshold, the speaker estimation unit 214 may determine the volume of the divided sound signal associated with the speaker to be a predetermined volume. The predetermined volume may be, for example, maximum volume. Also, if the average volume of the speaker's voice over a predetermined period of time is lower than a threshold, the speaker estimation unit 214 may determine the volume of the divided sound signal associated with the speaker to be zero. Note that the predetermined volume is not limited to maximum volume, and may be 50% or 80% of the maximum volume, as long as it is greater than zero. For example, this causes the volume of the divided sound signal of a person who has been silent for a while to be set to zero, thereby encouraging the person who has been silent for a while to speak.

[0181] Third Embodiment In a sound reproduction device according to a third embodiment, posture information relating to the posture of each of a plurality of people is acquired, and the volume of each of a plurality of divided sound signals is controlled in accordance with the posture of each of the plurality of people.

[0182] FIG. 10 is a diagram showing the overall configuration of a sound reproduction system according to the third embodiment, and FIG. 11 is a block diagram showing the configuration of a sound reproduction device 2B according to the third embodiment.

[0183] The sound reproduction system in the third embodiment includes a camera 1, a sound reproduction device 2B, an amplifier 3, and a speaker 4. In the third embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and the description thereof will be omitted.

[0184] In the third embodiment, each of the multiple divided sound signals is associated with a respective one of multiple positions in a predetermined space where multiple people are present. The predetermined space is, for example, a room 100 such as a conference room where multiple people can gather. The predetermined space includes multiple positions. For example, each of the multiple positions is a position where a person is seated. The room 100 includes a first position 111, a second position 112, a third position 113, and a fourth position 114. The positions where multiple people are seated are not fixed. One person is present at each position.

[0185] Camera 1 captures an image of a predetermined space including a plurality of positions. Camera 1 is a fixed camera such as a surveillance camera, and is placed in a position where it can capture the entirety of the plurality of positions. In the third embodiment, the predetermined space includes four positions, but the present disclosure is not particularly limited to this, and may include two or more positions. In the third embodiment, camera 1 captures images of a first position 111, a second position 112, a third position 113, and a fourth position 114.

[0186] The sound reproduction device 2B acquires information about multiple people in a predetermined space, synchronizes and reproduces multiple divided sound signals obtained by dividing the predetermined sound, and outputs the multiple divided sound signals based on the information about the multiple people to speakers that emit the multiple divided sounds converted from the multiple divided sound signals into the predetermined space. The sound reproduction device 2B detects people at each of multiple positions (first position 111, second position 112, third position 113, and fourth position 114) in the predetermined space (room 100) based on images captured by the camera 1. The sound reproduction device 2B controls the volume of each of the multiple divided sound signals in accordance with the posture of each of the multiple people. The sound reproduction device 2B changes the volume of each of the first to fourth divided sound signals in accordance with the posture of the people at each of the first position 111, second position 112, third position 113, and fourth position 114. For example, the sound reproducing device 2B estimates the standing and sitting postures of people at the first position 111, the second position 112, the third position 113, and the fourth position 114, respectively.

[0187] The sound reproduction device 2B includes at least a computer system including, for example, a control program, a processing circuit such as a processor or logic circuit that executes the control program, and a recording device such as an internal memory or an accessible external memory that stores the control program. Note that the sound reproduction device 2B may be realized, for example, by hardware implementation using the processing circuit, or by execution by the processing circuit of a software program stored in the memory or distributed from an external server, or by a combination of these hardware and software implementations.

[0188] The sound reproduction device 2B includes a person detection unit 201B, a feature extraction unit 202B, a posture information database 215, a posture estimation unit 216, a memory 205, a sound source reproduction unit 206, a first volume control unit 207, a second volume control unit 208, a third volume control unit 209, a fourth volume control unit 210, and a mixing unit 211.

[0189] The person detection unit 201B detects people present at each of a plurality of positions in the room 100 based on the image captured by the camera 1. The plurality of positions are determined in advance. Therefore, the person detection unit 201B detects people present in areas corresponding to each of the plurality of positions in the image.

[0190] The feature extraction unit 202B extracts the feature amount of the body of the person detected by the person detection unit 201.

[0191] The posture information database 215 stores a plurality of body feature amounts and posture information in association with each other. Here, a method for registering a person's body feature amounts in the posture information database 215 will be described. First, a person is photographed by a camera. Next, the person is detected from the photographed image, and the body feature amounts of the detected person are extracted. Next, the person's posture information is input by an input device such as a touch panel. Next, the person's body feature amounts and the person's posture information are stored in association with each other in the posture information database 215.

[0192] For example, when estimating whether a person is standing or sitting, the body feature amounts of the standing person and the body feature amounts of the sitting person are extracted. The body feature amounts of the standing person are associated with posture information indicating that the person is standing, and the body feature amounts of the sitting person are associated with posture information indicating that the person is sitting, and these are stored in the posture information database 215.

[0193] Posture estimation unit 216 outputs a playback start instruction to start playback of a predetermined sound to sound source playback unit 206. When a person is detected at any of the multiple positions by person detection unit 201B, posture estimation unit 216 outputs the playback start instruction to sound source playback unit 206. Furthermore, when a person is no longer detected at any of the multiple positions by person detection unit 201B, posture estimation unit 216 may output a playback end instruction to sound source playback unit 206 to end playback of the predetermined sound.

[0194] Furthermore, the posture estimation unit 216 may select a sound corresponding to the current time period from among a plurality of different types of sounds, and output a playback start instruction to start playback of the selected sound to the sound source playback unit 206. For example, the posture estimation unit 216 may select a sound corresponding to the current time period from among a first sound corresponding to the morning time period (8:00 AM to 12:00 AM), a second sound corresponding to the afternoon time period (12:00 AM to 6:00 PM), and a third sound corresponding to the evening time period (6:00 PM to 10:00 PM). Note that the time periods are not limited to those described above.

[0195] The posture estimation unit 216 acquires information about a plurality of people present in a predetermined space. The information about the plurality of people includes posture information about the posture of each of the plurality of people. The posture estimation unit 216 estimates the posture of each of the plurality of people. The posture estimation unit 216 controls the volume of each of the plurality of divided sound signals in accordance with the posture information of each of the plurality of people.

[0196] Posture estimation unit 216 compares the body feature amount extracted by feature extraction unit 202B with each of the plurality of body feature amounts stored in posture information database 215. If there is a feature amount that matches the body feature amount extracted by feature extraction unit 202B among the plurality of body feature amounts stored in posture information database 215, posture estimation unit 216 reads out posture information associated with the feature amount from posture information database 215, and estimates the posture of the person from the read posture information.

[0197] Note that posture estimation unit 216 may input the body feature amounts of the person extracted by feature extraction unit 202B into a posture estimation model and acquire the posture of the person from the posture estimation model. The posture estimation model is created by machine learning using the body feature amounts of the person and the posture of the person as training data. When the body feature amounts of the person extracted by feature extraction unit 202B are input into the posture estimation model, the posture estimation model outputs the posture of the person.

[0198] The posture information in the third embodiment indicates whether each of the plurality of people is standing or not. The posture estimation unit 216 estimates whether the person at each of the plurality of positions is standing or sitting.

[0199] The plurality of divided sound signals are respectively associated with a plurality of positions in a predetermined space where a plurality of people are present. The first divided sound signal is associated with a first position 111, the second divided sound signal is associated with a second position 112, the third divided sound signal is associated with a third position 113, and the fourth divided sound signal is associated with a fourth position 114.

[0200] The posture estimation unit 216 determines the volume of the first divided sound signal associated with the first position 111 in accordance with the posture of the person at the first position 111 in the room 100, and notifies the first volume control unit 207 of the determined volume. The posture estimation unit 216 determines the volume of the second divided sound signal associated with the second position 112 in accordance with the posture of the person at the second position 112 in the room 100, and notifies the second volume control unit 208 of the determined volume. The posture estimation unit 216 determines the volume of the third divided sound signal associated with the third position 113 in accordance with the posture of the person at the third position 113 in the room 100, and notifies the third volume control unit 209 of the determined volume. The posture estimation unit 216 determines the volume of the fourth divided sound signal associated with the fourth position 114 in accordance with the posture of the person at the fourth position 114 in the room 100, and notifies the fourth volume control unit 210 of the determined volume.

[0201] When the person is standing, the posture estimation unit 216 determines the volume of the divided sound signal to be a predetermined volume. The predetermined volume is, for example, maximum volume. When the person is not standing, the posture estimation unit 216 determines the volume of the divided sound signal to be zero. Note that the predetermined volume is not limited to maximum volume, and may be 50% or 80% of maximum volume, as long as it is greater than zero.

[0202] When the person at first position 111 in room 100 is standing, posture estimation unit 216 determines the volume of the first divided sound signal associated with first position 111 to be a predetermined volume. Furthermore, when the person at first position 111 in room 100 is not standing, i.e., when the person at first position 111 in room 100 is sitting, posture estimation unit 216 determines the volume of the first divided sound signal associated with first position 111 to be zero.

[0203] When the person at second position 112 in room 100 is standing, posture estimation unit 216 determines the volume of the second divided sound signal associated with second position 112 to be a predetermined volume. Furthermore, when the person at second position 112 in room 100 is not standing, i.e., when the person at second position 112 in room 100 is sitting, posture estimation unit 216 determines the volume of the second divided sound signal associated with second position 112 to be zero.

[0204] When the person at third position 113 in room 100 is standing, posture estimation unit 216 determines the volume of the third divided sound signal associated with third position 113 to be a predetermined volume. Furthermore, when the person at third position 113 in room 100 is not standing, that is, when the person at third position 113 in room 100 is sitting, posture estimation unit 216 determines the volume of the third divided sound signal associated with third position 113 to be zero.

[0205] When the person at fourth position 114 in room 100 is standing, posture estimation unit 216 determines the volume of the fourth divided sound signal associated with fourth position 114 to be a predetermined volume. Furthermore, when the person at fourth position 114 in room 100 is not standing, i.e., when the person at fourth position 114 in room 100 is sitting, posture estimation unit 216 determines the volume of the fourth divided sound signal associated with fourth position 114 to be zero.

[0206] If no person is present at each position in the room 100, the posture estimation unit 216 determines the volume of the divided sound signal associated with each position to be zero.

[0207] In addition, although the number of positions is four in the third embodiment, the present disclosure is not particularly limited to this, and the number of positions may be two or more. Furthermore, the number of the plurality of divided sound signals may be the same as the number of the plurality of positions, or may be different from the number of the plurality of positions.

[0208] Furthermore, in the third embodiment, the posture estimation unit 216 estimates whether the person is standing or sitting, but the present disclosure is not particularly limited to this, and the posture estimation unit 216 may estimate only the standing posture of the person. That is, if the person is standing, the posture estimation unit 216 may determine the volume of the divided sound signal to be a predetermined volume, and if the person is not standing, the posture estimation unit 216 may determine the volume of the divided sound signal to be zero.

[0209] When a playback start instruction is input from the posture estimation unit 216, the sound source playback unit 206 starts playing back a plurality of divided sound signals obtained by dividing a predetermined sound. When a playback end instruction is input from the posture estimation unit 216, the sound source playback unit 206 ends playing back the plurality of divided sound signals obtained by dividing the predetermined sound.

[0210] The sound source reproduction unit 206 reproduces all of the first to fourth divided sound signals in synchronization with each other, regardless of whether or not a person is present at the first to fourth positions 111 to 114 in the room 100. In other words, if a person is detected at at least one of the first to fourth positions 111 to 114, the sound source reproduction unit 206 reproduces all of the first to fourth divided sound signals in synchronization with each other.

[0211] The first volume control unit 207 to the fourth volume control unit 210 control the volume of each of the plurality of divided sound signals in accordance with the posture of each of the plurality of people.

[0212] The first volume control unit 207 controls the volume of the first divided sound signal depending on the posture of the person at the first position 111. That is, the first volume control unit 207 controls the volume of the first divided sound signal depending on whether the person at the first position 111 is standing or not. The first volume control unit 207 sets the volume of the first divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216.

[0213] The second volume control unit 208 controls the volume of the second divided sound signal depending on the posture of the person at the second position 112. That is, the second volume control unit 208 controls the volume of the second divided sound signal depending on whether the person at the second position 112 is standing or not. The second volume control unit 208 sets the volume of the second divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216.

[0214] The third volume control unit 209 controls the volume of the third divided sound signal depending on the posture of the person at the third position 113. That is, the third volume control unit 209 controls the volume of the third divided sound signal depending on whether the person at the third position 113 is standing or not. The third volume control unit 209 sets the volume of the third divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216.

[0215] The fourth volume control unit 210 controls the volume of the fourth divided sound signal depending on the posture of the person at the fourth position 114. That is, the fourth volume control unit 210 controls the volume of the fourth divided sound signal depending on whether the person at the fourth position 114 is standing or not. The fourth volume control unit 210 sets the volume of the fourth divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216.

[0216] Next, a sound reproduction process performed by the sound reproduction device 2B according to the third embodiment of the present disclosure will be described.

[0217] Figure 12 is a first flowchart for explaining the sound reproduction processing by the sound reproduction device 2B in embodiment 3 of the present disclosure, and Figure 13 is a second flowchart for explaining the sound reproduction processing by the sound reproduction device 2B in embodiment 3 of the present disclosure.

[0218] First, in step S61, posture estimation unit 216 determines whether or not a person has been detected at any of the multiple positions by person detection unit 201B. If it is determined that a person has not been detected at any of the multiple positions (NO in step S61), the determination process of step S61 is repeated.

[0219] On the other hand, if it is determined that a person has been detected at any of the multiple positions (YES in step S61), in step S62, the posture estimation unit 216 determines whether the first to fourth divided sound signals obtained by dividing a specified sound are being played.

[0220] If it is determined that the first to fourth divided sound signals are being reproduced (YES in step S62), the process proceeds to step S64.

[0221] On the other hand, if it is determined that the first to fourth divided sound signals are not being reproduced (NO in step S62), in step S63, the sound source reproduction unit 206 reproduces the first to fourth divided sound signals obtained by dividing the predetermined sound in synchronization with each other. At this time, the posture estimation unit 216 outputs a reproduction start instruction to the sound source reproduction unit 206 to start reproduction of the predetermined sound. When the reproduction start instruction is input from the posture estimation unit 216, the sound source reproduction unit 206 reads the first to fourth divided sound signals from the memory 205 and reproduces the read first to fourth divided sound signals in synchronization with each other. The sound source reproduction unit 206 outputs the reproduced first to fourth divided sound signals to the first volume control unit 207 to the fourth volume control unit 210, respectively.

[0222] Next, in step S64, posture estimation unit 216 estimates the postures of the people at first position 111 to fourth position 114 in room 100 based on the images captured by camera 1. More specifically, posture estimation unit 216 estimates whether the people at first position 111 to fourth position 114 in room 100 are standing.

[0223] Person detection unit 201B detects persons at first position 111 to fourth position 114 from images captured by camera 1. Feature extraction unit 202B extracts body features of the persons detected by person detection unit 201B. Posture estimation unit 216 compares the body features extracted by feature extraction unit 202B with each of a plurality of body features stored in posture information database 215. If there is a feature that matches the body feature extracted by feature extraction unit 202B among the plurality of body features stored in posture information database 215, posture estimation unit 216 reads out posture information associated with the feature from posture information database 215 and estimates the posture of the person from the read posture information.

[0224] Next, in step S65, the posture estimation unit 216 determines whether or not a person is present at the first position 111 in the room 100.

[0225] If it is determined that no person is present at the first position 111 (NO in step S65), the process proceeds to step S68.

[0226] On the other hand, if it is determined that a person is present at first position 111 (YES in step S65), in step S66, posture estimation unit 216 determines whether the person at first position 111 in room 100 is standing.

[0227] If it is determined that the person at first position 111 is standing (YES in step S66), then in step S67, posture estimation unit 216 determines the volume of the first divided sound signal associated with first position 111 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216 instructs first volume control unit 207 of the volume of the first divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216, first volume control unit 207 sets the volume of the first divided sound signal to the predetermined volume. First volume control unit 207 outputs the first divided sound signal with the set volume to mixing unit 211.

[0228] On the other hand, if it is determined that the person at first position 111 is not standing, that is, if it is determined that the person at first position 111 is sitting (NO in step S66), then in step S68, posture estimation unit 216 determines the volume of the first divided sound signal associated with first position 111 to be zero. Posture estimation unit 216 instructs first volume control unit 207 of the volume of the first divided sound signal that has been determined to be zero. First volume control unit 207 sets the volume of the first divided sound signal to zero based on the instruction from posture estimation unit 216. First volume control unit 207 outputs the first divided sound signal with the volume set to mixing unit 211.

[0229] Next, in step S69, the posture estimation unit 216 determines whether or not a person is present at the second position 112 in the room 100.

[0230] If it is determined that no person is present at the second position 112 (NO in step S69), the process proceeds to step S72.

[0231] On the other hand, if it is determined that a person is present at second position 112 (YES in step S69), in step S70, posture estimation unit 216 determines whether the person at second position 112 in room 100 is standing.

[0232] If it is determined that the person at second position 112 is standing (YES in step S70), then in step S71, posture estimation unit 216 determines the volume of the second divided sound signal associated with second position 112 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216 instructs second volume control unit 208 of the volume of the second divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216, second volume control unit 208 sets the volume of the second divided sound signal to the predetermined volume. Second volume control unit 208 outputs the second divided sound signal with the set volume to mixing unit 211.

[0233] On the other hand, if it is determined that the person at second position 112 is not standing, that is, if it is determined that the person at second position 112 is sitting (NO in step S70), in step S72, posture estimation unit 216 determines the volume of the second divided sound signal associated with second position 112 to be zero. Posture estimation unit 216 instructs second volume control unit 208 of the volume of the second divided sound signal determined to be zero. Second volume control unit 208 sets the volume of the second divided sound signal to zero based on the instruction from posture estimation unit 216. Second volume control unit 208 outputs the second divided sound signal with the set volume to mixing unit 211.

[0234] Next, in step S73, the posture estimation unit 216 determines whether or not a person is present at the third position 113 in the room 100.

[0235] If it is determined that no person is present at the third position 113 (NO in step S73), the process proceeds to step S76.

[0236] On the other hand, if it is determined that a person is present at the third position 113 (YES in step S73), in step S74, the posture estimation unit 216 determines whether the person at the third position 113 in the room 100 is standing.

[0237] If it is determined that the person at third position 113 is standing (YES in step S74), then in step S75, posture estimation unit 216 determines the volume of the third divided sound signal associated with third position 113 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216 instructs third volume control unit 209 of the volume of the third divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216, third volume control unit 209 sets the volume of the third divided sound signal to the predetermined volume. Third volume control unit 209 outputs the third divided sound signal with the set volume to mixing unit 211.

[0238] On the other hand, if it is determined that the person at third position 113 is not standing, that is, if it is determined that the person at third position 113 is sitting (NO in step S74), in step S76, posture estimation unit 216 determines the volume of the third divided sound signal associated with third position 113 to be zero. Posture estimation unit 216 instructs third volume control unit 209 of the volume of the third divided sound signal that has been determined to be zero. Based on the instruction from posture estimation unit 216, third volume control unit 209 sets the volume of the third divided sound signal to zero. Third volume control unit 209 outputs the third divided sound signal with the volume set to mixing unit 211.

[0239] Next, in step S77, the posture estimation unit 216 determines whether or not a person is present at the fourth position 114 in the room 100.

[0240] If it is determined that no person is present at the fourth position 114 (NO in step S77), the process proceeds to step S80.

[0241] On the other hand, if it is determined that a person is present at the fourth position 114 (YES in step S77), in step S78, the posture estimation unit 216 determines whether the person at the fourth position 114 in the room 100 is standing.

[0242] If it is determined that the person at fourth position 114 is standing (YES in step S78), then in step S79, posture estimation unit 216 determines the volume of the fourth divided sound signal associated with fourth position 114 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216 instructs fourth volume control unit 210 of the volume of the fourth divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216, fourth volume control unit 210 sets the volume of the fourth divided sound signal to the predetermined volume. Fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to mixing unit 211.

[0243] On the other hand, if it is determined that the person at fourth position 114 is not standing, that is, if it is determined that the person at fourth position 114 is sitting (NO in step S78), then in step S80, posture estimation unit 216 determines the volume of the fourth divided sound signal associated with fourth position 114 to be zero. Posture estimation unit 216 instructs fourth volume control unit 210 of the volume of the fourth divided sound signal that has been determined to be zero. Fourth volume control unit 210 sets the volume of the fourth divided sound signal to zero based on the instruction from posture estimation unit 216. Fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to mixing unit 211.

[0244] Next, in step S81, the mixing unit 211 outputs a synthesized sound signal obtained by synthesizing the first to fourth divided sound signals, whose volumes have been set, to the amplifier 3. The amplifier 3 amplifies the synthesized sound signal and outputs the amplified synthesized sound signal to the speaker 4. The speaker 4 converts the synthesized sound signal into a synthesized sound, and emits the synthesized sound obtained by synthesizing the first to fourth divided sounds, whose volumes have been set by the first to fourth volume control units 207 to 210, into the room 100.

[0245] As a result, if a person at first position 111 is standing, the first divided sound is played from speaker 4 at a predetermined volume, and if the person at first position 111 is sitting, the first divided sound is not played from speaker 4. Also, if a person at second position 112 is standing, the second divided sound is played from speaker 4 at a predetermined volume, and if the person at second position 112 is sitting, the second divided sound is not played from speaker 4. Also, if a person at third position 113 is standing, the third divided sound is played from speaker 4 at a predetermined volume, and if the person at third position 113 is sitting, the third divided sound is not played from speaker 4. Also, if a person at fourth position 114 is standing, the fourth divided sound is played from speaker 4 at a predetermined volume, and if the person at fourth position 114 is sitting, the fourth divided sound is not played from speaker 4.

[0246] In this way, if a person at each position is standing, the divided sound is increased to make the specified space an environment where multiple people can easily gather, and if a person at each position is sitting, the divided sound is decreased to make the specified space an environment where it is easy to have a conversation.

[0247] In the third embodiment, the posture of a person in a predetermined space is estimated based on the feature amounts of the person's body extracted from an image captured by camera 1, but the present disclosure is not limited to this, and other estimation methods may be used. For example, the posture of a person may be estimated using a distance measured by an ultrasonic sensor, a distance or a shape measured by a laser sensor such as LiDAR (Light Detection and Ranging), an acceleration measured by an acceleration sensor, a pressure value measured by a pressure sensor, or a distance measured by an infrared sensor.

[0248] (Embodiment 4) In a sound reproduction device shown in embodiment 4, posture information relating to the posture of each of a plurality of people is acquired, and the volume of each of a plurality of divided sound signals is controlled in accordance with the posture information of each of the plurality of people. The posture information in embodiment 4 indicates whether each of the plurality of people is sitting at each of a plurality of positions in a predetermined space, and indicates whether at least one of the plurality of people is in a posture that makes them feel sleepy.

[0249] FIG. 14 is a diagram showing the overall configuration of a sound reproduction system according to the fourth embodiment, and FIG. 15 is a block diagram showing the configuration of a sound reproduction device 2C according to the fourth embodiment.

[0250] The sound reproduction system of the fourth embodiment includes a camera 1, a sound reproduction device 2C, an amplifier 3, and a speaker 4. In the fourth embodiment, the same components as those in the first and third embodiments are denoted by the same reference numerals, and the description thereof will be omitted.

[0251] In the fourth embodiment, the predetermined space is, for example, a room 100 such as a conference room where multiple people can gather. The predetermined space includes multiple positions. For example, each of the multiple positions is a position where a person is seated. The room 100 includes a first position 111, a second position 112, and a third position 113. The positions where multiple people are seated are not fixed. One person is present at one position.

[0252] In the fourth embodiment, the predetermined space includes three positions, but the present disclosure is not particularly limited thereto, and the predetermined space may include two or more positions. In the fourth embodiment, the camera 1 captures images of the first position 111, the second position 112, and the third position 113.

[0253] The sound reproduction device 2C acquires information about multiple people in a predetermined space, synchronizes and reproduces multiple divided sound signals obtained by dividing the predetermined sound, and outputs the multiple divided sound signals based on the information about the multiple people to a speaker 4, which emits the multiple divided sounds converted from the multiple divided sound signals into the predetermined space. The sound reproduction device 2C detects people at each of multiple positions (first position 111, second position 112, and third position 113) in the predetermined space (room 100) based on images captured by a camera 1. The sound reproduction device 2C controls the volume of each of the multiple divided sound signals according to the posture of each of the multiple people. The sound reproduction device 2C changes the volume of each of the first to fourth divided sound signals according to the posture of the people at the first position 111, second position 112, and third position 113. For example, the sound reproduction device 2C estimates the standing posture, sitting posture, and sleepy posture of the people at the first position 111, second position 112, and third position 113, respectively.

[0254] The sound reproduction device 2C includes at least a computer system including, for example, a control program, a processing circuit such as a processor or logic circuit that executes the control program, and a recording device such as an internal memory or an accessible external memory that stores the control program. Note that the sound reproduction device 2C may be realized, for example, by hardware implementation using the processing circuit, or by execution by the processing circuit of a software program stored in the memory or distributed from an external server, or by a combination of these hardware and software implementations.

[0255] The sound playback device 2C includes a person detection unit 201B, a feature extraction unit 202B, a posture information database 215C, a posture estimation unit 216C, a memory 205, a sound source playback unit 206, a first volume control unit 207, a second volume control unit 208, a third volume control unit 209, a fourth volume control unit 210, and a mixing unit 211.

[0256] The posture information database 215C stores a plurality of body feature amounts and posture information in association with each other. Here, a method for registering a person's body feature amounts in the posture information database 215C will be described. First, a person is photographed by a camera. Next, the person is detected from the photographed image, and the body feature amounts of the detected person are extracted. Next, the person's posture information is input by an input device such as a touch panel. Next, the person's body feature amounts and the person's posture information are stored in association with each other in the posture information database 215C.

[0257] For example, when a person's posture is estimated as standing, sitting, or sleepy, the body feature amounts of the standing person, the body feature amounts of the sitting person, and the body feature amounts of the sleepy person are extracted. The body feature amounts of the standing person are associated with posture information indicating that the person is standing, and the body feature amounts of the sitting person are associated with posture information indicating that the person is sitting, and these are stored in the posture information database 215C. Furthermore, the body feature amounts of the sleepy person are associated with posture information indicating that the person is sleepy, and these are stored in the posture information database 215C.

[0258] Postures that indicate a person is feeling sleepy include a posture in which the person is sitting with their back hunched, their head is shaking back and forth, they are yawning frequently, they are rubbing their eyes frequently, or they are blinking frequently.

[0259] Posture estimation unit 216C outputs a playback start instruction to start playback of a predetermined sound to sound source playback unit 206. When a person is detected at any of the multiple positions by person detection unit 201B, posture estimation unit 216C outputs the playback start instruction to sound source playback unit 206. Furthermore, when a person is no longer detected at any of the multiple positions by person detection unit 201B, posture estimation unit 216C may output a playback end instruction to sound source playback unit 206 to end playback of the predetermined sound.

[0260] Furthermore, the posture estimation unit 216C may select a sound corresponding to the current time period from among a plurality of different types of sounds, and output a playback start instruction to start playback of the selected sound to the sound source playback unit 206. For example, the posture estimation unit 216C may select a sound corresponding to the current time period from among a first sound corresponding to the morning time period (8:00 AM to 12:00 AM), a second sound corresponding to the afternoon time period (12:00 AM to 6:00 PM), and a third sound corresponding to the evening time period (6:00 PM to 10:00 PM). Note that the time periods are not limited to those described above.

[0261] The posture estimation unit 216C acquires information about a plurality of people present in a predetermined space. The information about the plurality of people includes posture information about the posture of each of the plurality of people. The posture estimation unit 216C estimates the posture of each of the plurality of people. The posture estimation unit 216C controls the volume of each of the plurality of divided sound signals in accordance with the posture information of each of the plurality of people.

[0262] Posture estimation unit 216C compares the body feature amount extracted by feature extraction unit 202B with each of the multiple body feature amounts stored in posture information database 215C. If there is a feature amount that matches the body feature amount extracted by feature extraction unit 202B among the multiple body feature amounts stored in posture information database 215C, posture estimation unit 216C reads out posture information associated with the feature amount from posture information database 215C and estimates the person's posture from the read posture information.

[0263] Note that posture estimation unit 216C may input the body feature amounts of the person extracted by feature extraction unit 202B into a posture estimation model and acquire the posture of the person from the posture estimation model. The posture estimation model is created by machine learning using the body feature amounts of the person and the posture of the person as training data. When the body feature amounts of the person extracted by feature extraction unit 202B are input into the posture estimation model, the posture estimation model outputs the posture of the person.

[0264] The posture information in the fourth embodiment indicates whether each of a plurality of people is sitting at each of a plurality of positions in a predetermined space, and indicates whether at least one of the plurality of people is in a posture that makes them feel sleepy. The posture estimation unit 216C estimates whether the person in each of the plurality of positions is standing or sitting. Furthermore, the posture estimation unit 216C estimates whether at least one of the plurality of people is in a posture that makes them feel sleepy.

[0265] The plurality of divided sound signals are respectively associated with a plurality of positions in a predetermined space where a plurality of people are present. The first divided sound signal is associated with a first position 111, the second divided sound signal is associated with a second position 112, and the third divided sound signal is associated with a third position 113.

[0266] The posture estimation unit 216C determines the volume of the first divided sound signal associated with the first position 111 in accordance with the posture of the person at the first position 111 in the room 100, and instructs the first volume control unit 207 about the determined volume. The posture estimation unit 216C determines the volume of the second divided sound signal associated with the second position 112 in accordance with the posture of the person at the second position 112 in the room 100, and instructs the second volume control unit 208 about the determined volume. The posture estimation unit 216C determines the volume of the third divided sound signal associated with the third position 113 in accordance with the posture of the person at the third position 113 in the room 100, and instructs the third volume control unit 209 about the determined volume. The posture estimation unit 216C determines the volume of the fourth divided sound signal in accordance with the postures of the people at the first position 111 to fourth positions 114 in the room 100, and instructs the fourth volume control unit 210 about the determined volume.

[0267] When a person is sitting, the posture estimation unit 216C determines the volume of the divided sound signal associated with the position where the person is sitting to a predetermined volume. The predetermined volume is, for example, maximum volume. When a person is not sitting, the posture estimation unit 216C determines the volume of the divided sound signal associated with the position where no person is sitting to zero. When at least one of the multiple people is in a posture that makes them feel sleepy, the posture estimation unit 216C determines the volume of another divided sound signal for suppressing drowsiness, different from the multiple divided sound signals associated with each of the multiple positions, to a predetermined volume. When not all of the multiple people are in a posture that makes them feel sleepy, the posture estimation unit 216C determines the volume of the other divided sound signal to zero. The predetermined volume is not limited to maximum volume and may be 50% or 80% of maximum volume, as long as it is greater than zero.

[0268] When the person at first position 111 in room 100 is sitting, posture estimation unit 216C determines the volume of the first divided sound signal associated with first position 111 to be a predetermined volume. Furthermore, when the person at first position 111 in room 100 is not sitting, that is, when the person at first position 111 in room 100 is standing, posture estimation unit 216C determines the volume of the first divided sound signal associated with first position 111 to be zero.

[0269] When the person at second position 112 in room 100 is sitting, posture estimation unit 216C determines the volume of the second divided sound signal associated with second position 112 to be a predetermined volume. Furthermore, when the person at second position 112 in room 100 is not sitting, i.e., when the person at second position 112 in room 100 is standing, posture estimation unit 216C determines the volume of the second divided sound signal associated with second position 112 to be zero.

[0270] When the person at third position 113 in room 100 is sitting, posture estimation unit 216C determines the volume of the third divided sound signal associated with third position 113 to be a predetermined volume. Furthermore, when the person at third position 113 in room 100 is not sitting, that is, when the person at third position 113 in room 100 is standing, posture estimation unit 216C determines the volume of the third divided sound signal associated with third position 113 to be zero.

[0271] When at least one person present at first position 111 to fourth position 114 in room 100 is feeling drowsy, posture estimation unit 216C determines the volume of the fourth divided sound signal to be a predetermined volume for suppressing drowsiness. Furthermore, when none of the people present at first position 111 to fourth position 114 in room 100 is feeling drowsy, posture estimation unit 216C determines the volume of the fourth divided sound signal to be zero.

[0272] The fourth divided sound signal for suppressing drowsiness includes a brighter sound than the first to third divided sound signals, a percussion sound with a moderate rhythm, or a sound effect that attracts a person's attention. Furthermore, the posture estimation unit 216C may set the predetermined volume of the fourth divided sound signal to be higher than the predetermined volumes of the first to third divided sound signals.

[0273] If no person is present at each position in the room 100, the posture estimation unit 216C determines the volume of the divided sound signal associated with each position to be zero.

[0274] Furthermore, in the fourth embodiment, the number of positions is three, but the present disclosure is not particularly limited to this, and the number of positions may be two or more.

[0275] Furthermore, in the fourth embodiment, the posture estimation unit 216C estimates the posture of a person in a sitting position, a standing position, and a sleepy position, but the present disclosure is not particularly limited to this, and the posture estimation unit 216C may estimate the posture of a person in a sitting position and a sleepy position. That is, the posture estimation unit 216C may determine the volume of the divided sound signal to be a predetermined volume when the person is sitting, and may determine the volume of the divided sound signal to be zero when the person is not sitting.

[0276] The first volume control unit 207 to the fourth volume control unit 210 control the volume of each of the plurality of divided sound signals in accordance with the posture of each of the plurality of people.

[0277] The first volume control unit 207 controls the volume of the first divided sound signal depending on the posture of the person at the first position 111. That is, the first volume control unit 207 controls the volume of the first divided sound signal depending on whether the person at the first position 111 is sitting or not. The first volume control unit 207 sets the volume of the first divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216C.

[0278] The second volume control unit 208 controls the volume of the second divided sound signal depending on the posture of the person at the second position 112. That is, the second volume control unit 208 controls the volume of the second divided sound signal depending on whether the person at the second position 112 is sitting or not. The second volume control unit 208 sets the volume of the second divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216C.

[0279] The third volume control unit 209 controls the volume of the third divided sound signal depending on the posture of the person at the third position 113. That is, the third volume control unit 209 controls the volume of the third divided sound signal depending on whether the person at the third position 113 is sitting or not. The third volume control unit 209 sets the volume of the third divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216C.

[0280] The fourth volume control unit 210 controls the volume of the fourth divided sound signal according to the posture of at least one person present at the first position 111 to the fourth position 114. That is, the fourth volume control unit 210 controls the volume of the fourth divided sound signal according to whether or not at least one person present at the first position 111 to the fourth position 114 is feeling drowsy. The fourth volume control unit 210 sets the volume of the fourth divided sound signal input from the sound source reproduction unit 206 to the volume instructed by the posture estimation unit 216C.

[0281] Next, the sound reproduction process performed by the sound reproduction device 2C according to the fourth embodiment of the present disclosure will be described.

[0282] Figure 16 is a first flowchart for explaining the sound reproduction processing by the sound reproduction device 2C in embodiment 4 of the present disclosure, and Figure 17 is a second flowchart for explaining the sound reproduction processing by the sound reproduction device 2C in embodiment 4 of the present disclosure.

[0283] The processing in steps S91 to S93 is the same as the processing in steps S61 to S63 shown in FIG. 12, and therefore a description thereof will be omitted.

[0284] Next, in step S94, posture estimation unit 216C estimates the postures of the people at first position 111 to third position 113 in room 100 based on the images captured by camera 1. More specifically, posture estimation unit 216C estimates whether the people at first position 111 to third position 113 in room 100 are sitting or not, and estimates whether the people at first position 111 to third position 113 in room 100 are feeling drowsy or not.

[0285] Next, in step S95, posture estimation section 216C determines whether or not a person is present at first position 111 in room 100.

[0286] If it is determined that no person is present at the first position 111 (NO in step S95), the process proceeds to step S98.

[0287] On the other hand, if it is determined that a person is present at first position 111 (YES in step S95), in step S96, posture estimation unit 216C determines whether the person at first position 111 in room 100 is sitting.

[0288] If it is determined that the person at first position 111 is sitting (YES in step S96), then in step S97, posture estimation unit 216C determines the volume of the first divided sound signal associated with first position 111 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216C instructs first volume control unit 207 to set the volume of the first divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216C, first volume control unit 207 sets the volume of the first divided sound signal to the predetermined volume. First volume control unit 207 outputs the first divided sound signal with the set volume to mixing unit 211.

[0289] On the other hand, if it is determined that the person at first position 111 is not sitting, that is, if it is determined that the person at first position 111 is standing (NO in step S96), in step S98, posture estimation unit 216C sets the volume of the first divided sound signal associated with first position 111 to zero. Posture estimation unit 216C instructs first volume control unit 207 of the volume of the first divided sound signal that has been set to zero. First volume control unit 207 sets the volume of the first divided sound signal to zero based on the instruction from posture estimation unit 216C. First volume control unit 207 outputs the first divided sound signal with the set volume to mixing unit 211.

[0290] Next, in step S99, posture estimation section 216C determines whether or not a person is present at second position 112 in room 100.

[0291] If it is determined that no person is present at the second position 112 (NO in step S99), the process proceeds to step S102.

[0292] On the other hand, if it is determined that a person is present at second position 112 (YES in step S99), in step S100, posture estimation unit 216C determines whether the person at second position 112 in room 100 is sitting.

[0293] If it is determined that the person at second position 112 is sitting (YES in step S100), then in step S101, posture estimation unit 216C determines the volume of the second divided sound signal associated with second position 112 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216C instructs second volume control unit 208 to set the volume of the second divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216C, second volume control unit 208 sets the volume of the second divided sound signal to the predetermined volume. Second volume control unit 208 outputs the second divided sound signal with the set volume to mixing unit 211.

[0294] On the other hand, if it is determined that the person at second position 112 is not sitting, that is, if it is determined that the person at second position 112 is standing (NO in step S100), in step S102, posture estimation unit 216C determines the volume of the second divided sound signal associated with second position 112 to be zero. The posture estimation unit 216C instructs second volume control unit 208 of the volume of the second divided sound signal that has been determined to be zero. Based on the instruction from posture estimation unit 216C, second volume control unit 208 sets the volume of the second divided sound signal to zero. The second volume control unit 208 outputs the second divided sound signal with the set volume to mixing unit 211.

[0295] Next, in step S103 , posture estimation section 216C determines whether or not a person is present at third position 113 in room 100 .

[0296] If it is determined that no person is present at the third position 113 (NO in step S103), the process proceeds to step S106.

[0297] On the other hand, if it is determined that a person is present at the third position 113 (YES in step S103), in step S104, the posture estimation unit 216C determines whether or not the person at the third position 113 in the room 100 is sitting.

[0298] If it is determined that the person at third position 113 is sitting (YES in step S104), then in step S105, posture estimation unit 216C determines the volume of the third divided sound signal associated with third position 113 to be a predetermined volume. The predetermined volume is, for example, maximum volume. Posture estimation unit 216C instructs third volume control unit 209 to set the volume of the third divided sound signal determined to be the predetermined volume. Based on the instruction from posture estimation unit 216C, third volume control unit 209 sets the volume of the third divided sound signal to the predetermined volume. Third volume control unit 209 outputs the third divided sound signal with the set volume to mixing unit 211.

[0299] On the other hand, if it is determined that the person at third position 113 is not sitting, that is, if it is determined that the person at third position 113 is standing (NO in step S104), in step S106, posture estimation unit 216C determines the volume of the third divided sound signal associated with third position 113 to be zero. Posture estimation unit 216C instructs third volume control unit 209 of the volume of the third divided sound signal that has been determined to be zero. Based on the instruction from posture estimation unit 216C, third volume control unit 209 sets the volume of the third divided sound signal to zero. Third volume control unit 209 outputs the third divided sound signal with the volume set to mixing unit 211.

[0300] Next, in step S107, posture estimation section 216C determines whether or not there is anyone feeling sleepy at first position 111 to fourth position 114 in room 100.

[0301] If it is determined that a person feeling drowsy is present at first position 111 to fourth position 114 (YES in step S107), then in step S108, posture estimation unit 216C determines the volume of the fourth divided sound signal to be a predetermined volume for suppressing drowsiness. The predetermined volume is, for example, maximum volume. Posture estimation unit 216C instructs fourth volume control unit 210 on the volume of the fourth divided sound signal that has been determined to be the predetermined volume. Based on the instruction from posture estimation unit 216C, fourth volume control unit 210 sets the volume of the fourth divided sound signal to the predetermined volume. Fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to mixing unit 211.

[0302] On the other hand, if it is determined that no one is feeling drowsy at first position 111 to fourth position 114 (NO in step S107), in step S109, posture estimation unit 216C determines the volume of the fourth divided sound signal to suppress drowsiness to be zero. Posture estimation unit 216C instructs fourth volume control unit 210 of the volume of the fourth divided sound signal that has been determined to be zero. Fourth volume control unit 210 sets the volume of the fourth divided sound signal to zero based on the instruction from posture estimation unit 216C. Fourth volume control unit 210 outputs the fourth divided sound signal with the volume set to mixing unit 211.

[0303] Next, in step S110, the mixing unit 211 outputs a synthesized sound signal obtained by synthesizing the first to fourth divided sound signals, whose volumes have been set, to the amplifier 3. The amplifier 3 amplifies the synthesized sound signal and outputs the amplified synthesized sound signal to the speaker 4. The speaker 4 converts the synthesized sound signal into a synthesized sound, and emits the synthesized sound obtained by synthesizing the first to fourth divided sounds, whose volumes have been set by the first to fourth volume control units 207 to 210, into the room 100.

[0304] As a result, if a person at first position 111 is sitting, the first divided sound is played from speaker 4 at a predetermined volume, and if the person at first position 111 is standing, the first divided sound is not played from speaker 4. Furthermore, if a person at second position 112 is sitting, the second divided sound is played from speaker 4 at a predetermined volume, and if the person at second position 112 is standing, the second divided sound is not played from speaker 4. Furthermore, if a person at third position 113 is sitting, the third divided sound is played from speaker 4 at a predetermined volume, and if the person at third position 113 is standing, the third divided sound is not played from speaker 4. Furthermore, if a person feeling drowsy is present at first position 111 to fourth position 114, the fourth divided sound is played from speaker 4 at a predetermined volume, and if no person feeling drowsy is present at first position 111 to fourth position 114, the fourth divided sound is not played from speaker 4.

[0305] For example, if a person is sitting only at first position 111, a first divided sound representing the sound of a harp is emitted from speaker 4. Furthermore, if a person is sitting at both first position 111 and second position 112, a first divided sound representing the sound of a harp and a second divided sound representing the sound of a violin are emitted from speaker 4. Furthermore, if a person is sitting at each of first position 111 to third position 113, a first divided sound representing the sound of a harp, a second divided sound representing the sound of a violin, and a third divided sound representing the sound of a double bass are emitted from speaker 4. Furthermore, if a person is sitting at each of first position 111 to third position 113 and the person at second position 112 is feeling sleepy, a first divided sound representing the sound of a harp, a second divided sound representing the sound of a violin, a third divided sound representing the sound of a double bass, and a fourth divided sound representing the sounds of a marimba and drums are emitted from speaker 4.

[0306] In this way, if there is a person feeling sleepy in any of the multiple positions, divided sounds are emitted to suppress the drowsiness, stimulating the person who is feeling sleepy and allowing them to concentrate on the conversation.

[0307] Furthermore, if a person is standing, the divided sounds are not emitted, and if a person is seated, the divided sounds are emitted, so that participants in a conversation (conference) can be encouraged to take a seat.

[0308] If posture estimation unit 216C determines that a person feeling sleepy is present at first position 111 to fourth position 114, it may change the predetermined sound to music with a fast tempo whose BPM is equal to or higher than a threshold value. This can further reduce the person's sleepiness.

[0309] In each of the above embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for that component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. Furthermore, the program may be executed by another independent computer system by recording the program on a recording medium and transferring it, or by transferring the program via a network.

[0310] Some or all of the functions of the device according to the embodiment of the present disclosure are typically realized as an LSI (Large Scale Integration), which is an integrated circuit. These may be individually integrated into a single chip, or some or all of them may be integrated into a single chip. Furthermore, the integrated circuit is not limited to an LSI, and may be realized using a dedicated circuit or a general-purpose processor. It is also possible to use an FPGA (Field Programmable Gate Array), which can be programmed after LSI manufacturing, or a reconfigurable processor, which can reconfigure the connections and settings of circuit cells within an LSI.

[0311] Furthermore, some or all of the functions of the device according to the embodiment of the present disclosure may be realized by a processor such as a CPU executing a program.

[0312] Furthermore, all the numbers used above are merely examples to specifically explain the present disclosure, and the present disclosure is not limited to the numbers used as examples.

[0313] The order in which the steps are executed in the above flowchart is merely an example for specifically explaining the present disclosure, and other orders may be used as long as similar effects are obtained. Also, some of the steps may be executed simultaneously (in parallel) with other steps.

[0314] The technology disclosed herein is useful as a sound reproduction technology because it can gather multiple people in a specified space and stimulate conversation among multiple people in the specified space.

Claims

1. A sound reproduction method in a computer, comprising: acquiring information about a plurality of people in a specified space; synchronizing and playing a plurality of divided sound signals obtained by dividing the specified sound; and outputting the plurality of divided sound signals based on the information about the plurality of people to a speaker that emits a plurality of divided sounds converted from the plurality of divided sound signals into the specified space.

2. The sound reproduction method according to claim 1, wherein the information relating to the plurality of persons includes identification result information for identifying each of the plurality of persons, and further includes controlling the volume of each of the plurality of divided sound signals depending on whether each of the plurality of persons has been identified.

3. The sound reproduction method of claim 2, wherein the volume control includes determining the volume of the divided sound signal associated with the person to a predetermined volume when the person is identified, and determining the volume of the divided sound signal associated with the person to zero when the person is not identified.

4. The sound reproduction method of claim 1, wherein the information relating to the plurality of people includes audio information indicating an average volume of the voice of each of the plurality of people over a specified period of time, and further includes controlling the volume of each of the plurality of divided sound signals in accordance with the average volume of the voice of each of the plurality of people over the specified period of time.

5. The sound reproduction method of claim 4, wherein the volume control includes determining the volume of the divided sound signal associated with the person to a predetermined volume when the average volume of the person's voice is smaller than a threshold value, and determining the volume of the divided sound signal associated with the person to zero when the average volume of the person's voice is equal to or greater than the threshold value.

6. The sound reproduction method according to claim 1, wherein the information relating to the plurality of people includes posture information relating to the posture of each of the plurality of people, and further includes controlling the volume of each of the plurality of divided sound signals in accordance with the posture of each of the plurality of people.

7. The sound reproduction method of claim 6, wherein the posture information indicates whether each of the multiple people is standing or not, and the volume control includes determining the volume of the divided sound signal to a predetermined volume if the person is standing, and determining the volume of the divided sound signal to zero if the person is not standing.

8. The sound reproducing method according to claim 7, wherein each of the plurality of divided sound signals is associated with a plurality of positions in the specified space where the plurality of people are present.

9. The sound reproduction method of claim 6, wherein the posture information indicates whether each of the multiple people is sitting at each of multiple positions in the specified space, and indicates whether at least one of the multiple people is in a posture that makes them feel sleepy, and the volume control includes: if a person is sitting, determining the volume of the divided sound signal corresponding to the position where the person is sitting to a predetermined volume, if the person is not sitting, determining the volume of the divided sound signal corresponding to the position where the person is not sitting to zero, if at least one of the multiple people is in a posture that makes them feel sleepy, determining the volume of another divided sound signal for suppressing the drowsiness, different from the multiple divided sound signals corresponding to each of the multiple positions, to a predetermined volume, and if not all of the multiple people are in a posture that makes them feel sleepy, determining the volume of the another divided sound signal to zero.

10. The sound reproducing method according to any one of claims 1 to 9, wherein the predetermined sound is divided according to frequency height.

11. The sound reproducing method according to any one of claims 1 to 9, wherein the predetermined sound is music and is divided according to a plurality of performance parts that make up the music.

12. A sound playback device comprising: an acquisition unit that acquires information about a plurality of people in a specified space; a playback unit that synchronizes and plays a plurality of divided sound signals obtained by dividing a specified sound; and an output unit that outputs the plurality of divided sound signals based on information about the plurality of people to a speaker that emits a plurality of divided sounds converted from the plurality of divided sound signals into the specified space.

13. A sound playback program that causes a computer to acquire information about a plurality of people in a specified space, play a plurality of divided sound signals obtained by dividing a specified sound in synchronization with each other, and output the plurality of divided sound signals to a speaker that emits a plurality of divided sounds converted from the plurality of divided sound signals into the specified space based on the information about the plurality of people.

Images