Information processing apparatus

Abstract

The invention provides an information processing apparatus. A control unit of an information processing apparatus acquires a plurality of first sounds output from a plurality of speakers. A control unit of the information processing device calculates the ratio of the magnitudes of the plurality of acquired first sounds. Then, the control unit sets a mixing ratio by applying, as the mixing ratio, the ratio of the magnitudes of the plurality of first sounds that have been calculated, the mixing ratio is a ratio for mixing a plurality of sound signals, and is used when generating a reference signal for cancelling out a plurality of output sounds output by a plurality of speakers from sounds acquired by a microphone in accordance with the plurality of sound signals.

Description

Technical Field

[0001] The present disclosure relates to an information processing device. Background Art

[0002] Japanese Patent Laid-Open No. 2009-181025 discloses a vehicle-mounted speech recognition device, which implements an echo cancellation process to remove echo components contained in input speech. The vehicle-mounted speech recognition device disclosed in Japanese Patent Laid-Open No. 2009-181025 removes echo components contained in input speech picked up via a microphone and signals from multiple sound sources. In addition, the vehicle-mounted speech recognition device performs speech recognition on the output from which the echo components have been removed. In addition, the vehicle-mounted speech recognition device monitors the input speech picked up via a microphone and signals from multiple sound sources, and determines whether the speech recognition rate is improved by removing the echo components, thereby controlling the echo cancellation process. Summary of the invention

[0003] An object of the present disclosure is to effectively cancel out a plurality of sounds output from a plurality of speakers.

[0004] The information processing device according to the present disclosure includes a control unit configured to execute the following processing:

[0005] Acquire a plurality of first sounds output from a plurality of speakers;

[0006] Calculating the ratio of the magnitudes of the plurality of first sounds obtained;

[0007] The mixing ratio is set by applying the calculated ratio of the sizes of the multiple first sounds as a mixing ratio, wherein the mixing ratio is a ratio for mixing multiple sound signals and is a mixing ratio used when generating a reference signal for canceling out the multiple output sounds output by the multiple speakers based on the multiple sound signals from the sound obtained by the microphone.

[0008] According to the present disclosure, a plurality of sounds output from a plurality of speakers can be effectively canceled out. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described below with reference to the accompanying drawings, in which like symbols represent like elements, and in which:

[0010] Figure 1 It is a diagram showing a schematic configuration of a speech recognition system according to the present embodiment.

[0011] Figure 2A diagram showing the arrangement of a plurality of speakers and in-vehicle devices in a vehicle.

[0012] Figure 3 This is a block diagram schematically showing an example of the functional structure of the vehicle-mounted device.

[0013] Figure 4 The figure shows an example of the table structure of the scale information stored in the scale information database.

[0014] Figure 5 This is a flowchart of a first process executed by the control unit of the vehicle-mounted device.

[0015] Figure 6 This is a flowchart of the second process executed by the control unit of the vehicle-mounted device. DETAILED DESCRIPTION

[0016] Suppose that a sound is acquired through a microphone. At this time, there is a situation where a speaker existing around the microphone is outputting sound. Then, the sound output from the speaker will be mixed with the sound acquired from the microphone.

[0017] In addition, there is a case where multiple speakers are outputting multiple sounds. In this case, there is a case where a reference signal for canceling the multiple sounds output from the multiple speakers is used to cancel the multiple sounds from the sound obtained by the microphone. The purpose of the information processing device involved in the present disclosure is to cancel the multiple sounds output from the multiple speakers in such a case.

[0018] The control unit of the information processing device involved in the present disclosure obtains a plurality of first sounds output from a plurality of speakers. The control unit of the information processing device calculates the ratio of the magnitudes of the obtained plurality of first sounds. Then, the control unit sets the mixing ratio by applying the calculated ratio of the magnitudes of the plurality of first sounds as a mixing ratio. Here, the mixing ratio is a ratio for mixing a plurality of sounds, and is a mixing ratio used when generating a reference signal for canceling a plurality of output sounds output through a plurality of speakers according to a plurality of sound signals from a sound obtained by a microphone.

[0019] As described above, the mixing ratio is specified by the information processing device. Thus, mixing can be performed according to the magnitude of the first sound output by each speaker, and a reference signal can be generated. Then, the reference signal can be used to cancel out the multiple sounds output by the multiple speakers from the sound obtained by the microphone.

[0020] At this time, in the reference signal, multiple sound signals are mixed according to the size of the first sound. Thus, among the multiple output sounds, the sound with a larger output sound is mixed at a larger ratio in the reference signal. Therefore, among the multiple output sounds, the emphasis can be placed on the sound with a larger output sound. As a result, the multiple sounds output from the multiple speakers can be effectively canceled out.

[0021] Hereinafter, specific embodiments of the present disclosure will be described based on the drawings. Unless otherwise specified, the disclosed technical scope is not intended to be limited to the hardware configuration, module configuration, functional configuration, etc. described in each embodiment.

[0023] based on Figure 1 to Figure 2 Next, the speech recognition system 1 in this embodiment will be described. Figure 1 1 is a diagram showing a schematic structure of a speech recognition system 1 according to the present embodiment. The speech recognition system 1 is configured to include an in-vehicle device 100 and an audio device 200. In the speech recognition system 1, the in-vehicle device 100 and the audio device 200 are connected to each other via an interface (I / F) and an in-vehicle network.

[0024] Vehicle-mounted device

[0025] The vehicle-mounted device 100 is a device mounted on a vehicle 10. The vehicle-mounted device 100 provides various services such as information provision to the user based on the voice of the user riding in the vehicle 10. In addition, the vehicle-mounted device 100 implements signal output for outputting sounds such as music or white noise in the vehicle 10. Specifically, the vehicle-mounted device 100 is configured to include a source device 11, a microphone 12, and a canceller 13.

[0026] The source device 11 is a device that outputs an audio signal for causing the audio device 200 to play music or other sounds. The source device 11 is, for example, a device that reads a medium such as a CD drive. The source device 11 reads a medium such as a CD and outputs an audio signal. In addition, the source device 11 is a device that outputs pre-stored information such as music or white noise as an audio signal. The microphone 12 is a microphone mounted on the vehicle 10. The microphone 12 receives the voice of a user riding in the vehicle 10.

[0027] The canceller 13 is a device for cancelling sounds other than the user's voice from the sound including the user's voice acquired by the microphone 12. Details of the method by which the canceller 13 cancels sounds other than the user's voice from the sound including the user's voice will be described later.

[0028] The vehicle-mounted device 100 is configured to include a computer having a processor 110, a main storage unit 120, and an auxiliary storage unit 130. The processor 110 is, for example, a CPU (Central Processing Unit) or a DSP (Digital Signal Processor). The main storage unit 120 is, for example, a RAM (Random Access Memory). The auxiliary storage unit 130 is, for example, a ROM (Read Only Memory). In addition, the auxiliary storage unit 130 is, for example, a disk recording medium such as an HHD (Hard Disk Drive), or a CD-ROM (Compact Disc-Read Only Memory), a DVD (Digital Video Disc), or a Blu-ray disc. In addition, the auxiliary storage unit 130 may also be a removable medium (removable storage medium). Here, as a removable medium, for example, a USB memory or an SD card can be exemplified.

[0029] In the vehicle-mounted device 100, an operating system (OS), various programs, various information tables, etc. are stored in the auxiliary storage unit 130. In addition, in the vehicle-mounted device 100, the processor 110 loads the program stored in the auxiliary storage unit 130 into the main storage unit 120 and executes it, thereby realizing various functions described later. However, part or all of the functions in the vehicle-mounted device 100 can also be realized by hardware circuits such as ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). In addition, the vehicle-mounted device 100 does not necessarily have to be realized by a single physical structure, and can also be composed of multiple computers that cooperate with each other.

[0030] Audio Devices

[0031] The audio device 200 is a device mounted on the vehicle 10. The audio device 200 outputs sounds such as music using an audio signal received from the vehicle-mounted device 100. The audio device 200 is configured to include a microcomputer 21, an amplifier 22, a plurality of speakers 23, and a mixer 24. In addition, the audio device 200 is configured to include a computer similarly to the vehicle-mounted device 100.

[0032] The microcomputer 21 is a device that converts an audio signal received from the vehicle 10 into an output signal for the audio device 200 (speaker 23) to output sound. The microcomputer 21 sends the output signal obtained by converting the audio signal to the amplifier 22. The amplifier 22 is a device that amplifies the output signal received from the vehicle 10 and outputs it to the speaker 23. In addition, in the present embodiment, the output signal is a signal that specifies the size of the sound according to the size of the voltage.

[0033] In addition, the speaker 23 is a speaker provided in the vehicle 10. A plurality of speakers 23 are provided in the vehicle 10. And the speaker 23 outputs sound into the vehicle 10 using the amplified output signal received from the amplifier 22. Here, the microcomputer 21 sends the output signals of a plurality of channels to the microcomputer 21 in order to make the plurality of speakers 23 output sound. Here, the number of output signals sent by the microcomputer 21 may be the same as the number of speakers 23, or may be a number smaller than the number of speakers 23. When the number of output signals is smaller than the number of speakers 23, at least two speakers 23 output sound using the same output signal.

[0034] At this time, there is a case where the user of the vehicle 10 speaks to the vehicle-mounted device 100 (microphone 12). In this case, it is conceivable that the sound of music or the like output by the speaker 23 is also acquired through the microphone 12 together with the sound of the vehicle 10. Therefore, the sound of music or the like output by the speaker 23 may hinder the voice recognition of the user of the vehicle 10 performed by the vehicle-mounted device 100.

[0035] Therefore, it is conceivable that the audio device 200 sends an output signal to the vehicle-mounted device 100, and the vehicle-mounted device 100 refers to the output signal and cancels the sound output by the audio device 200 (speaker 23) from the sound obtained by the microphone 12. On the other hand, in the present embodiment, the vehicle-mounted device 100 and the audio device 200 are connected through the interface (I / F) possessed by each other. At this time, the audio signal sent by the vehicle-mounted device 100 and the signal used to cancel the sound output by the audio device 200 (speaker 23) are sent and received simultaneously between the vehicle-mounted device 100 and the audio device 200. As a result, there is a situation where the frequency band for sending and receiving signals is insufficient. In this way, since all of the multiple output signals cannot be sent to the vehicle-mounted device 100 due to insufficient frequency band, there is a need to mix at least a part of the output signals.

[0036] Figure 2 2 is a diagram showing the arrangement of a plurality of speakers 23 and the vehicle-mounted device 100 in the vehicle 10. Figure 2As shown, eight speakers 23 (speaker 23A, speaker 23B, speaker 23C, speaker 23D, speaker 23E, speaker 23F, speaker 23G, and speaker 23H) are provided in the vehicle 10. In addition, in the vehicle 10, the vehicle-mounted device 100 is provided in the right front of the vehicle 10. The vehicle-mounted device 100 is provided in front of the driver's seat of the vehicle 10, for example.

[0037] At this time, the speaker 23C and the speaker 23D are provided at positions closer than the other speakers 23. Therefore, the directions of the speakers 23C and the speakers 23D when viewed from the vehicle-mounted device 100 are similar to those of the other speakers 23. In addition, the difference in distance between the speakers 23C and the speakers 23D and the vehicle-mounted device 100 is smaller than the difference in distance between the other two speakers 23 and the vehicle-mounted device 100. Therefore, the positional relationship between the speakers 23C and the speakers 23D and the vehicle-mounted device 100 is similar to that of the positional relationship between the other speakers 23 and the vehicle-mounted device 100.

[0038] Therefore, it can be said that the condition in which the sound outputted by the speaker 23C and the speaker 23D is reflected by the wall or the like before reaching the vehicle-mounted device 100 is more similar to the condition in which the sound outputted by the other speakers 23 is reflected before reaching the vehicle-mounted device 100. In addition, it can be said that the amount of attenuation of the sound outputted by the speaker 23C and the speaker 23D before reaching the vehicle-mounted device 100 is more similar to the amount of attenuation of the sound outputted by the other speakers 23 before reaching the vehicle-mounted device 100. In other words, it can be said that the sound outputted by the speaker 23C and the speaker 23D undergoes a change that is more similar to that of the other speakers 23 and reaches the vehicle-mounted device 100. Therefore, in the present embodiment, the speaker 23C and the speaker 23D are treated as a group.

[0039] In addition, Figure 2 In the accompanying drawings shown, the speaker 23G and the speaker 23H are also arranged at a closer position than the other speakers 23. Therefore, the speaker 23G and the speaker 23H can be treated as a group. In addition, the mixer 24 mixes the output signals output for the speaker 23C and the speaker 23D, and the output signals output for the speaker 23G and the speaker 23H, respectively, as one signal. Thus, for example, eight output signals can be set to six signals. In addition, although two speakers 23 are set as one group in the present embodiment, more than two speakers 23 can also be set as one group. In this way, a plurality of speakers 23 arranged within a predetermined distance from each other are set as one group, and the output signals for the plurality of speakers 23 are mixed.

[0040] Then, the mixer 24 outputs the signal obtained by mixing the output signal (hereinafter sometimes referred to as a "reference signal") to the vehicle-mounted device 100. In addition, the mixer 24 outputs the output signal of other speakers 23 that do not belong to any group among the output signals as a reference signal to the vehicle-mounted device 100 without mixing with other output signals. Specifically, the mixer 24 outputs the reference signal to the canceller 13 via the I / F. As a result, the canceller 13 can use the reference signal to cancel the sound output by the speaker 23. In addition, the mixer 24 outputs the reference signal (output signal) to the vehicle-mounted device 100 in real time.

[0041] At this time, it is necessary to determine the ratio (hereinafter sometimes referred to as "mixing ratio") when the audio device 200 mixes the output signal. Therefore, the vehicle-mounted device 100 causes each speaker 23 belonging to one group to output white noise. In addition, the vehicle-mounted device 100 uses the microphone 12 to obtain the sound level (sound pressure or volume, etc.) of the white noise output from each speaker 23. Then, the vehicle-mounted device 100 specifies the ratio of the sound level of the white noise output from each speaker 23 as the mixing ratio for the output signal of each speaker 23.

[0042] By determining the mixing ratio in this way, the sounds output by the multiple speakers 23 belonging to a group will be mixed in the reference signal according to the volume of the white noise sound. That is, among the sounds output by the multiple speakers 23 belonging to a group, the sound output by the speaker 23 with a larger volume of white noise sound will be mixed in a larger ratio in the reference signal. Therefore, among the sounds output by the multiple speakers 23 belonging to a group, the emphasis can be placed on the sound with a larger volume. As a result, the multiple sounds output by the multiple speakers 23 belonging to a group can be effectively offset. In addition, the sound output by the speaker 23 that does not belong to the group will also be output as a reference signal without being mixed. As a result, the sound output by the speaker 23 that does not belong to the group can also be offset.

[0043] Functional structure

[0044] Next, based on Figure 3 to Figure 4 Next, the functional structure of the vehicle-mounted device 100 constituting the speech recognition system 1 will be described. Figure 3 This is a block diagram schematically showing an example of the functional structure of the vehicle-mounted device 100.

[0045] The vehicle-mounted device 100 is configured to include a control unit 101, an input / output unit 102, and a ratio information database 103 (ratio information DB 103). The control unit 101 has a function of performing a calculation process for controlling the vehicle-mounted device 100. The control unit 101 can be implemented by a processor 110 in the vehicle-mounted device 100. The input / output unit 102 has a function of connecting the vehicle-mounted device 100 and the audio device 200 and inputting and outputting various signals. The input / output unit 102 can be implemented by an I / F in the vehicle-mounted device 100.

[0046] The control unit 101 outputs an audio signal to the audio device 200 via the input / output unit 102. In addition, the control unit 101 outputs an audio signal for causing each speaker 23 to output white noise to the audio device 200 via the input / output unit 102. Specifically, the control unit 101 causes the source device 11 to output an audio signal. Here, the audio signal for causing the white noise to be output includes a signal for specifying the speaker 23 for causing the white noise to be output. In addition, the control unit 101 outputs an audio signal for causing the plurality of speakers 23 (in a group) to be grouped together. Figure 2 In the example shown, the speaker 23C and the speaker 23D, and the speaker 23G and the speaker 23H) output audio signals of white noise. Here, the control unit 101 sequentially outputs audio signals to each speaker 23 so that the plurality of speakers 23 gathered in one group do not output white noise at the same time.

[0047] At this time, the control unit 101 causes the plurality of speakers 23 grouped together to output white noise of the same volume. If the setting value is determined so that the volume of the sound output by each speaker 23 is different for the same audio signal, the control unit 101 outputs the sound according to the setting value.

[0048] When the control unit 101 outputs an audio signal for outputting white noise, it uses the microphone 12 to obtain the white noise output from each speaker 23. At this time, the control unit 101 obtains the volume of the sound of the white noise output from each speaker 23 and obtained by the microphone 12 (hereinafter, sometimes simply referred to as "the volume of the sound of the white noise"). Then, the control unit 101 calculates the ratio of the volume of the sound of the white noise output from each speaker 23. Here, the control unit 101 calculates the ratio of the volume of the sound of the white noise output from the plurality of speakers 23 belonging to each group.

[0049] The control unit 101 specifies the ratio of the calculated sound size of the white noise as the mixing ratio. Then, the control unit 101 stores the ratio information indicating the specified mixing ratio in the ratio information DB 103. The ratio information DB 103 has a function of storing the ratio information. The ratio information DB 103 can be implemented by the auxiliary storage unit 130 in the vehicle-mounted device 100. Figure 4 2 is a diagram showing an example of a table structure of proportion information stored in the proportion information DB 103 .

[0050] like Figure 4 As shown, the ratio information includes a group ID field, a speaker ID field, and a ratio field. In the group ID field, an identifier (group ID) for identifying the group to which each speaker 23 belongs is stored. In the speaker ID field, an identifier (speaker ID) for identifying the speaker 23 is stored. Here, in the case where a plurality of speakers belong to one group, a plurality of speaker IDs are stored in the group ID field corresponding to one group ID.

[0051] The ratio field stores the mixing ratio (ratio of the volume of the sound of white noise) calculated by the control unit 101. Here, the mixing ratios of the speakers 23 belonging to one group are normalized so that the sum of the mixing ratios of the plurality of speakers 23 becomes 1. That is, when all the mixing ratios stored in the plurality of ratio fields corresponding to one group are added together, the sum becomes 1.

[0052] The control unit 101 refers to the ratio information and sends instruction information to the audio device 200, which is information that instructs the audio device 200 to mix the audio signals at the ratio of the speakers 23 belonging to each group. That is, the control unit 101 sends instruction information to the audio device 200 that instructs the mixing ratio for the plurality of speakers 23 belonging to each group. Upon receiving the instruction information, the audio device 200 performs mixing at the mixing ratio for each group. Specifically, the control unit 101 sends the instruction information via the I / Fs of each other. Then, the audio device 200 instructs the mixer 24 to mix the output signal at the specified mixing ratio for each group. As a result, the audio device 200 mixes the output signal, so that the vehicle-mounted device 100 can receive the reference signal.

[0053] The control unit 101 determines whether the user of the vehicle 10 has made a sound. When the user of the vehicle 10 has made a sound, the control unit 101 performs speech recognition in order to determine the content of the user's sound. At this time, the control unit 101 obtains a reference signal about the sound being output by the speaker 23. Then, the control unit 101 causes the eliminator 13 to cancel out the sound being output by the speaker 23 from the sound obtained by the microphone 12. Here, the process of canceling out the sound output by the speaker 23 from the sound obtained by the microphone 12 (hereinafter sometimes referred to as "input sound") includes the process of eliminating the sound being output by the speaker 23 from the input sound as noise. In addition, the process of canceling out the sound being output by the speaker 23 from the input sound includes the process of eliminating the echo of the sound being output by the speaker 23 from the input sound.

[0054] At this time, the reference signal obtained by the control unit 101 is a reference signal when (during) the user of the vehicle 10 speaks. That is, the control unit 101 obtains a reference signal about the sound output by the multiple speakers 23 when the user of the vehicle 10 speaks. The control unit 101 causes the eliminator 13 to cancel out the sound generated by the multiple speakers 23 from the input sound including the user's voice. At this time, the control unit 101 may also cancel out the sound generated by the multiple speakers 23 after appropriately amplifying or processing the reference signal. In addition, a known method can be used for the method by which the control unit 101 uses the reference signal to cancel out the sound. The control unit 101 may also cancel out the sound output by the multiple speakers 23 by, for example, overlapping sounds with a phase opposite to the phase indicated by the reference signal.

[0055] First treatment

[0056] based on Figure 5 A first process executed by the control unit 101 in the vehicle-mounted device 100 in the speech recognition system 1 will be described. Figure 5 This is a flowchart of the first process executed by the control unit 101 . Figure 5 The first process shown is a process for causing the speaker 23 to output white noise, determining a mixing ratio, and instructing the audio device 200 .

[0057] In the first process, first, in S101, an audio signal for outputting white noise is output to the audio device 200 using the source device 11. Next, in S102, the white noise is acquired using the microphone 12. Next, in S103, the magnitude of the sound of the white noise of each speaker 23 belonging to one group is designated as a mixing ratio. Next, in S105, ratio information indicating the designated mixing ratio is generated and stored in the ratio information DB 103. Next, in S106, the instruction information is sent to the audio device 200. Then, the first process ends.

[0058] Second treatment

[0059] Next, based on Figure 6 Next, the second process executed by the control unit 101 in the vehicle-mounted device 100 in the speech recognition system 1 will be described. Figure 6 This is a flowchart of the second process executed by the control unit 101 . Figure 6 The second process shown is a process for performing speech recognition of an utterance of a user of the vehicle 10 . Figure 6 The second process shown is repeatedly executed at predetermined intervals. Thus, the second process can perform voice recognition in real time for the utterance of the user of the vehicle 10. In addition, the second process is started after the execution of the first process.

[0060] In the second process, first, in S201, it is determined whether the utterance of the user of the vehicle 10 is acquired through the microphone 12. If a negative determination is made in S201, the user of the vehicle 10 has not uttered a word. Therefore, since speech recognition is not required, the second process is once terminated.

[0061] When a positive determination is made in S201, an input sound is obtained in S202. Next, a reference signal is obtained in S203. Then, in S204, a cancellation process is performed to cancel the sound output by the speaker 23 from the input sound. Here, in S203, the control unit 101 obtains a reference signal at the time point (period) when the user of the vehicle 10 utters a sound from among the reference signals received from the audio device 200. And, since the cancellation process is performed using the obtained reference signal, the sound output by the speaker 23 can be canceled when the user of the vehicle 10 utters a sound.

[0062] Next, in S205, speech recognition processing is performed on the sound subjected to the cancellation processing. Thus, speech recognition can be performed based on the sound obtained by the microphone 12 including the voice of the user of the vehicle 10 and the sound output by the plurality of speakers 23, with the sound output by the plurality of speakers 23 canceled out.

[0063] As described above, the mixing ratio is specified in the speech recognition system 1. Thus, mixing is performed according to the size of the sounds output by the multiple speakers 23, and a reference signal is generated. Then, the reference signal is used to cancel the sounds output by the multiple speakers 23 from the sounds obtained by the microphone 12. By adopting this method, the multiple sounds output from the multiple speakers can be effectively canceled.

[0064] Change Example 1

[0065] In the present embodiment, the vehicle-mounted device 100 and the audio device 200 are installed in the vehicle 10. However, the same devices as the vehicle-mounted device 100 and the audio device 200 may be installed in a place other than the vehicle 10. For example, the same devices as the vehicle-mounted device 100 and the audio device 200 may be installed in any place such as indoors or outdoors. In such a case, the present embodiment can also be applied.

[0066] Change Example 2

[0067] In the present embodiment, a plurality of speakers 23 disposed within a predetermined distance from each other are grouped together to perform mixing of output signals. However, in the present variation, all output signals for all speakers 23 in the vehicle 10 may be mixed and output as a reference signal to the vehicle-mounted device 100. By adopting this method, the vehicle-mounted device 100 can perform cancellation processing using one reference signal without acquiring a plurality of signals. As a result, the processing burden of the vehicle-mounted device 100 (eliminator 13) can be reduced. In this way, a plurality of sounds output from a plurality of speakers 23 can also be effectively canceled out.

[0068] Change Example 3

[0069] The mixer 24 may also be provided on the vehicle-mounted device 100. In this case, the microcomputer 21 in the audio device 200 outputs the output signal to the mixer 24 provided on the vehicle-mounted device 100. Then, the mixer 24 mixes the output signal and outputs the reference signal to the canceller 13. Thus, the sounds outputted from the plurality of speakers 23 can be canceled out while the number of reference signals processed by the canceller 13 is reduced. As a result, the processing load of the vehicle-mounted device 100 (canceller 13) is reduced, so that the plurality of sounds outputted from the plurality of speakers 23 can be effectively canceled out.

[0070] Change Example 4

[0071] Figure 5The first process shown may also be configured to be executed when an input to start execution is given to the vehicle-mounted device 100. That is, the first process may be executed by a person (designer) who designs the model of the vehicle 10 before manufacturing the vehicle 10, or by a user of the vehicle 10. It is assumed that the designer executes the first process. In this case, the designer executes the first process when designing the model of the vehicle 10 before manufacturing the vehicle 10. Moreover, by presetting the calculated mixing ratio for the audio device 200, it is not necessary to re-execute the first process in the same model as the vehicle 10, such as the interior. Here, the process of presetting the calculated mixing ratio for the audio device 200 includes a process of pre-storing the ratio information indicating the calculated mixing ratio in the ratio information DB 103 and sending the instruction information to the audio device 200. In addition, the process of pre-setting the calculated mixing ratio for the audio device 200 includes a process of directly specifying the calculated mixing ratio for the audio device (mixer 24) in advance.

[0072] In addition, a case where the user of the vehicle 10 executes the first process is assumed. In this case, the following method may be adopted, that is, the user of the vehicle 10 executes the first process when the interior of the vehicle 10 is changed. Here, the change of the interior of the vehicle 10 is, for example, a case where the material or shape of the seat or lining in the vehicle 10 is changed. By changing the material or shape of the seat or lining in the vehicle 10, when the speaker 23 outputs the sound, the reflection condition of the sound in the vehicle 10 will be different. Therefore, a case where the sound obtained by the vehicle-mounted device 100 changes is assumed. In addition, the change of the interior of the vehicle 10 may also be a change of the speaker 23. A case where the sound obtained by the vehicle-mounted device 100 changes due to the change of the model or manufacturer of the speaker 23 is assumed. By having the vehicle-mounted device 100 execute the first process at an arbitrary timing by the user of the vehicle 10, even when the sound obtained by the vehicle-mounted device 100 changes, multiple sounds output from multiple speakers 23 can be effectively canceled.

[0073] Change Example 5

[0074] In this embodiment, the microphone 12 is provided on the vehicle-mounted device 100. That is, the microphone 12 is directly connected to the control unit 101. However, the connection method between the microphone 12 and the control unit 101 may not be limited to such an example. In another example, the control unit 101 may be indirectly connected to the microphone 12 via one or more computers such as a relay device.

[0075] Other Implementations

[0076] The above-mentioned embodiment is only an example, and the present disclosure can be implemented with appropriate changes without departing from the gist of the present disclosure. In addition, the processes and means described in the present disclosure can be implemented in combination as long as no technical contradiction occurs.

[0077] Furthermore, a process described as being performed by one device may be shared and executed by a plurality of devices. Alternatively, a process described as being performed by different devices may be performed by one device. In a computer system, the hardware structure (server structure) used to implement each function can be flexibly changed.

[0078] The present disclosure can also be implemented by providing a computer program with the functions described in the above-mentioned embodiments, and enabling one or more processors of the computer to read and execute the program. Such a computer program can be provided to the computer via a non-temporary computer-readable storage medium that can be connected to the system bus of the computer, or it can be provided to the computer via a network. Non-temporary computer-readable storage media include, for example, any type of disk (Floopy (registered trademark), or hard disk drive (HDD)), optical disk (CD-ROM, DVD disc, or Blu-ray disc, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic card, flash memory, or optical card, etc., any type of medium suitable for storing electronic instructions.

Claims

1. An information processing device, wherein: A control unit is provided, and the control unit is configured to execute the following processing, namely: Acquire a plurality of first sounds output from a plurality of speakers; Calculating the ratio of the magnitudes of the plurality of first sounds obtained; The mixing ratio is set by applying the calculated ratio of the sizes of the multiple first sounds as a mixing ratio, wherein the mixing ratio is a ratio for mixing multiple sound signals and is a mixing ratio used when generating a reference signal for canceling out the multiple output sounds output by the multiple speakers based on the multiple sound signals from the sound obtained by the microphone.

2. The information processing device according to claim 1, wherein: The control unit is configured to further execute a process of outputting the set mixing ratio.

3. The information processing device according to claim 2, wherein: The process of outputting the mixing ratio includes a process of instructing a mixer to perform mixing at the mixing ratio.

4. The information processing device according to claim 1, wherein: The plurality of speakers are disposed within a predetermined distance from each other.

5. The information processing device according to any one of claims 1 to 4, wherein: The control unit is configured to further execute the following processing, namely: obtaining, via the microphone, an input sound including a plurality of second sounds output by the plurality of speakers; acquiring, as the reference signal, a signal obtained by mixing a plurality of signals for outputting the plurality of second sounds at the mixing ratio; The plurality of second sounds are canceled from the input sound using the obtained reference signal.

Images