Information processing device

By performing voice conversion processing on the sound collected by the microphone and combining image analysis, the problems of inaccurate audio data recording and privacy leakage in the prior art are solved, and audio data is recorded and stored under the premise of protecting privacy, ensuring the privacy of audio data.

JP2025020313AInactive Publication Date: 2025-02-12PIONEER IP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024194091
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-11-06
Publication Date
2025-02-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art cannot effectively detect and record audio data when an event occurs, resulting in the inability to investigate the cause of the event, and there is a risk of privacy leakage.

Method used

By performing voice conversion processing on the sound collected by the microphone, the processed voice is stored in the storage unit, only the voice processing has been recorded, and the identity of the speaker is determined in combination with image analysis to achieve privacy protection.

Benefits of technology

It realizes recording and storing audio data while protecting privacy, preventing third parties from identifying the speaker, and ensuring the privacy of audio data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025020313000001_ABST
    Figure 2025020313000001_ABST
Patent Text Reader

Abstract

To provide an information processing device capable of recording voice while protecting privacy.SOLUTION: An information processing device comprises a control unit, a storage unit, a microphone, a communication unit and a camera. A processing operation in the information processing device includes applying voice change processing to voice collected by the microphone, storing the voice applied with the voice change processing in the storage unit, and transmitting the voice stored in the storage unit.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device. [Background technology]

[0002] A drive recorder records the voice inside the car in addition to the images inside and outside the car while driving. Such voice can be used to investigate the cause of an event such as an accident, but there are some users who do not want their voice to be recorded from the viewpoint of privacy.

[0003] Therefore, for example, Patent Document 1 discloses a technique for recording audio data only when an event occurs. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-82390 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, with the technology disclosed in Patent Document 1, if the occurrence of an event cannot be properly detected, audio data is not recorded, making it impossible to investigate the cause of the event occurrence based on the audio.

[0006] One example of a problem to be solved by the present invention is recording audio while protecting privacy. [Means for solving the problem]

[0007] In order to solve the above problem, the invention described in claim 1 comprises an audio processing unit that applies voice change processing to audio picked up by a microphone, and a memory unit that stores the audio that has been subjected to the voice change processing.

[0008] The invention described in claim 11 is an information processing method executed by a computer, comprising an audio processing step of applying voice change processing to audio picked up by a microphone, and a storage processing step of storing the audio that has been subjected to the voice change processing in a storage unit.

[0009] The invention as recited in claim 12 causes the information processing method as recited in claim 11 to be executed by a computer.

[0010] The invention as recited in claim 13 stores the information processing program as recited in claim 12. [Brief description of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating an information processing device 100 according to an embodiment of the present invention. [Diagram 2] FIG. 1 illustrates a control unit 110 according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram showing a processing operation in an information processing device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] An information processing device according to an embodiment of the present invention has a voice processing unit that performs voice change processing on a voice picked up by a microphone, and a storage unit that stores the voice that has been subjected to the voice change processing. In this manner, in this embodiment, only the voice that has been subjected to the voice change processing is stored in the storage unit. Therefore, in this embodiment, even if a third party hears the voice stored in the storage unit, the third party cannot identify who is speaking. In other words, in this embodiment, it is possible to record voice while protecting privacy.

[0013] The sound to be subjected to the voice change process by the sound processor may be a part of the sound picked up by the microphone, so that the sound other than the part of the sound can be recorded without being subjected to the voice change process.

[0014] The part of the sounds may be sounds with a frequency between 400 Hz and 700 Hz. In this way, only sounds in the frequency range of human voices are subjected to voice change processing. As a result, it is possible to record sounds other than human voices without undergoing voice change processing while protecting privacy.

[0015] The part of the sound may be the voice of a specific person or the voice of a person other than the specific person. In this way, it is possible to record the sound while protecting the privacy of a specific person.

[0016] The information processing device may further include a voice utterance determining unit that determines whether or not a person speaking is the specific person based on the voice recorded by the microphone and / or the image captured by the camera. In this way, it becomes possible to determine whether or not a specific person's voice is speaking.

[0017] The information processing device may further include a voice determination unit that determines whether or not a person is speaking based on an image captured by the camera, and the voice to which the voice processing unit applies voice change processing is applied to a voice collected while it is determined that a person is speaking. In this way, it is possible to record sounds other than the sound of an object speaking without applying voice change processing, while protecting privacy.

[0018] The microphone may be adapted to pick up sounds from within the vehicle, making it possible to record sounds while protecting the privacy of passengers within the vehicle.

[0019] The inside of the moving body may be divided into a plurality of regions, each of the plurality of regions may be provided with a microphone for picking up the sound of the corresponding region, and the sound to be subjected to the voice change process by the sound processing unit may be sound picked up by some of the plurality of microphones provided in the moving body. In this way, it is possible to record sound while protecting the privacy of a person in a specific region.

[0020] Two microphones may be installed inside the moving body, the information processing unit may further include a voice generation position identification unit that identifies the position where the voice is generated based on the voice picked up by the two microphones, and the voice to which the voice processing unit applies voice change processing may be a voice generated within a predetermined area. In this way, it is possible to record voice while protecting the privacy of a person in a specific area.

[0021] The information processing device may further include a temporary storage unit for temporarily storing the voice picked up by the microphone. In this way, it becomes possible to use the voice stored in the storage unit when, for example, it is necessary to identify the speaker in investigating the cause of an event such as an accident.

[0022] Moreover, an information processing method according to one embodiment of the present invention is an information processing method executed by a computer, and includes a voice processing step of performing a voice change process on a voice collected by a microphone, and a storage processing step of storing the voice that has been subjected to the voice change process in a storage unit. Thus, in this embodiment, only the voice that has been subjected to the voice change process is stored in the storage unit. Therefore, in this embodiment, even if a third party hears the voice stored in the storage unit, the third party cannot identify who is the speaker. In other words, in this embodiment, it is possible to record voice while protecting privacy.

[0023] Moreover, an information processing program according to an embodiment of the present invention causes a computer to execute the above-mentioned information processing method. Therefore, in this embodiment, it is possible to record audio while protecting privacy by using a computer.

[0024] Moreover, a computer-readable storage medium according to an embodiment of the present invention stores the above-mentioned information processing program. Therefore, in this embodiment, the above-mentioned information processing program can be distributed as a standalone program in addition to being incorporated into a device, and version upgrades can be easily performed. EXAMPLES

[0025] <Information processing device 100> 1 is a diagram showing an information processing device 100 according to an embodiment of the present invention. The information processing device 100 is, for example, a device installed in an automobile (mobile object), such as a drive recorder or a smartphone, and stores voices inside the automobile. The information processing device 100 may transmit the stored voices to a cloud (external device).

[0026] The information processing device 100 has a control unit 110, a storage unit 120, a microphone 130, a communication unit 140, and a camera 150. The control unit 110 is configured by a computer having a CPU and the like. The storage unit 120 is, for example, a storage device such as a hard disk or a memory. The microphone 130 is a device that collects sound. The communication unit 140 is a communication device for transmitting and receiving information to and from other devices. The camera 150 is a device that captures images.

[0027] 2 is a diagram showing the control unit 110 according to an embodiment of the present invention. The control unit 110 includes a voice processing unit 111, a storage processing unit 112, and a transmission processing unit 113.

[0028] The voice processing unit 111 applies voice change processing to the voice picked up by the microphone 130. The voice change processing is a process of converting the voice so that the person speaking cannot be identified while the contents of the conversation being spoken can be understood, and is, for example, a voice conversion process such as pitch shift processing, formant shift processing, delay processing, echo processing, or a combination of these processes.

[0029] The storage processing unit 112 stores the voice that has been subjected to the voice change processing by the voice processing unit 111 in the storage unit 120. The transmission processing unit 113 transmits the voice stored in the storage unit 120 to an external device via the communication unit .

[0030] In this way, in this embodiment, only the voice that has been subjected to the voice change process is stored in the storage unit 120. Therefore, in this embodiment, even if a third party hears the voice stored in the storage unit 120, the third party cannot identify who the speaker is. Also, in this embodiment, only the voice that has been subjected to the voice change process is transmitted to the external device. Therefore, in this embodiment, even if a third party hears the voice transmitted to the external device, the third party cannot identify who the speaker is. In other words, in this embodiment, it is possible to record voice while protecting privacy.

[0031] The storage processing unit 112 may store the voice picked up by the microphone 130 in the storage unit 120, and the transmission processing unit 113 may transmit the voice that has been subjected to voice change processing by the voice processing unit 111 to an external device via the communication unit 130. In this manner, it becomes possible to record voice that has not been subjected to voice change processing in the storage unit 120 while preventing a third party from identifying the speaker from the voice transmitted to the external device, and it becomes possible to use the voice stored in the storage unit 120 when it is necessary to identify the speaker.

[0032] At this time, it is preferable that the storage processing unit 112 encrypts the voice picked up by the microphone 130 and stores the encrypted voice in the storage unit 120. It is also preferable that the voice is encrypted so that only a specific person (for example, a user of the information processing device 100) can decrypt it. In this way, even if the data stored in the storage unit 120 is obtained by a third party, it is possible to prevent the third party from decrypting the data, and it is also possible to prevent the third party from listening to the voice stored in the storage unit 120.

[0033] 3 is a diagram showing a processing operation in an information processing device according to an embodiment of the present invention. The voice processing unit 111 performs voice change processing on the voice collected by the microphone 130 (step S301). The storage processing unit 112 stores the voice that has been subjected to voice change processing by the voice processing unit 111 in the storage unit 120 (step S302). The transmission processing unit 113 transmits the voice stored in the storage unit 120 to an external device (step S303).

[0034] <Processing specific voice> The audio processor 111 may apply voice change processing to all of the audio picked up by the microphone, or may apply voice change processing to a part of the audio picked up by the microphone.

[0035] The audio processor 111 may, for example, apply voice change processing only to sounds with frequencies between 400 Hz and 700 Hz among sounds picked up by the microphone. In this way, only sounds in the frequency range of human voices are subjected to voice change processing. As a result, it becomes possible to record sounds other than human voices without applying voice change processing while protecting privacy.

[0036] Also, it is preferable that the audio processor 111 applies voice change processing only to the voice of a specific person, for example. In this way, it becomes possible to record audio while protecting the privacy of a specific person.

[0037] Also, the audio processor 111 may perform voice change processing only on the voices of people other than a specific person, for example. In this way, it becomes possible to record audio while protecting the privacy of people other than the specific person.

[0038] In this case, the control unit 110 may preferably have a speaking person determination unit 114 that determines whether the person speaking is a specified person or not based on, for example, the voice recorded by the microphone 130 and / or the image captured by the camera 150.

[0039] For example, the storage unit 120 may store information about the voice of a specific person, such as voice data of the voice of the specific person and voice features, and the speaking person discrimination unit 114 may use existing voice analysis technology to determine whether or not the voice recorded by the microphone 130 contains the voice of the specific person, based on this stored information and the voice recorded by the microphone 130. Also, for example, the storage unit 120 may store information about the face of the specific person, such as image data of the face of the specific person and facial features, and the speaking person discrimination unit 114 may use existing image analysis technology to determine whether or not the voice of the specific person is speaking, based on this stored information and an image captured by the camera 150.

[0040] The control unit 110 may have a voice judging unit 115 that judges whether or not a person is speaking based on an image captured by the camera 150. The voice judging unit 115 judges whether or not a person is speaking in the image captured by the camera 150, for example, by using an existing image analysis technique. Then, the audio processing unit 111 may apply voice change processing only to the audio picked up while it is judged that a person is speaking. In this way, it becomes possible to record sounds other than the sound while a person is speaking without applying voice change processing, while protecting privacy.

[0041] <Processing of sounds generated in specific areas> The interior of the vehicle may be divided into a plurality of regions, a microphone 130 may be installed in each of the plurality of regions, and each of the plurality of microphones 130 may record the sound of the region in which it is installed. Then, the sound processing unit 111 may perform a voice change process only on the sound picked up by some of the plurality of microphones 130. In this manner, it becomes possible to record the sound while protecting the privacy of a person in a specific region.

[0042] For example, the microphone 130 may include a microphone (driver's seat microphone) that collects only the voice of the driver's seat, a microphone (passenger's seat microphone) that collects only the voice of the passenger's seat, and a microphone (rear seat microphone) that collects only the voice of the rear seat. The audio processor 111 may then apply voice change processing only to the voice collected by the driver's seat microphone. In this way, it is possible to record audio while protecting the privacy of the driver. The audio processor 111 may also apply voice change processing only to the voice collected by the passenger's seat microphone and the voice collected by the rear seat microphone. In this way, it is possible to record audio while protecting the privacy of people other than the driver.

[0043] Two microphones 130 may also be installed in the automobile. By measuring the difference between the sounds picked up by the two microphones 130, it is possible to identify the position where the sound picked up by the microphone 130 is generated. Therefore, it is preferable that the control unit 110 has a sound generation position identification unit 116 that identifies the position where the sound is generated based on the sounds picked up by the two microphones 130. Then, the sound processing unit 111 may apply voice change processing only to the sound generated within a predetermined area. This also makes it possible to record the sound while protecting the privacy of a person in a specific area.

[0044] <Temporary storage of voice that has not undergone voice change processing> The control unit 110 may have a temporary storage processing unit 117 that temporarily stores the voice collected by the microphone 130 in the storage unit 120. The temporary storage processing unit 117 may, for example, store the voice collected by the microphone 130 in the storage unit 120, and erase the voice from the storage unit 120 after a predetermined time has passed since it was stored. In this case, for example, the information processing device 100 may have a means for acquiring information indicating that an event such as an accident has occurred in an automobile in which the information processing device 100 is installed, and the temporary storage processing unit 117 may prevent the voice temporarily stored in the storage unit 120 by the temporary storage processing unit 117 from being erased when an event such as an accident occurs. In this way, it is possible to store the voice before and after the occurrence of an event such as an accident in the storage unit 120 without performing voice change processing. As a result, it is possible to use the voice stored in the storage unit 120 when it is necessary to identify the speaker in investigating the cause of the occurrence of an event such as an accident.

[0045] The information processing device 100 may have a storage device in addition to the memory unit 120, and the temporary storage processing unit 117 may store the audio picked up by the microphone 130 temporarily in this storage device instead of in the memory unit 120.

[0046] The present invention has been described above in terms of preferred embodiments thereof. Although the present invention has been described herein with reference to specific examples, various modifications and variations can be made to these examples without departing from the spirit and scope of the present invention as set forth in the claims. [Explanation of symbols]

[0047] 100 Information processing device 110 Control section 111 Audio processing unit 112 Memory Processing Unit 113 Transmission processing unit 114 Voice Person Identification Unit 115 Vocalisation Judgment Unit 116 Voice generation position identification unit 117 Temporary Storage Processing Unit 120 Storage section 130 Mike 140 Communications Department 150 Camera

Claims

[Claim 1] a voice processing unit that performs a voice change process on the voice picked up by the microphone; A storage unit that stores the voice that has been subjected to the voice change processing.

Citation Information

Patent Citations

  • Communication device, communication method, communication program and communication system

    JP2018195926A

  • Operating data recording system, operating data recorder, terminal device and operating data recording method

    JP2020077237A

  • Recording device, recording method, and program

    WO2018138983A1

  • Recording device, recording method, and program

    JP2018082390A