JP7768849B2 - On-vehicle device - Google Patents

Description

The disclosed embodiments relate to an in-vehicle device, a voice processing method, and a voice processing system.

There are in-vehicle devices such as drive recorders that record video of the vehicle's surroundings and audio from within the vehicle cabin. Some in-vehicle devices also allow the audio recording function to be switched on and off when recording video (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2021-157290

However, while the in-vehicle device can protect the user's privacy when the recording function is turned off, it cannot record audio information inside the vehicle, which is important for determining the cause of an accident, for example.

One aspect of the embodiment has been made in consideration of the above, and aims to provide an in-vehicle device, audio processing method, and audio processing system that can record important in-vehicle audio while protecting the user's privacy.

An in-vehicle device according to one aspect of the embodiment includes a controller. The controller acquires in-vehicle audio and an outside-vehicle video captured outside the vehicle. The controller detects a pre-registered user's voice from the in-vehicle audio . The controller processes the detected user's voice from the in-vehicle audio. The controller records the processed in-vehicle audio, which is the processed user's voice, and the outside-vehicle video in a storage device.

The vehicle-mounted device according to one aspect of the embodiment has an effect of being able to record important sounds inside the vehicle cabin while protecting the privacy of the user.

FIG. 1 is an explanatory diagram illustrating an example of the configuration of an in-vehicle device according to an embodiment. FIG. 2 is a flowchart illustrating an example of a process executed by the controller of the vehicle-mounted device according to the embodiment. FIG. 3 is a flowchart showing a modified example of the process executed by the controller of the vehicle-mounted device according to the embodiment. FIG. 4 is an explanatory diagram illustrating an example of the configuration of a voice processing system according to an embodiment. FIG. 5 is a flowchart illustrating an example of processing executed by the center device according to the embodiment.

Embodiments of an in-vehicle device, audio processing method, and audio processing system will be described in detail below with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below. The in-vehicle device according to the embodiments is a drive recorder that is mounted on a vehicle and captures and records images of the area around the vehicle (hereinafter referred to as "exterior vehicle images") and collects and records audio from within the vehicle cabin (hereinafter referred to as "in-vehicle audio").

[1. Configuration example of in-vehicle device]
First, a configuration example of an in-vehicle device 1 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is an explanatory diagram showing a configuration example of an in-vehicle device 1 according to an embodiment.

As shown in FIG. 1, the vehicle-mounted device 1 includes cameras 20 and 21, a sensor 22, a microphone 23, a controller 3, and a storage 4. The camera 20 is an imaging device that captures video of the interior of the vehicle (hereinafter referred to as "in-vehicle video 50"). The camera 21 is an imaging device that captures video of the exterior of the vehicle 51. The sensor 22 is a detection device that detects an impact applied to the vehicle in which the vehicle-mounted device 1 is installed. The microphone 23 is a sound collection device that collects in-vehicle audio 52.

The controller 3 includes a microcomputer with a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and various other circuits. The controller 3 controls the overall operation of the vehicle-mounted device 1 by having the CPU execute programs stored in the ROM using the RAM as a working area.

The controller 3 may be partially or entirely configured using hardware such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

Storage 4 is an information storage device such as a data flash, and stores in-vehicle video 50, outside-vehicle video 51, in-vehicle audio 52, and user information 53. User information 53 includes voice information 54 and a facial image 55. Voice information 54 is pre-registered voice information of user 10 of in-vehicle device 1. Voice information 54 includes, for example, voiceprint information and voice frequency information of user 10. Facial image 55 is an image of the face of user 10.

Using a specific application program (hereinafter referred to as "app") installed on a terminal device such as a smartphone (hereinafter referred to as "user terminal 11"), the user 10 can record their own voice and capture an image 55 of their face, which can then be sent from the user terminal 11 to the in-vehicle device 1. The controller 3 stores and registers the user information 53 received from the user terminal 11 in the storage 4.

When the vehicle-mounted device 1 is started, the controller 3 records the in-vehicle image 50 input from the camera 20, the outside-vehicle image 51 input from the camera 21, and the in-vehicle audio 52 input from the microphone 23 in the storage 4. The controller 3 overwrites and records the outside-vehicle image 51 and the in-vehicle audio 52 in the storage 4 every predetermined time (for example, every two hours).

When an audio output trigger is activated, the controller 3 outputs an outside-vehicle image 51 and an inside-vehicle audio 52. The in-vehicle device 1 activates the audio output trigger, for example, when it receives a request to output recorded audio from an app on the user terminal 11. The in-vehicle device 1 may also be configured to activate the audio output trigger, for example, when a predetermined output operation is performed on an operation unit (not shown).

In this way, by recording and outputting the outside-vehicle video 51 and the inside-vehicle audio 52, the in-vehicle device 1 can contribute to clarifying the cause of a vehicle accident, for example, by outputting the recorded outside-vehicle video 51 and inside-vehicle audio 52 in the event of a vehicle accident.

However, some in-vehicle device users 10 may not want in-vehicle audio 52 to be heard by third parties for privacy reasons. For this reason, some in-vehicle devices allow the recording function to be turned off. However, when the recording function is turned off, the in-vehicle device cannot record audio information 54 other than conversations within the vehicle cabin, which is important for determining the cause of the accident.

The in-vehicle device 1 according to the embodiment is therefore configured to record important in-vehicle audio 52 while protecting the privacy of the user 10. Specifically, the controller 3 of the in-vehicle device 1 records the in-vehicle audio 52 and detects the voice of the user 10 from the recorded in-vehicle audio 52 that corresponds to the voice information 54 of the user 10 that has been registered in advance. The controller 3 then processes the detected voice of the user 10.

With the vehicle-mounted device 1, the controller 3 processes the recorded voice of the user 10 to make it impossible to identify the user 10 from the voice, thereby protecting the privacy of the user 10 while recording important in-vehicle voice 52.

At this time, the controller 3 processes the user's 10 voice so that the detected user's 10 voice is erased. For example, the controller 3 erases the user's 10 voice from the in-vehicle voice 52 by synthesizing the in-vehicle voice 52 with an antiphase sound of the user's 10 speech. This allows the vehicle-mounted device 1 to record in-vehicle voice 52 other than the user's 10 voice, thereby enabling important in-vehicle voice 52 to be recorded while reliably protecting the user's 10 privacy.

The controller 3 also processes the user's 10 voice by performing a voice change process to convert the detected user's 10 voice into a voice that does not identify the speaker. As a result, if, for example, the content of the user's 10 speech at the time of an accident includes content that can lead to the elucidation of the cause of the accident, the vehicle-mounted device 1 can record the in-vehicle voice 52 including the content of the user's 10 speech without identifying the user 10. Therefore, the vehicle-mounted device 1 can record important in-vehicle voice 52 while reliably protecting the user's 10 privacy.

The controller 3 also stores pre-registered voice information 54 of the user 10, compares the in-vehicle voice 52 with the user 10's voice information 54, and detects the user 10's voice from the in-vehicle voice 52. This allows the vehicle-mounted device 1 to accurately detect the user 10's voice from the in-vehicle voice 52.

The controller 3 also stores in the storage 4 a pre-registered facial image 55 of the user 10 in association with the user's 10 voice information 54. The controller 3 then compares the in-vehicle video 50 with the user's 10 facial image 55 (e.g., through facial recognition processing), and when the controller 3 detects the user 10 from the in-vehicle video 50, it detects the user's voice from the in-vehicle audio 52. This allows the in-vehicle device 1 to more reliably detect the user's voice from the in-vehicle audio 52, even if, for example, there is another occupant with a similar voice quality.

The controller 3 may also be configured to output in-vehicle audio 52 that is a processed version of the user's 10 voice when an audio output trigger is activated. In this case, the controller 3 starts processing the user's 10 voice when the audio output trigger is activated. This means that the vehicle-mounted device 1 does not need to process the user's 10 voice unless the audio output trigger is activated, thereby reducing the processing load on the controller 3 and the power consumption required for voice processing.

The controller 3 may also be configured to start processing the user's 10 voice when the in-vehicle device 1 is started. This allows the in-vehicle device 1 to process all recorded in-vehicle voice 52 so that the speaker of the user's 10 voice cannot be identified by a third party, thereby reliably protecting the privacy of the user 10.

The controller 3 may also be configured to process the user's 10 voice and record the in-vehicle voice 52 so that the user's 10 voice is erased from the time the vehicle-mounted device 1 is started until the voice recording trigger is activated. The vehicle-mounted device 1 activates the voice recording trigger, for example, when the controller 3 receives a detection result from the sensor 22 indicating that the vehicle has been impacted.

In this case, when the voice recording trigger is activated, the controller processes the voice of the user 10 and records the in-vehicle voice 52 so that the voice of the user 10 is converted into voice that does not identify the speaker.

As a result, the in-vehicle device 1 can reduce the amount of storage 4 capacity used by erasing the user's 10 voice from the in-vehicle voice 52 during a period when there is little likelihood of the in-vehicle voice 52 being requested, for example, before an audio recording trigger is activated due to the occurrence of a vehicle accident.

In addition, during the period when a voice recording trigger is activated due to a vehicle accident and output of in-vehicle voice 52 is likely to be requested, the in-vehicle device 1 processes the user's 10 voice so that the speaker cannot be identified to a third party, so that conversation content important to determining the cause of the accident can be output.

In this way, when an accident occurs, the in-vehicle device 1 records collision sounds and surrounding audio information 54 as important information, but does not record conversations inside the vehicle, thereby satisfying the need to not record private information while preserving important information. Furthermore, the in-vehicle device 1 can record in-vehicle audio 52 when necessary without identifying individuals.

[2. Processing Executed by the In-Vehicle Controller]
Next, a process executed by the controller 3 of the vehicle-mounted device 1 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a flowchart showing an example of a process executed by the controller 3 of the vehicle-mounted device 1 according to the embodiment.

While the controller 3 is running, it repeatedly executes the process shown in Figure 2. Specifically, as shown in Figure 2, when the vehicle-mounted device 1 is started, the controller 3 first determines whether user information 53 has been input (step S101).

At this time, the controller 3 determines whether or not voice information 54 of the user 10 has been input from the microphone 23 or an app on the user terminal 11. The controller 3 also determines whether or not a facial image 55 of the user 10 has been input from the camera 20 capturing images of the interior of the vehicle or an app on the user terminal 11. If the controller 3 determines that user information 53 has not been input (step S101, No), it proceeds to step S103.

If the controller 3 determines that user information 53 has been input (step S101, Yes), it registers the user information 53 in the storage 4 (step S102). For example, the controller 3 registers the user information 53 by storing the user's 10 voice information 54 and facial image 55 in the storage 4.

Then, the controller 3 records the vehicle exterior image 51 captured by the camera 21 and the vehicle interior sound 52 collected by the microphone 23 in the storage 4 (step S103). Next, the controller 3 determines whether or not there is registered user information 53 in the storage 4 (step S104). If the controller 3 determines that there is no registered user information 53 (step S104, No), it ends the current processing.

If the controller 3 determines that registered user information 53 exists (step S104, Yes), it detects the voice of the user 10 from the recorded in-vehicle voice 52 that corresponds to the pre-registered voice information 54 of the user 10 (step S105).

At this time, the controller 3 may, for example, compare the in-vehicle audio 52 with the user's 10 audio information 54 and detect the user's 10 audio from the in-vehicle audio 52. The controller 3 may also be configured to compare the in-vehicle video 50 captured by the camera 20 capturing the interior of the vehicle with the user's 10 facial image 55, and, if the controller 3 detects the user 10 from the in-vehicle video 50, detect the user's 10 audio from the in-vehicle audio 52.

The controller 3 then processes the detected voice of the user 10 (step S106). In this way, the controller 3 begins processing the voice of the user 10 when the vehicle-mounted device 1 is started.

At this time, the controller 3 processes the user's 10 voice so that the user's 10 voice is erased. Alternatively, the controller 3 processes the user's 10 voice so that the user's 10 voice is converted into voice that does not identify the speaker of the user's 10 voice.

The controller 3 then records the in-vehicle voice 52, which is the processed voice of the user 10, in the storage 4 (step S107) and determines whether the voice output trigger has been activated (step S108).

The in-vehicle device 1 activates an audio output trigger, for example, when it receives a request to output recorded audio from an app on the user terminal 11. The in-vehicle device 1 may also be configured to activate an audio output trigger, for example, when a predetermined output operation is performed on an operation unit (not shown).

If the controller 3 determines that the audio output trigger has not been activated (step S108, No), it ends the current processing. If the controller 3 determines that the audio output trigger has been activated (step S108, Yes), it outputs in-vehicle audio 52, which is a processed version of the user's 10 voice (step S109), and ends the current processing.

At this time, the controller 3 outputs the outside-vehicle image 51 along with the inside-vehicle audio 52. The controller 3 outputs the outside-vehicle image 51 and the inside-vehicle audio 52 via wireless communication to a center device 12 provided at an information collection center, for example. The controller 3 may also be configured to output the outside-vehicle image 51 and the inside-vehicle audio 52 to an external information storage medium, for example.

3. Modification of the process executed by the controller of the vehicle-mounted device
Next, a modified example of the process executed by the controller 3 of the vehicle-mounted device 1 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing a modified example of the process executed by the controller 3 of the vehicle-mounted device 1 according to the embodiment.

The controller 3 may be configured to execute the process shown in FIG. 3 instead of the process shown in FIG. 2. In this case, the controller 3 repeatedly executes the process shown in FIG. 3 while it is running. As shown in FIG. 3, when the vehicle-mounted device 1 is started, the controller 3 first determines whether user information 53 has been input (step S201).

At this time, the controller 3 determines whether or not voice information 54 of the user 10 has been input from the microphone 23 or an application on the user terminal 11. The controller 3 also determines whether or not a facial image 55 of the user 10 has been input from the camera 20 capturing images of the interior of the vehicle or an application on the user terminal 11. If the controller 3 determines that user information 53 has not been input (step S201, No), it proceeds to step S203.

If the controller 3 determines that user information 53 has been input (Yes in step S201), it registers the user information 53 in the storage 4 (step S202). For example, the controller 3 registers the user information 53 by storing the voice information 54 and facial image 55 of the user 10 in the storage 4.

Then, the controller 3 records the vehicle exterior image 51 captured by the camera 21 and the vehicle interior sound 52 collected by the microphone 23 in the storage 4 (step S203). Next, the controller 3 determines whether or not there is registered user information 53 in the storage 4 (step S204). If the controller 3 determines that there is no registered user information 53 (step S204, No), it ends the current processing.

If the controller 3 determines that registered user information 53 exists (step S204, Yes), it detects the voice of the user 10 from the recorded in-vehicle voice 52 that corresponds to the pre-registered voice information 54 of the user 10 (step S205).

At this time, the controller 3 may, for example, compare the in-vehicle audio 52 with the user's 10 audio information 54 and detect the user's 10 audio from the in-vehicle audio 52. The controller 3 may also be configured to compare the in-vehicle video 50 captured by the camera 20 capturing the interior of the vehicle with the user's 10 facial image 55, and, if the controller 3 detects the user 10 from the in-vehicle video 50, detect the user's 10 audio from the in-vehicle audio 52.

Next, the controller 3 processes the user's 10 voice so that the user's 10 voice is erased. The controller 3 then records the in-vehicle voice 52 from which the user's 10 voice has been erased in the storage 4 (step S206).

The controller 3 then determines whether the voice recording trigger has been activated (step S207). The vehicle-mounted device 1 activates the voice recording trigger, for example, when the controller 3 receives a detection result from the sensor 22 indicating that an impact has been applied to the vehicle.

If the controller 3 determines that the voice recording trigger has not been activated (step S207, No), it proceeds to step S203. In this way, the controller 3 processes the voice of the user 10 and records the in-vehicle voice 52 so that the voice of the user 10 is erased from the time the in-vehicle device 1 is started until the voice recording trigger is activated.

Furthermore, when the controller 3 determines that the voice recording trigger has been activated (step S207, Yes), it processes the voice of the user 10 so that the voice of the user 10 is converted into voice that does not identify the speaker of the voice of the user 10. Then, the controller 3 records the in-vehicle voice 52 into which the voice of the user 10 has been converted in the storage 4 (step S208). In this way, the controller 3 starts processing the voice of the user 10 when the voice recording trigger is activated.

The controller 3 then determines whether an audio output trigger has been activated (step S209). The vehicle-mounted device 1 activates the audio output trigger, for example, when it receives a request to output recorded audio from an app on the user terminal 11. The vehicle-mounted device 1 may also be configured to activate the audio output trigger, for example, when a predetermined output operation is performed on an operation unit (not shown).

If the controller 3 determines that the audio output trigger has not been activated (step S209, No), it ends the current processing. If the controller 3 determines that the audio output trigger has been activated (step S209, Yes), it outputs in-vehicle audio 52, which is a processed version of the user's 10 voice (step S210), and ends the current processing.

At this time, the controller 3 outputs the outside-vehicle image 51 along with the inside-vehicle audio 52. The controller 3 outputs the outside-vehicle image 51 and the inside-vehicle audio 52 via wireless communication to a center device 12 provided at an information collection center, for example. The controller 3 may also be configured to output the outside-vehicle image 51 and the inside-vehicle audio 52 to an external information storage medium, for example.

[4. Example of voice processing system configuration]
Next, a configuration example of the voice processing system 100 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is an explanatory diagram showing a configuration example of the voice processing system 100 according to the embodiment.

As shown in FIG. 4, the voice processing system 100 includes, in addition to the vehicle-mounted device 1, a center device 12 installed in an information collection center. The center device 12 includes a microcomputer having a CPU, ROM, RAM, etc., and various circuits. The center device 12 is capable of wireless communication with the vehicle-mounted device 1. The center device 12 is also capable of wireless communication with the user terminal 11.

The center device 12 includes a storage 13. The center device 12 stores user information 53 of pre-registered users 10 in the storage 13. Using a specific application installed on the user terminal 11, the user 10 can record their own voice and capture an image 55 of their face, which can then be sent from the user terminal 11 to the center device 12.

In addition, the user 10 can use the app to send vehicle information 56 of the vehicle they are using from the user terminal 11 to the center device 12. The vehicle information 56 includes the vehicle's license plate number, chassis number, and the vehicle's preset ID.

The center device 12 stores and registers the voice information 54, facial image 55, and vehicle information 56 of the user 10 received from the user terminal 11 in the storage 13. The center device 12 transmits the user information 53, including the voice information 54 and facial image 55 of the user 10 registered in the storage 13, to the vehicle-mounted device 1.

The vehicle-mounted device 1 records in-vehicle voice 52 and detects, from the recorded in-vehicle voice 52, the voice of the user 10 that corresponds to the voice information 54 of the user 10 received from the center device 12. The vehicle-mounted device 1 then processes the detected voice of the user 10, similar to the vehicle-mounted device 1 shown in Figure 1.

With the voice processing system 100, the vehicle-mounted device 1 processes the recorded voice of the user 10 to make it impossible to identify the user 10 from the voice, thereby protecting the privacy of the user 10 while recording important in-vehicle voice 52.

Furthermore, when the center device 12 receives occupant information from the vehicle-mounted device 1, it transmits voice information 54 of the user 10 corresponding to the occupant information to the vehicle-mounted device 1. The vehicle-mounted device 1 that receives the voice information 54 processes the voice of the user 10 detected from the recorded in-vehicle voice 52, similar to the vehicle-mounted device 1 shown in Figure 1.

As a result, even if the user 10 is using a vehicle for the first time, such as a rental car or car sharing vehicle, the center device 12 can send the user's own voice information 54 to the vehicle-mounted device 1 of the vehicle they are using, making it impossible to identify the speaker of the user's own voice stored in the vehicle-mounted device 1.

5. Processing Executed by the Controller of the Center Device
Next, a process executed by the center device 12 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of a process executed by the center device 12 according to the embodiment.

The center device 12 repeatedly executes the process shown in Figure 5 while the power is on. Specifically, when the center device 12 is turned on, it first determines whether user information 53 has been input (step S301).

At this time, the center device 12 determines whether voice information 54 of the user 10 has been input from the in-vehicle device 1 or the app on the user terminal 11. The controller 3 also determines whether a facial image 55 of the user 10 has been input from the in-vehicle device 1 or the app on the user terminal 11.

Furthermore, the center device 12 determines whether vehicle information 56 on which the onboard device 1 is installed has been input from the onboard device 1 or an app on the user terminal 11. The vehicle information 56 includes the vehicle's license plate number, chassis number, and the vehicle's preset ID, etc.

If the center device 12 determines that user information 53 has not been input (step S301, No), it proceeds to step S305. If the center device 12 determines that user information 53 has been input (step S301, Yes), it stores and registers the input user information 53 in the storage 13 (step S302).

Then, the center device 12 determines whether the user information 53 has been input from an app on the user terminal 11 (step S303). If the center device 12 determines that the user information 53 has not been input from an app (step S303, No), the center device 12 proceeds to step S305.

Furthermore, if the center device 12 determines that the user information 53 has been input from an app (step S303, Yes), it transmits the user's 10 voice information 54 to the user's 10 vehicle-mounted device 1 (step S304) and terminates this processing.

Furthermore, in step S305, the center device 12 determines whether occupant information has been received from the vehicle-mounted device 1. The occupant information may be, for example, voice information 54 of the user of the vehicle in which the vehicle-mounted device 1 is installed, a facial image 55 of the user, or vehicle information 56.

If the center device 12 determines that it has not received the vehicle information 56 (step S305, No), it terminates this processing. If the center device 12 determines that it has received the vehicle information 56 (step S305, Yes), it transmits the user 10's voice information 54 corresponding to the occupant information to the vehicle-mounted device 1 (step S306), and terminates this processing.

The controller 3 of the vehicle-mounted device 1 in the voice processing system 100 executes the same processing as that shown in FIG. 2 or FIG. 3. However, in this case, in step S101 shown in FIG. 2 and step S201 shown in FIG. 3, the controller 3 of the vehicle-mounted device 1 determines whether voice information 54 of the user 10 has been input from the microphone 23, an app on the user terminal 11, or the center device 12. The controller 3 of the vehicle-mounted device 1 determines whether a facial image 55 of the user 10 has been input from the camera 20 capturing images of the interior of the vehicle, an app on the user terminal 11, or the center device 12.

[6. Notes]
As an appendix, the features of the present invention are as follows.
(1)
detecting a user's voice corresponding to pre-registered user voice information from voices within the vehicle;
An in-vehicle device comprising a controller that processes the detected user's voice.
(2)
The controller
The vehicle-mounted device according to (1), further comprising: processing the user's voice so that the detected user's voice is deleted.
(3)
The controller
The vehicle-mounted device according to (1), further comprising: processing the detected user's voice so that the detected user's voice is converted into voice from which a speaker cannot be identified.
(4)
The controller
storing the pre-registered user's voice information;
The vehicle-mounted device according to any one of (1) to (3), wherein the vehicle-mounted device detects the user's voice from the vehicle-mounted voice by comparing the voice in the vehicle with voice information of the user.
(5)
The controller
storing the pre-registered face image of the user and the voice information of the user in association with each other;
The vehicle-mounted device described in (4) above compares an image of the interior of the vehicle captured by a camera that captures images of the interior of the vehicle with an image of the user's face, and when the user is detected from the image of the interior of the vehicle, detects the user's voice from the audio within the vehicle.
(6)
The controller
The vehicle-mounted device according to any one of (1) to (5), wherein when a voice output trigger is activated, a voice in the vehicle cabin is output that is a processed version of the user's voice.
(7)
The controller
The vehicle-mounted device according to (6), wherein processing of the user's voice is started when the voice output trigger is activated.
(8)
The controller
The in-vehicle device according to (6), which starts processing the user's voice when activated.
(9)
The controller
recording the voice of the user in the vehicle cabin by processing the voice of the user so that the voice of the user is erased from the time of activation until a voice recording trigger is activated;
The vehicle-mounted device according to any one of (1) to (6), wherein when the voice recording trigger is activated, the user's voice is processed and recorded in the vehicle cabin so that the user's voice is converted into voice that does not identify the speaker of the user's voice.
(10)
A voice processing method executed by a controller of an in-vehicle device, comprising:
detecting a user's voice corresponding to pre-registered user voice information from voices within the vehicle;
and processing the detected user's voice.
(11)
a vehicle-mounted device; and a center device capable of communicating with the vehicle-mounted device;
The center device
storing voice information of a user that is registered in advance;
transmitting voice information of the user to the vehicle-mounted device;
The vehicle-mounted device is
detecting a voice of the user corresponding to the voice information of the user received from the center device from the voices in the vehicle;
A voice processing system that processes the detected voice of the user.

Further advantages and modifications may readily occur to those skilled in the art. Therefore, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents.

REFERENCE SIGNS LIST 1 In-vehicle device 10 User 11 User terminal 12 Center device 20, 21 Camera 22 Sensor 23 Microphone 3 Controller 4, 13 Storage 51 Outside vehicle image 52 Inside vehicle voice 53 User information 54 Voice information 55 Facial image 56 Vehicle information 100 Voice processing system

Claims (4)

An in-vehicle device including a controller that records the acquired in-vehicle voice and outside-vehicle video in a storage device ,
The controller
During a period when no voice recording trigger is activated, the outside-of-vehicle video is recorded in a storage together with the inside-vehicle voice in which the user's voice has been muted, and
During a period when a voice recording trigger is activated, the outside-vehicle video is recorded in a storage together with the voice of the inside-vehicle voice that has been subjected to a voice change process to convert the inside-vehicle voice into a voice that does not identify the speaker of the user .
Onboard machine. The audio recording trigger is activated by the occurrence of a vehicle accident.
The vehicle-mounted device according to claim 1 . The user's voice is a pre-registered user's voice.
The vehicle-mounted device according to claim 1 . The controller
The video of the vehicle interior is compared with a pre-registered facial image of the user,
When the user is detected, the voice of the user is detected from the in-vehicle voice using voice information of the user that is registered in advance in association with a face image of the user.
The vehicle-mounted device according to claim 1 .