Sound command receiving apparatus, sound command receiving method, and computer program product

Abstract

A sound command receiving apparatus includes a sound command receiving section that receives a sound command, a detection section that detects a condition of a situation that causes the sound command to be unable to be properly recognized in an environment in which the sound command is issued, and an execution control section that executes a function of the received sound command when the sound command receiving section receives the sound command. When the detection section determines that the condition is not the condition of the situation that causes the sound command to be unable to be properly recognized, the sound command receiving section receives the sound command in a manner that a recognition rate of the sound command acquired by the sound command receiving section is equal to or higher than a first threshold value. When the detection section determines that the condition is the condition of the situation that causes the sound command to be unable to be properly recognized, the sound command receiving section receives the sound command in a manner that the recognition rate of the sound command acquired by the sound command receiving section is equal to or higher than a second threshold value that is smaller than the first threshold value.

Description

Technical Field

[0001] This disclosure relates to a voice command receiving device, a voice command receiving method, and a computer program product. Background Technology

[0002] Devices operated via voice commands are becoming increasingly diverse. For example, in vehicle recording devices, also known as dashcams, there are devices that record events via voice commands in addition to impact detection based on acceleration sensors (e.g., Non-Patent Document 1). Voice-command-based event recording allows for safe recording of events without the need for touch panels while driving, especially when recording accidents where the user is not involved. Patent Document 1 discloses a dashcam that records events by issuing voice commands based on acceleration-based event detection.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-154904

[0006] Non-patent literature

[0007] Non-patent literature 1: DRV-MR 760 [Searched on December 20, 2013], Internet (URL: https: / / www.kenwood.com / jp / car / drive-recorders / products / drv-mr760 / ). Summary of the Invention

[0008] The audio commands for recording events to the dashcam are pre-set to receive commands such as "ろくがかいし (Start recording)". To prevent false detections caused by other sounds, the audio commands are required to consist of a certain number of syllables. For example, "ろくがかいし (Start recording)" consists of 6 syllables. Therefore, to accurately recognize audio commands, the speaker usually speaks towards the direction of the microphone from which the audio command is input. A typical dashcam is positioned in front of the vehicle from the perspective of the passenger, thus it can appropriately recognize audio command inputs directed towards the direction of travel in front of the vehicle.

[0009] However, when a voice command is issued in a situation where it cannot be properly recognized, the recognition rate of the voice command becomes low, resulting in a situation where the instruction based on the voice command is not received. In such cases, for example, voice commands used to indicate urgent or immediate operations, such as those used for recording events in a dashcam, may cause delays in operation due to repetition of the voice command. Situations where a voice command cannot be properly recognized may occur, for example, when the person issuing the voice command is not facing the microphone that receives the voice command, as illustrated in this disclosure, among other conditions.

[0010] The purpose of this disclosure is to provide a voice command receiving device, a voice command receiving method, and a computer program product capable of performing voice command-based operations appropriately.

[0011] This disclosure relates to a voice command receiving device, comprising: a voice command receiving unit for receiving voice commands; a detection unit for detecting conditions in the environment in which the voice command is issued that cause the voice command to be inappropriately recognized; and an execution control unit for executing the function of the received voice command when the voice command receiving unit receives the voice command, wherein when the detection unit determines that the condition is not a condition causing the voice command to be inappropriately recognized, the voice command receiving unit receives the voice command with a recognition rate of the voice command obtained by the voice command receiving unit of at least a first threshold, and when the detection unit determines that the condition is a condition causing the voice command to be inappropriately recognized, the voice command receiving unit receives the voice command with a recognition rate of the voice command obtained by the voice command receiving unit of at least a second threshold that is less than the first threshold.

[0012] This disclosure relates to a method for receiving a voice command, comprising the following steps performed by a voice command receiving device: detecting conditions in the environment in which the voice command is issued that would cause the voice command to be inappropriately recognized; when it is determined that the conditions are not conditions that would cause the voice command to be inappropriately recognized, receiving the voice command with a recognition rate of at least a first threshold; when it is determined that the conditions are conditions that would cause the voice command to be inappropriately recognized, receiving the voice command with a recognition rate of at least a second threshold, wherein the second threshold is less than the first threshold; and when the voice command is received, performing the function of the received voice command.

[0013] The computer program product disclosed herein includes a computer program that causes a computer to perform the following steps: detecting a condition in an environment where a sound command is issued that would cause the sound command to be inappropriately recognized; when it is determined that the condition is not a condition that would cause the sound command to be inappropriately recognized, receiving a sound command with a recognition rate of the sound command of at least a first threshold; when it is determined that the condition is a condition that would cause the sound command to be inappropriately recognized, receiving a sound command with a recognition rate of at least a second threshold, the second threshold being less than the first threshold; and when the sound command is received, performing the function of the received sound command.

[0014] According to this disclosure, it is possible to perform operations based on voice commands appropriately. Attached Figure Description

[0015] Figure 1 This is a block diagram illustrating an example of the configuration of the recording device according to the first embodiment.

[0016] Figure 2 This is a flowchart illustrating the processing flow of the control unit involved in the first embodiment.

[0017] Figure 3 This is a block diagram illustrating an example of the configuration of the recording device according to the second embodiment.

[0018] Figure 4 This is a flowchart illustrating the processing flow of the control unit involved in the second embodiment.

[0019] Figure 5 This is a flowchart illustrating the processing flow of the control unit involved in the third embodiment.

[0020] Figure 6 This is a flowchart illustrating the processing flow of the control unit involved in the fourth embodiment.

[0021] Figure 7 This is a flowchart illustrating the processing flow of the control unit involved in the fifth embodiment.

[0022] Figure 8 This is a flowchart illustrating the processing flow of the control unit involved in the sixth embodiment.

[0023] Figure 9 This is a block diagram illustrating a configuration example of the recording device according to the seventh embodiment.

[0024] Figure 10 This is a flowchart illustrating the processing flow of the control unit involved in the seventh embodiment.

[0025] Figure 11 This is a block diagram illustrating a configuration example of the voice command receiving device according to the eighth embodiment.

[0026] Figure 12 This is a flowchart illustrating the processing flow of the voice command receiving device according to the eighth embodiment.

[0027] Figure 13 This is a flowchart illustrating the processing flow of the voice command receiving device according to the ninth embodiment.

[0028] Figure 14 This is a flowchart illustrating the processing flow of the voice command receiving device according to the tenth embodiment.

[0029] Figure 15 This is a flowchart illustrating the processing flow of the voice command receiving device according to the eleventh embodiment.

[0030] Figure 16 This is a flowchart illustrating the processing flow of the voice command receiving device according to the twelfth embodiment.

[0031] Figure 17 This is a flowchart illustrating the processing flow of the voice command receiving device according to the thirteenth embodiment. Detailed Implementation

[0032] Hereinafter, embodiments relating to this disclosure will be described in detail with reference to the accompanying drawings. However, this disclosure is not limited to these embodiments, and in the following embodiments, repeated descriptions are omitted by referring to the same parts with the same reference numerals. Furthermore, the voice command receiving apparatus disclosed herein envisions various devices that operate using voice commands, and the devices used are not limited to the following embodiments.

[0033] [First Implementation Method]

[0034] In the first embodiment, a recording device used in a vehicle will be described as an example of a voice command receiving device.

[0035] (Recording device)

[0036] use Figure 1 An example of the configuration of the recording device according to the first embodiment will be described. Figure 1 This is a block diagram illustrating an example of the configuration of the recording device according to the first embodiment.

[0037] The recording device 1 is a so-called dashcam that records images and other data related to events occurring in a vehicle. The recording device 1 can be a device mounted on a vehicle or a portable device that can be used within a vehicle. The recording device 1 may also include functions or configurations pre-installed in the vehicle, such as a navigation device. The recording device 1 processes received audio commands and changes their recognition rate based on whether passengers, including the driver, are facing the direction of travel.

[0038] like Figure 1 As shown, the recording device 1 includes a first camera 10, a second camera 12, a recording unit 14, a display unit 16, a microphone 18, an accelerometer 20, an operation unit 22, a GNSS (Global Navigation Satellite System) 24, and a control unit (recording control device) 26. The recording device 1 can be a device that integrates the first camera 10, the second camera 12, and the microphone 18 as a single unit, or it can be a device in which the first camera 10, the second camera 12, and the microphone 18 are separately configured.

[0039] The first camera 10 is a camera that captures images of the area surrounding the vehicle. For example, the first camera 10 may be a camera inherent to the recording device 1, or multiple cameras that capture images of the vehicle's front and rear directions. In the first embodiment, the first camera 10 may consist of multiple cameras positioned facing the front and rear of the vehicle, capturing images of the area centered on the front and rear of the vehicle. The first camera 10 may also be a single camera capable of capturing the entire sky or half the sky. The first camera 10 outputs the captured first image data to the image data acquisition unit 30 of the control unit 26. The first image data is, for example, a moving image composed of images at 30 frames per second.

[0040] The second camera 12 is a camera that captures images inside the vehicle's passenger compartment. The second camera 12 is positioned to capture at least the faces of the vehicle's occupants. The occupants may be only the driver, or may include other passengers besides the driver. The second camera 12 may be located, for example, inside or around the rearview mirror of the vehicle. The shooting range and shooting direction of the second camera 12 are fixed or substantially fixed. The second camera 12 may be, for example, a visible light camera or a near-infrared camera. The second camera 12 may also be, for example, a combination of a visible light camera and a near-infrared camera. The second camera 12 outputs the captured second image data to the image data acquisition unit 30 of the control unit 26. The second image data is, for example, a moving image composed of images at 30 frames per second. Furthermore, when it is not necessary to distinguish between the first and second image data, it is recorded as image data.

[0041] The first camera 10 and the second camera 12 may, for example, be a single camera capable of capturing the entire sky or half the sky. In this case, the image data obtained from capturing the entire sky or half the sky is designated as the first image data, including the entire image data, the area surrounding the vehicle, the area in front of the vehicle, etc. Additionally, the area capable of capturing the face of the occupant seated in the vehicle is designated as the second image data, also from capturing the entire sky or half the sky. Alternatively, the entire image data obtained from capturing the entire sky or half the sky may be processed as both the first and second image data.

[0042] The recording unit 14 is used for temporary storage of data in the recording device 1. The recording unit 14 may be, for example, a semiconductor storage element such as RAM (Random Access Memory), flash memory, or a recording medium such as a memory card. Alternatively, it may be an external recording unit wirelessly connected via a communication device not shown. The recording unit 14 records looped video data or event data based on control signals output from the recording control unit 36 ​​of the control unit 26.

[0043] The display unit 16 may be an integral display unit of the recording device 1, or a display unit shared with other systems including a navigation system. The display unit 16 may also be integrally formed with the first camera 10. The display unit 16 may be a display including, for example, a liquid crystal display (LCD) or an organic EL (Organic Electro-Luminescence) display. In the first embodiment, the display unit 16 is disposed on a control panel, instrument panel, center console, etc., in front of the driver of the vehicle. The display unit 16 displays images based on image signals output from the recording control unit 36 ​​of the control unit 26. The display unit 16 displays images captured by the first camera 10 or images recorded on the recording unit 14.

[0044] Microphone 18 collects sound from inside the vehicle's passenger compartment. In the first embodiment, microphone 18 is positioned to capture sound emitted by occupants of the vehicle, including the driver. Microphone 18 is disposed, for example, on a control panel, instrument panel, or center console. Microphone 18 collects sound related to sound commands directed to recording device 1. Microphone 18 outputs the sound related to the sound commands to sound command receiving unit 44. Microphone 18 can output the collected sound to image data acquisition unit 30, thereby recording control unit 36 ​​recording loop recording image data or event data including sound.

[0045] Accelerometer 20 is a sensor that detects the acceleration generated on the vehicle. Accelerometer 20 outputs the detection result to event detection unit 46 of control unit 26. Accelerometer 20 is, for example, a sensor that detects acceleration in three axes. The three axes refer to the vehicle's forward / backward, left / right, and up / down directions.

[0046] The operation unit 22 can receive various operations for the recording device 1. For example, the operation unit 22 can receive operations to manually save captured image data as event data to the recording unit 14. For example, the operation unit 22 can receive operations to reproduce loop-recorded image data or event data recorded in the recording unit 14. For example, the operation unit 22 can receive operations to delete event data recorded in the recording unit 14. For example, the operation unit 22 can receive operations to end loop recording. The operation unit 22 outputs operation information to the operation control unit 48 of the control unit 26.

[0047] The GNSS receiver 24 consists of a GNSS receiver and the like that receives GNSS signals from GNSS satellites. The GNSS receiver 24 outputs the received GNSS signals to the position information acquisition unit 50 of the control unit 26.

[0048] The control unit 26 controls various parts of the recording device 1. The control unit 26 may include, for example, an information processing device such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), and a storage device such as RAM (Random Access Memory) or ROM (Read Only Memory). The control unit 26 executes a program that controls the operation of the recording device 1 disclosed herein. The control unit 26 may also be implemented using an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or a FPGA (Field Programmable Gate Array). The control unit 26 may also be implemented using a combination of hardware and software.

[0049] The control unit 26 includes an image data acquisition unit 30, a buffer memory 32, an image data processing unit 34, a recording control unit 36, a playback control unit 38, a display control unit 40, a detection unit 42, a sound command receiving unit 44, an event detection unit 46, an operation control unit 48, and a position information acquisition unit 50 as functional blocks that constitute the control unit 26 or are implemented through the execution of a program.

[0050] The image data acquisition unit 30 acquires first image data of the surrounding area of ​​the vehicle and second image data of the interior of the vehicle. Specifically, the image data acquisition unit 30 acquires first image data captured by the first camera 10 and second image data captured by the second camera 12. The image data acquisition unit 30 outputs the acquired first and second image data to the buffer memory 32. The first and second image data acquired by the image data acquisition unit 30 are not limited to image data, but may also be image data containing both image and sound. The image data acquisition unit 30 can acquire image data obtained by capturing the entire sky or half of the sky as the first and second image data.

[0051] The buffer memory 32 is an internal memory provided by the recording device 1. It is a memory that updates and temporarily records a certain amount of image data acquired by the image data acquisition unit 30.

[0052] The image data processing unit 34 converts the image data temporarily stored in the buffer memory 32 into any file format, such as MP4, encoded using any codec, such as H.264 or MPEG-4 (Moving Picture Experts Group). The image data processing unit 34 generates image data as a file of a certain duration based on the image data temporarily stored in the buffer memory 32. Specifically, the image data processing unit 34 generates a file of 60 seconds of image data from the image data temporarily stored in the buffer memory 32 according to the recording order. The image data processing unit 34 outputs the generated image data to the recording control unit 36. The image data processing unit 34 outputs the generated image data to the display control unit 40. The duration of the image data generated as a file is set to 60 seconds as an example, but it is not limited to this.

[0053] The recording control unit 36 ​​controls the recording unit 14 to record the image data documented by the image data processing unit 34. During cyclic recording processing, such as when the vehicle's auxiliary power is turned on, the recording control unit 36 ​​records the image data documented by the image data processing unit 34 as overwriteable image data in the recording unit 14. During cyclic recording processing, the recording control unit 36 ​​continuously records the image data generated by the image data processing unit 34 to the recording unit 14. When the recording unit 14 becomes full, the oldest image data is overwritten with the newest image data for recording.

[0054] When the sound command receiving unit 44 receives an instruction to record an event based on a sound command, the recording control unit 36 ​​saves first image data containing the time point at which the instruction to record the event was received as event data. The recording control unit 36 ​​saves the event data as data that cannot be overwritten in the recording unit 14. For example, the recording control unit 36 ​​copies first image data from the buffer memory for a predetermined period of approximately 10 seconds before and after the time point at which the sound command receiving unit 44 receives the event detection based on a sound command, and saves it as event data.

[0055] When the event detection unit 46 detects an event based on the output value of the accelerometer 20, the recording control unit 36 ​​saves first image data containing the time point at which the event was detected as event data. The recording control unit 36 ​​saves the event data as data that cannot be overwritten in the recording unit 14. For example, the recording control unit 36 ​​copies first image data from the buffer memory for a predetermined period of about 10 seconds before and after the time point at which the event detection unit 46 detected the event as event data and saves it.

[0056] The playback control unit 38 performs the following control: based on the playback operation control signal output from the operation control unit 48, it reproduces the loop recording image data or event data recorded in the recording unit 14, and outputs the reproduced image, etc. to the display unit 16 through the display control unit 40.

[0057] The display control unit 40 controls the display of image data in the display unit 16. The display control unit 40 outputs an image signal that causes the image data to be output to the display unit 16. More specifically, the display control unit 40 outputs an image signal that is displayed by reproducing the image captured by the first camera 10 or the looped recorded image data or event data recorded in the recording unit 14.

[0058] The detection unit 42 detects conditions in the environment where a voice command is issued that prevent the voice command from being properly recognized. In this embodiment, the detection unit 42 detects the orientation of the face of the person issuing the voice command. The orientation of the face of the person issuing the voice command not towards the microphone that receives the sound of the voice command can be a condition that prevents the voice command from being properly recognized. Therefore, the detection unit 42 identifies the occupants of the vehicle from the second image data. In the first embodiment, the occupants include the driver and passengers other than the driver. The occupants may also be only the driver of the vehicle. The detection unit 42 identifies the person's face from the second image data and detects the orientation of the face. The detection unit 42 detects the person's face, for example, based on the positional relationships of the features constituting the face, or based on the positional relationships of the facial center line and the various elements constituting the face. These detection methods can use known methods and are not limited to any particular method.

[0059] The detection unit 42 detects the direction of the vehicle occupant's face based on the second image data, and determines whether the occupant is facing the direction from which the microphone 18 can appropriately collect the occupant's voice. For example, the detection unit 42 detects the direction of the vehicle occupant's face based on the second image data and determines whether the occupant is facing the vehicle's direction of travel or a direction other than the direction of travel. The vehicle's direction of travel, for example, refers to a direction within a range of approximately ±30 degrees when the angle of the occupant facing forward of the vehicle is set to 0 degrees.

[0060] In this embodiment, the detection unit 42 is described as determining whether the vehicle's occupant is facing the direction of travel or a direction other than the direction of travel, but this disclosure is not limited to this. The detection unit 42 may also determine, for example, whether the vehicle's occupant is facing the direction of the microphone 18 or a direction other than the microphone 18 based on the second image data.

[0061] The detection unit 42 detects, for example, whether or not an object is obstructing the mouth of a person issuing a voice command. The presence of an object obstructing the mouth of a person issuing a voice command can prevent the voice command from being properly recognized. Therefore, the detection unit 42 identifies the vehicle occupants from the second image data. In the first embodiment, occupants include the driver and passengers other than the driver. The occupant may also be only the driver of the vehicle. The detection unit 42 identifies the person's face from the second image data and detects whether or not an object is obstructing the person's mouth. Objects obstructing the mouth are not limited to the mouth itself, but also include objects obstructing the lower half of the person's face, etc. The detection unit 42 detects, for example, whether or not a mask or similar object is obstructing the person's mouth using object recognition processing with dictionary data. The method for detecting objects obstructing the person's mouth can use known methods and is not limited.

[0062] The detection unit 42 detects, for example, the volume of the background noise in the environment where the sound command is received. The background noise in the environment where the sound command is received is ambient noise inside and outside the vehicle, such as advertising sounds outside the vehicle, exhaust sounds or audio sounds from other vehicles, echoes in tunnels, or the audio sound of one's own vehicle. A background noise volume exceeding a predetermined value can cause the sound command to be improperly recognized. The predetermined value for the background noise volume in the environment where the sound command is received is, for example, 70 dB. The detection unit 42 detects the background noise from the sound collected by the microphone 18. The detection unit 42 detects the volume of the detected background noise. The detection unit 42 may also perform sound feature analysis processing on the sound collected by the microphone 18, detecting sounds other than the sound command extracted by the sound command receiving unit 44 as background noise. The method for detecting the background noise and its volume can use known methods and is not limited.

[0063] The detection unit 42 detects, for example, the volume of the emitted sound. A volume lower than a predetermined value can cause the sound command to fail to be properly recognized. The predetermined value for the volume of the emitted sound is, for example, 50 dB. The detection unit 42 detects the volume of the emitted sound from the emitted sound of the sound command collected by the microphone 18. The method for detecting the volume of the emitted sound can use known methods and is not limited.

[0064] The detection unit 42, for example, detects the volume difference between the background noise of the environment receiving the sound command and the volume of the sound command being emitted. A volume difference less than a predetermined value can cause the sound command to fail to be properly recognized. Conversely, a volume difference greater than or equal to a predetermined value, where the background noise is louder than the emitted sound, can also cause the sound command to fail to be properly recognized. In this case, the volume difference is, for example, around 15 dB to 20 dB. The method for detecting the volume difference between the background noise of the environment receiving the sound command and the volume of the sound command being emitted can be any known method and is not limited to this method.

[0065] The detection unit 42 detects conditions that prevent the sound command from being properly recognized in the environment where the sound command is issued. In this embodiment, the detection unit 42 detects the distance between the microphone 18 and the person issuing the sound command. A distance between the microphone 18 and the person issuing the sound command that is greater than a predetermined distance can be a condition that prevents the sound command from being properly recognized. The predetermined distance may be set to 1.0m, for example, but is not limited to this. The predetermined distance is detected, for example, based on the seating position in the vehicle. For example, if the person in the front seat makes a sound, the detection unit 42 detects that the distance between the microphone 18 and the person making the sound is less than the predetermined distance. For example, if the person in the rear seat makes a sound, the detection unit 42 detects that the distance between the microphone 18 and the person making the sound is less than the predetermined distance. Therefore, the detection unit 42 identifies the vehicle occupants from the second image data. In the first embodiment, the occupants include the driver and passengers other than the driver. The occupants may also be only the driver of the vehicle. The detection unit 42 identifies the person's face from the second image data. The method for detecting the distance between the microphone 18 and the person issuing the voice command can use known methods and is not limited.

[0066] The voice command receiving unit 44 receives voice commands by recognizing the sounds collected by the microphone 18. For example, the voice command receiving unit 44 performs sound source separation processing and sound recognition processing on the sounds collected by the microphone 18 to recognize a voice command for starting event recording. A voice command for starting event recording is, for example, "Start recording (ろくがかいし)". If the voice command receiving unit 44 recognizes six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" in the sounds collected by the microphone 18, it outputs a control signal for starting event recording processing to the recording control unit 36. Alternatively, if the voice command receiving unit 44 recognizes the sound of the word "RoKuGaKaIShi" in the sounds collected by the microphone 18, it outputs a control signal for starting event recording processing to the recording control unit 36. The voice command receiving unit 44 adjusts the sound recognition rate used to determine whether a voice command has been acquired based on whether the vehicle occupants are facing the direction of travel, i.e., whether they are facing the microphone 18 used to acquire the voice command.

[0067] When a voice command receiving unit 44 appropriately recognizes a voice command, such as when the vehicle occupant is facing the direction of travel, and all syllables in the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent, it determines that a voice command has been acquired. For example, the voice command receiving unit 44 sets a first threshold of 90% for determining that a voice command has been acquired. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 90% of the six syllables of "Ro·Ku·Ga·Ka·I·Shi".

[0068] When a voice command receiving unit 44 cannot properly recognize a voice command, such as when the vehicle occupant is facing a direction other than the vehicle's direction of travel, it determines that a voice command has been acquired if at least five of the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent. In this case, the voice command receiving unit 44 sets the recognition rate for determining that a voice command has been acquired to a second threshold lower than a first threshold. For example, the voice command receiving unit 44 sets the second threshold to 80%. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 80% of the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi". That is, even when a voice command cannot be properly recognized, such as when the vehicle occupant is facing a direction other than the vehicle's direction of travel, it determines that a voice command has been issued even if the occupant's voice cannot be fully recognized, thereby enabling proper recognition of voice commands.

[0069] Furthermore, when the vehicle occupant is facing the direction of travel, the voice command receiving unit 44 sets, for example, a first threshold of recognition rate (90%) to determine if a voice command has been acquired, based on the consistency between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if the consistency between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 90% or higher.

[0070] Furthermore, when the vehicle occupant is facing a direction other than the vehicle's direction of travel, the voice command receiving unit 44 sets the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform to, for example, 80%, as a second threshold lower than the first threshold for determining the recognition rate of a voice command. In this case, the voice command receiving unit 44 determines that a voice command has been acquired when the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 80% or higher. That is, when the vehicle occupant is facing a direction other than the vehicle's direction of travel, the occupant's voice is easily recognized as a voice command.

[0071] In addition, the voice command receiving unit 44 adjusts the voice recognition rate used to determine whether a voice command has been received based on whether the mouth of the vehicle occupant is obscured by an object.

[0072] When the voice command receiving unit 44 properly recognizes the voice command, such as when the mouth of the vehicle occupant is not obstructed by an object, it determines that a voice command has been acquired if all syllables in the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent. For example, the voice command receiving unit 44 sets a first threshold of 90% for determining that a voice command has been acquired. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 90% of the six syllables of "Ro·Ku·Ga·Ka·I·Shi".

[0073] When a voice command receiving unit 44 cannot properly recognize a voice command, such as when the mouth of a vehicle occupant is obscured by an object, it determines that a voice command has been acquired if five or more syllables out of six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent. In this case, the voice command receiving unit 44 sets the recognition rate for determining that a voice command has been acquired to a second threshold lower than a first threshold. For example, the voice command receiving unit 44 sets the second threshold to 80%. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 80% of the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi". That is, even when a voice command cannot be properly recognized, such as when the mouth of a vehicle occupant is obscured by an object, it determines that a voice command has been issued even if the occupant's voice cannot be fully recognized, thereby enabling proper recognition of the voice command.

[0074] Furthermore, when the mouth of the vehicle occupant is not obstructed by an object, the voice command receiving unit 44 sets, for example, a first threshold of recognition rate (90%) to determine whether a voice command has been acquired, based on the consistency between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform. In this case, the voice command receiving unit 44 determines that a voice command has been acquired when the consistency between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 90% or higher.

[0075] Furthermore, when the mouth of a vehicle occupant is obscured by an object, the voice command receiving unit 44 sets the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform to, for example, 80%, as a second threshold lower than the first threshold for determining the recognition rate of a voice command. In this case, the voice command receiving unit 44 determines that a voice command has been acquired when the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 80% or higher. That is, even when the mouth of a vehicle occupant is obscured by an object, the occupant's voice is easily recognized as a voice command.

[0076] In addition, the voice command receiving unit 44 changes the voice recognition rate used to determine whether the voice command has been acquired based on the volume of the background noise in the environment where the voice command is received and the volume of the voice command being spoken.

[0077] Furthermore, when the sound command receiving unit 44 appropriately recognizes the sound command, such as when the volume of the background noise is less than a predetermined value, and when all syllables in the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent, it determines that a sound command has been acquired. For example, the sound command receiving unit 44 sets a first threshold of 90% for the recognition rate of determining that a sound command has been acquired. In this case, the sound command receiving unit 44 determines that a sound command has been acquired if it can recognize more than 90% of the six syllables of "Ro·Ku·Ga·Ka·I·Shi". The sound command receiving unit 44 sets the recognition rate of determining that a sound command has been acquired to the first threshold when the volume of the sound command's utterance is above a predetermined value. The sound command receiving unit 44 sets the recognition rate of determining that a sound command has been acquired to the first threshold when the volume difference between the background noise of the environment receiving the sound command and the volume of the sound command's utterance is above a predetermined value, and the volume of the utterance is greater than the volume of the background noise. That is, when the volume of the voice signal is greater than the volume of the background noise by a predetermined value, the voice command receiving unit 44 determines that the voice command has been received and sets the recognition rate to a first threshold.

[0078] Furthermore, when a voice command receiving unit 44 cannot properly recognize a voice command, such as when the volume of the background noise is above a predetermined value, it determines that a voice command has been acquired if five or more syllables out of six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent. In this case, the voice command receiving unit 44 sets the recognition rate for determining that a voice command has been acquired to a second threshold lower than the first threshold. For example, the voice command receiving unit 44 sets the second threshold to 80%. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 80% of the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi". That is, even when a voice command cannot be properly recognized, such as when the volume of the background noise in the environment where the voice command is received is above a predetermined value, it determines that a voice command has been issued even if the passenger's voice cannot be fully recognized, thereby enabling proper recognition of the voice command. When the volume of the sound command being emitted is less than a predetermined value, the sound command receiving unit 44 determines that the sound command has been acquired and sets the recognition rate to a second threshold. When the volume difference between the background noise of the receiving environment and the volume of the sound command being emitted is greater than or equal to a predetermined value, and the volume of the background noise is greater than the volume of the emitted sound, the sound command receiving unit 44 determines that the sound command has been acquired and sets the recognition rate to the second threshold. In other words, when the volume of the background noise is greater than or equal to the volume of the emitted sound by a predetermined value, the sound command receiving unit 44 determines that the sound command has been acquired and sets the recognition rate to the second threshold.

[0079] Furthermore, when the volume of the background noise is less than a predetermined value, the voice command receiving unit 44 sets the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform to, for example, 90%, as a first threshold for determining that a voice command has been acquired. In this case, the voice command receiving unit 44 determines that a voice command has been acquired when the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 90% or higher. This also applies when the volume of the voice command is higher than a predetermined value, and when the difference between the volume of the background noise in the environment receiving the voice command and the volume of the voice command is higher than a predetermined value, and the volume of the voice command is greater than the volume of the background noise.

[0080] Furthermore, when the volume of the background noise is above a predetermined value, the voice command receiving unit 44 sets the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform to, for example, 80%, as a second threshold lower than the first threshold for determining the recognition rate of a voice command. In this case, the voice command receiving unit 44 determines that a voice command has been acquired when the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 80% or higher. That is, when the volume of the background noise in the environment where the voice command is received is above a predetermined value, the passenger's voice is easily recognized as a voice command. This is also true when the volume of the voice command is below a predetermined value, and when the difference between the volume of the background noise in the environment where the voice command is received and the volume of the voice command is above a predetermined value, and the volume of the background noise is greater than the volume of the voice command.

[0081] Furthermore, when the voice command receiving unit 44 appropriately recognizes the voice command, such as when the distance between the microphone 18 and the passenger of the vehicle issuing the voice command is less than a predetermined distance, it determines that a voice command has been acquired if all syllables in the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent. For example, the first threshold for the recognition rate of determining that a voice command has been acquired is set to 90%. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 90% of the six syllables of "Ro·Ku·Ga·Ka·I·Shi".

[0082] Furthermore, in situations where the voice command receiving unit 44 cannot properly recognize the voice command, such as when the distance between the microphone 18 and the passenger of the vehicle issuing the voice command is more than a predetermined distance, it determines that a voice command has been acquired if at least five of the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi" are consistent. In this case, the voice command receiving unit 44 sets the recognition rate for determining that a voice command has been acquired to a second threshold lower than the first threshold. For example, the voice command receiving unit 44 sets the second threshold to 80%. In this case, the voice command receiving unit 44 determines that a voice command has been acquired if it can recognize more than 80% of the six consecutive syllables of "Ro·Ku·Ga·Ka·I·Shi". That is, even in situations where the voice command cannot be properly recognized, such as when the distance between the microphone 18 and the passenger of the vehicle issuing the voice command is more than a predetermined distance, it determines that a voice command has been issued even if the passenger's voice cannot be fully recognized, thereby enabling proper recognition of the voice command.

[0083] In addition, the voice command receiving unit 44 adjusts the voice recognition rate used to determine whether the voice command has been acquired based on whether the distance between the microphone 18 and the passenger of the vehicle that issued the voice command is above a predetermined distance.

[0084] Furthermore, when the distance between the microphone 18 and the passenger in the vehicle issuing the voice command is less than a predetermined distance, the voice command receiving unit 44 sets, for example, a first threshold of 90% as the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform to determine that the voice command has been acquired. In this case, the voice command receiving unit 44 determines that the voice command has been acquired when the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 90% or higher.

[0085] Furthermore, when the distance between the microphone 18 and the passenger of the vehicle issuing the voice command is at or above a predetermined distance, the voice command receiving unit 44 sets the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform to, for example, 80%, as a second threshold lower than the first threshold for determining the recognition rate of a voice command. In this case, the voice command receiving unit 44 determines that a voice command has been acquired when the consistency rate between the acoustic model of the sound waveform representing the word "RoKuGaKaIShi" and the input sound waveform is 80% or higher. That is, when the distance between the microphone 18 and the passenger of the vehicle issuing the voice command is at or above a predetermined distance, the passenger's voice is easily recognized as a voice command.

[0086] The event detection unit 46 detects events based on the acceleration applied to the vehicle. The event detection unit 46 detects events based on the detection results of the acceleration sensor 20. The event detection unit 46 detects an event as having occurred if the acceleration information is above a preset threshold that would indicate a vehicle collision.

[0087] The operation control unit 48 acquires operation information received by the operation unit 22. For example, the operation control unit 48 acquires save operation information indicating a manual save operation of image data, playback operation information indicating a playback operation, or deletion operation information indicating a deletion operation of image data, and outputs a control signal. For example, the operation control unit 48 acquires end operation information indicating the end of loop recording and outputs a control signal.

[0088] The operation control unit 48 receives event recording operations based on the voice command identified and received by the voice command receiving unit 44.

[0089] The location information acquisition unit 50 acquires location information indicating the current location of the vehicle. The location information acquisition unit 50 calculates the current location information of the vehicle based on the GNSS signal received by the GNSS receiver 24 and using known methods.

[0090] (Processing by the Control Department)

[0091] use Figure 2 The processing flow of the control unit involved in the first embodiment will be explained. Figure 2 This is a flowchart illustrating the processing flow of the control unit involved in the first embodiment. Figure 2 The flowchart shown begins with the power of the engine or the like of the vehicle equipped with the recording device 1 being started.

[0092] With the start of processing, the control unit 26 begins normal recording and orientation detection (step S10). Specifically, the recording control unit 36 ​​sends image data captured by the first camera 10 and the second camera 12 to the buffer memory 32, for example, generating image files at predetermined intervals of 60 seconds, and recording them to the recording unit 14. The detection unit 42 begins detecting the orientation of the vehicle occupants' faces. Then, it proceeds to step S12.

[0093] The detection unit 42 determines whether the vehicle's occupants are facing a direction other than the vehicle's direction of travel (step S12). Specifically, the detection unit 42 determines whether the vehicle's occupants are facing a direction other than the direction of travel for a predetermined time or more. If the detection unit 42 determines that the vehicle's occupants are facing a direction other than the direction of travel for a predetermined time or more, the detection unit 42 determines that the vehicle's occupants are facing a direction other than the direction of travel. The predetermined time is, for example, 2 seconds or more, but is not limited to this. If it is determined that the occupants are facing a direction other than the vehicle's direction of travel (step S12; yes), proceed to step S14. If it is not determined that the occupants are facing a direction other than the vehicle's direction of travel (step S12; no), proceed to step S18.

[0094] If the determination in step S12 is "yes", the voice command receiving unit 44 determines whether a voice command has been obtained from the vehicle occupant via the microphone 18 (step S14). If it is determined that a voice command has been obtained (step S14; yes), proceed to step S16. If it is not determined that a voice command has been obtained (step S14; no), proceed to step S24.

[0095] If the determination in step S14 is "yes", the voice command receiving unit 44 determines whether the recognition rate of the acquired voice command is above the second threshold (step S16). If the recognition rate of the voice command is determined to be above the second threshold (step S16; yes), proceed to step S22. If the recognition rate of the voice command is not determined to be above the second threshold (step S16; no), proceed to step S24.

[0096] If the determination in step S12 is "No", the voice command receiving unit 44 determines whether a voice command has been obtained from the vehicle occupant via the microphone 18 (step S18). If it is determined that a voice command has been obtained (step S18; Yes), proceed to step S20. If it is not determined that a voice command has been obtained (step S18; No), proceed to step S24.

[0097] If the determination in step S18 is "yes", the voice command receiving unit 44 determines whether the recognition rate of the acquired voice command is above a first threshold (step S20). If the recognition rate of the voice command is determined to be above the first threshold (step S20; yes), proceed to step S22. If the recognition rate of the voice command is not determined to be above the second threshold (step S20; no), proceed to step S24.

[0098] In steps S14 and S18, in addition to determining whether a sound command has been received, it can also be determined whether the received sound command is an urgent or immediate sound command. In other words, in steps S14 and S18, it is determined whether an urgent or immediate sound command has been received. An urgent or immediate sound command refers to a sound command that requests operation for a function by receiving a sound command, that is, a function that requests to start operation without delay. For example, in recording device 1, an urgent or immediate sound command refers to a sound command that instructs event recording.

[0099] If the determination is "yes" in step S16 or step S20, the recording control unit 36 ​​saves the event data in the recording unit 14 (step S22). Specifically, the recording control unit 36 ​​saves the first image data before and after the time point when the sound command is acquired by the sound command receiving unit 44 as event data to the recording unit 14. Then, it proceeds to step S24.

[0100] If the determination in steps S14 to S20 is "No", or after step S22, the control unit 26 determines whether to end the process (step S24). Specifically, the control unit 26 determines to end the process when the operation unit 22 receives an operation to disconnect the power, indicating an end to the process, or when the power to the engine or other components of the vehicle equipped with the recording device 1 is disconnected. If the determination is to end the process (step S24; Yes), the process ends. Figure 2 If the process is not determined to be terminated (step S24; no), proceed to step S12.

[0101] As described above, in the first embodiment, the recognition rate used to identify sound as a voice command is changed to save event data when the vehicle occupant is facing the direction of travel and when the occupant is facing a direction other than the direction of travel. In the first embodiment, when the occupant is facing a direction other than the direction of travel, the recognition rate is reduced to perform the event data saving process. Therefore, in the first embodiment, even when the microphone 18 has difficulty collecting the occupant's voice because the occupant is facing a direction other than the direction of travel, it is still possible to appropriately save event data based on voice commands.

[0102] [Second Implementation]

[0103] The second embodiment will be described. The difference between the second embodiment and the first embodiment is that, when multiple passengers are in the vehicle, the recognition rate of the voice command is changed based on the direction in which the multiple passengers are facing.

[0104] (Recording device)

[0105] use Figure 3 An example of the configuration of the recording device according to the second embodiment will be described. Figure 3 This is a block diagram illustrating an example of the configuration of the recording device according to the second embodiment.

[0106] like Figure 3 As shown, the recording device 1A is similar to the control unit 26A in that it includes a proportional calculation unit 52. Figure 1 The recording device 1 shown is different.

[0107] When multiple passengers are riding in the vehicle, the detection unit 42A detects the direction each passenger is facing. The detection unit 42A detects whether each passenger is facing the direction of travel or a direction other than the direction of travel. If a predetermined proportion or more of the passengers are facing the same direction other than the direction of travel, the detection unit 42A determines that the passengers are facing a direction other than the direction of travel.

[0108] The proportion calculation unit 52 calculates the proportion of passengers facing a predetermined direction among multiple passengers. The proportion calculation unit 52 also calculates the proportion of passengers facing directions other than the travel direction among multiple passengers. The proportion calculation unit 52 determines whether the proportion of passengers facing directions other than the travel direction among multiple passengers is a predetermined proportion or higher. The predetermined proportion is, for example, 50% or higher. Specifically, the proportion calculation unit 52 determines that a predetermined proportion of passengers facing directions other than the travel direction is present when there are 2 passengers and 1 or more passengers facing the same direction other than the travel direction, when there are 3 passengers and 2 or more passengers facing the same direction other than the travel direction, or when there are 4 passengers and 2 or more passengers facing the same direction other than the travel direction. Furthermore, the predetermined proportion is not limited to 50% and can be other values.

[0109] (Processing by the Control Department)

[0110] use Figure 4 The processing flow of the control unit involved in the second embodiment will be explained. Figure 4 This is a flowchart illustrating the processing flow of the control unit involved in the second embodiment.

[0111] Control unit 26A begins normal recording and orientation detection (step S30). Normal recording processing and... Figure 2 The steps shown in step S10 are the same, so the description is omitted. The detection unit 42A detects the orientation of the faces of each of the multiple passengers in the vehicle. Then, it proceeds to step S22.

[0112] The detection unit 42A determines whether a predetermined proportion or more of the occupants are facing a direction other than the vehicle's direction of travel (step S32). Specifically, the proportion calculation unit 52 determines whether a predetermined proportion or more of the occupants are facing a direction other than the vehicle's direction of travel based on the detection results of the detection unit 42A. Furthermore, if a predetermined proportion or more of the occupants are facing the same direction other than the vehicle's direction of travel, the detection unit 42A determines that the occupants are facing a direction other than the vehicle's direction of travel. If it is determined that a predetermined proportion or more of the occupants are facing a direction other than the vehicle's direction of travel (step S32; yes), proceed to step S34. If it is not determined that a predetermined proportion or more of the occupants are facing a direction other than the vehicle's direction of travel (step S32; no), proceed to step S38.

[0113] The processing in steps S34 to S44 is respectively with Figure 2 The processes in steps S14 to S24 are the same, so the explanation is omitted.

[0114] As described above, the second embodiment adjusts the recognition rate for identifying sound as a voice command based on the proportion of passengers facing directions other than the direction of travel among the multiple passengers in the vehicle, and saves event data accordingly. In the second embodiment, when the proportion of passengers facing directions other than the direction of travel is a predetermined proportion or higher, the recognition rate is reduced and event data saving processing is performed. Therefore, in the second embodiment, even in situations where the microphone 18 has difficulty collecting passengers' voices because multiple passengers are facing directions other than the direction of travel, event data based on voice commands can be appropriately saved.

[0115] [Third Implementation Method]

[0116] The third embodiment will be described. The structure of the recording device involved in the third embodiment is similar to... Figure 1 The recording device 1 shown has the same structure, so the description is omitted.

[0117] (Processing by the Control Department)

[0118] use Figure 5 The processing flow of the control unit involved in the third embodiment will be explained. Figure 5 This is a flowchart illustrating the processing flow of the control unit involved in the third embodiment.

[0119] With the start of processing, the control unit 26 begins normal recording and detection (step S50). Specifically, the recording control unit 36 ​​sends the image data captured by the first camera 10 and the second camera 12 to the buffer memory 32, for example, generating image files at predetermined intervals of 60 seconds, and recording them to the recording unit 14. The detection unit 42 begins detecting objects obstructing the mouth of the vehicle occupants. Then, the process proceeds to step S52.

[0120] The detection unit 42 determines whether an object is obstructing the mouth of a vehicle occupant (step S52). Specifically, if the object obstructs more than a predetermined area of ​​the occupant's mouth, the detection unit 42 determines that an object is obstructing the occupant's mouth. If an object is determined to be obstructing the occupant's mouth (step S52; yes), the process proceeds to step S54. If no object is determined to be obstructing the occupant's mouth (step S52; no), the process proceeds to step S58.

[0121] The processing in steps S54 to S64 is respectively related to Figure 2 The processes in steps S14 to S24 are the same, so the explanation is omitted.

[0122] As described above, the third embodiment adjusts the recognition rate used to identify sounds as voice commands and saves event data when the passenger's mouth is obscured by an object and when the mouth is not obscured. In the third embodiment, when the passenger's mouth is obscured by an object, the recognition rate is reduced compared to when the mouth is not obscured, and event data saving processing is performed. Therefore, the third embodiment can appropriately save voice command-based event data even when the microphone 18 has difficulty collecting the passenger's voice because the passenger's mouth is obscured by an object.

[0123] [Fourth Implementation Method]

[0124] The fourth embodiment will be described. The structure of the recording device according to the fourth embodiment is similar to... Figure 1 The recording device 1 shown has the same structure, so the description is omitted.

[0125] (Processing by the Control Department)

[0126] use Figure 6 The processing flow of the control unit involved in the fourth embodiment will be explained. Figure 6 This is a flowchart illustrating the processing flow of the control unit involved in the fourth embodiment.

[0127] With the start of processing, the control unit 26 begins normal recording and volume detection (step S70). Specifically, the recording control unit 36 ​​sends the image data captured by the first camera 10 and the second camera 12 to the buffer memory 32, for example, generating image files at predetermined intervals of 60 seconds, and recording them to the recording unit 14. The detection unit 42 begins detecting the volume of the background noise. Then, step S72 is performed.

[0128] The detection unit 42 determines whether the volume of the background sound is above a predetermined value (step S72). If it determines that the volume of the background sound is above the predetermined value (step S72; Yes), proceed to step S74. If it does not determine that the volume of the background sound is above the predetermined value (step S72; No), proceed to step S78.

[0129] The processing in steps S74 to S84 is respectively related to Figure 2 The processes in steps S14 to S24 are the same, so the explanation is omitted.

[0130] As described above, the fourth embodiment changes the recognition rate used to identify the sound as a voice command and saves event data when the background noise volume is above a predetermined value and when it is below a predetermined value. In the fourth embodiment, when the background noise volume is above a predetermined value, the recognition rate is reduced compared to when the background noise volume is below a predetermined value, and event data saving processing is performed. Therefore, the fourth embodiment can appropriately save voice command-based event data even when the microphone 18 has difficulty collecting the passenger's voice because the background noise volume is above a predetermined value.

[0131] [Fifth Implementation]

[0132] The fifth embodiment will be described. The structure of the recording device according to the fifth embodiment is similar to... Figure 1 The recording device 1 shown has the same structure, so the description is omitted.

[0133] (Processing by the Control Department)

[0134] use Figure 7 The processing flow of the control unit involved in the fifth embodiment will be explained. Figure 7 This is a flowchart illustrating the processing flow of the control unit involved in the fifth embodiment.

[0135] With the start of processing, control unit 26 begins normal recording (step S90). Normal recording of processing and... Figure 6 The steps shown in step S70 are the same, so the explanation is omitted. Then, proceed to step S92.

[0136] Processing in step S92 and Figure 2The process of step S14 shown is the same, so the explanation is omitted.

[0137] If the determination in step S92 is "yes", the detection unit 42 determines whether the volume of the sound command is above a predetermined value (step S94). If the determination is that the volume of the sound command is not above the predetermined value (step S94; no), proceed to step S96. If the determination is that the volume of the sound command is above the predetermined value (step S94; yes), proceed to step S98.

[0138] Processing in step S96 and Figure 2 The process of step S16 is the same as shown, so the description is omitted. The processes of steps S98 to S102 are the same as... Figure 2 The processes in steps S20 to S24 are the same, so the explanation is omitted.

[0139] As described above, in the fifth embodiment, the recognition rate for identifying the sound as a voice command is changed when the volume of the voice command is above a predetermined value and when it is below a predetermined value, and event data is saved accordingly. In the fifth embodiment, when the volume of the voice command is below a predetermined value, the recognition rate is reduced and event data saving is performed compared to when the volume of the voice command is below a predetermined value. Therefore, even in situations where the microphone 18 has difficulty collecting the passenger's voice due to the volume of the voice command being below a predetermined value, the fifth embodiment can still appropriately save event data based on voice commands.

[0140] [Sixth Implementation Method]

[0141] The sixth embodiment will be described. The structure of the recording device according to the sixth embodiment is similar to... Figure 1 The recording device 1 shown has the same structure, so the description is omitted.

[0142] (Processing by the Control Department)

[0143] use Figure 8 The processing flow of the control unit involved in the sixth embodiment will be explained. Figure 8 This is a flowchart illustrating the processing flow of the control unit involved in the sixth embodiment.

[0144] The processing in steps S110 and S112 is respectively related to Figure 6 The processes in steps S70 and S72 shown are the same, so the explanation is omitted.

[0145] If the determination in step S112 is "yes", the detection unit 42 determines whether the volume of the emitted sound is greater than or equal to the volume of the background sound by a predetermined value (step S114). If the determination is not that the volume of the emitted sound is greater than or equal to the volume of the background sound by a predetermined value, that is, if the volume difference between the emitted sound and the background sound is less than a predetermined value, or if the volume difference is greater than or equal to a predetermined value and the volume of the background sound is greater (step S114; no), proceed to step S116. If the determination is that the volume difference between the emitted sound and the background sound is greater than or equal to a predetermined value (step S114; yes), proceed to step S118.

[0146] The processing of step S116 and Figure 2 The process of step S16 is the same as shown, so the description is omitted. The processes of steps S118 to S122 are the same as... Figure 2 The processes in steps S20 to S24 are the same, so the explanation is omitted.

[0147] As described above, in the sixth embodiment, when the volume difference between the emitted sound and the background sound is greater than a predetermined value, or when the volume difference between the emitted sound and the background sound is not greater than a predetermined value, the recognition rate used to identify the sound as a voice command is changed, and event data is saved. In the sixth embodiment, when the volume of the emitted sound is less than a predetermined value of the background sound volume, the recognition rate is reduced and event data saving processing is performed compared to when the volume of the emitted sound is greater than or equal to the predetermined value of the background sound volume. Therefore, even in situations where the microphone 18 has difficulty collecting the passenger's voice because the volume of the emitted sound is less than a predetermined value of the background sound volume, the sixth embodiment can still appropriately save event data based on voice commands.

[0148] [Seventh Implementation Method]

[0149] (Recording device)

[0150] use Figure 9 An example of the configuration of the recording device according to the seventh embodiment will be described. Figure 9 This is a block diagram illustrating a configuration example of the recording device according to the seventh embodiment.

[0151] like Figure 9 As shown, the recording device 1B and Figure 1 The difference in the recording device 1 shown is that the control unit 26B has a speaker detection unit 54.

[0152] The speaker detection unit 54 detects a person's face and lip movements of the lips within the detected face based on the second image data acquired by the image data acquisition unit 30. The method for detecting lip movements can be any known method and is not limited to this.

[0153] (Processing by the Control Department)

[0154] use Figure 10 The processing flow of the control unit involved in the seventh embodiment will be explained. Figure 10 This is a flowchart illustrating the processing flow of the control unit involved in the seventh embodiment.

[0155] The processing in steps S130 and S132 is respectively related to Figure 7 The processes in steps S90 to S92 are the same, so the explanation is omitted.

[0156] The detection unit 42 determines the speaker who issued the voice command (step S134). Specifically, the detection unit 42 determines that the person whose voice command received by the voice command receiving unit 44 matches the lip movements on the face detected by the speaker detection unit 54 is the speaker who issued the voice command. Then, it proceeds to step S136.

[0157] The detection unit 42 determines whether the distance from the microphone 18 to the speaker of the sound command is greater than or equal to a predetermined distance (step S136). If it is determined that the distance from the microphone 18 to the speaker of the sound command is greater than or equal to the predetermined distance (step S136; Yes), proceed to step S138. If it is not determined that the distance from the microphone 18 to the speaker of the sound command is greater than or equal to the predetermined distance (step S136; No), proceed to step S140.

[0158] Processing in step S138 and Figure 2 The process of step S16 is the same as shown, so the description is omitted. The processes of steps S140 to S144 are the same as... Figure 2 The processes in steps S20 to S24 are the same, so the explanation is omitted.

[0159] As described above, the seventh embodiment changes the recognition rate used to identify the sound as a sound command and saves event data when the distance from the microphone 18 to the speaker of the sound command is greater than or equal to a predetermined distance and when the distance is less than the predetermined distance. In the seventh embodiment, when the distance from the microphone 18 to the speaker of the sound command is greater than or equal to a predetermined distance, the recognition rate is reduced to perform event data saving processing compared to when the distance is less than the predetermined distance. Therefore, even when the distance from the microphone 18 to the speaker of the sound command is greater than or equal to a predetermined distance, the seventh embodiment can still appropriately save event data based on sound commands.

[0160] [Eighth Implementation Method]

[0161] The eighth embodiment will be described. The eighth embodiment can be applied to general devices that are operated using voice commands, such as smart speakers, TV receivers and other home appliances, smartphones, tablets, PCs and other information devices, navigation devices used in vehicles, infotainment systems, etc.

[0162] use Figure 11 An example of the configuration of the voice command receiving device according to the eighth embodiment will be described. Figure 11 This is a block diagram illustrating a configuration example of the voice command receiving device according to the eighth embodiment.

[0163] like Figure 11 As shown, the voice command receiving device 100 includes a voice command receiving unit 102, a detection unit 104, and an execution control unit 106. The voice command receiving device 100 may include, for example, an information processing device such as a CPU or MPU, and a storage device such as RAM or ROM. The voice command receiving device 100 executes the program disclosed herein. The voice command receiving device 100 may also be implemented using integrated circuits such as ASICs or FPGAs. The voice command receiving device 100 may also be implemented using a combination of hardware and software.

[0164] Microphone 110 collects the sound emitted by the speaker. Microphone 110 outputs the sound related to the collected sound to voice command receiver 100. Microphone 110 can be integrated with voice command receiver 100 or can be configured separately.

[0165] Camera 120 captures images of the speaker. Camera 120 captures at least the speaker's face. Camera 120 outputs image data related to the captured images to voice command receiving device 100. Camera 120 can be integrated with voice command receiving device 100 or can be separate from it.

[0166] The voice command receiving unit 102 receives voice commands. For example, the voice command receiving unit 102 receives voice commands by recognizing the sound collected by the microphone 110.

[0167] The detection unit 104 detects conditions in the environment in which the voice command is issued that cause the voice command to be unable to be properly recognized. In this embodiment, the detection unit 104 detects the orientation of the face of the person issuing the voice command. The detection unit 104 detects the orientation of the face of the person issuing the voice command, for example, based on image data captured by the camera 120.

[0168] The detection unit 104 detects conditions in the environment where a sound command is issued, causing the sound command to be unable to be properly recognized. In this embodiment, the detection unit 104 begins to detect objects that obstruct the mouth of the person issuing the sound command. The detection unit 104 begins to detect objects obstructing the mouth of the person issuing the sound command, for example, based on image data captured by the camera 120.

[0169] The detection unit 104 detects the volume of the background noise of the environment where the sound command was issued, the volume of the sound command being emitted, and the difference between the volume of the background noise of the environment where the sound command was issued and the volume of the sound command being emitted. For example, the detection unit 104 detects the volume of the background noise of the environment where the sound command was issued, the volume of the sound command being emitted, and the difference between the volume of the background noise of the environment where the sound command was issued and the volume of the sound command being emitted based on the sound collected by the microphone 110.

[0170] The detection unit 104 detects conditions in the environment where a sound command is issued that would prevent the sound command from being properly recognized. In this embodiment, the detection unit 104 detects the distance between the microphone 110 and the person issuing the sound command. The detection unit 104 determines the speaker of the sound command, for example, based on image data captured by the camera 120. The detection unit 104 detects the distance between the microphone 110 and the determined speaker of the sound command based on the image data captured by the camera 120.

[0171] When the voice command receiving unit 102 receives a voice command, the execution control unit 106 executes the function of the received voice command.

[0172] The voice command receiving unit 102 receives the voice command by adjusting the recognition rate based on whether the person's face is facing the microphone 110 from which the voice command is received, as detected by the detection unit 104. For example, if the voice command receiving unit 102 determines that the person's face is facing the microphone 110, it receives the voice command at a recognition rate of at least a first threshold. If the voice command receiving unit 102 determines that the person's face is facing a direction other than the microphone 110, it receives the voice command at a recognition rate of at least a second threshold, which is lower than the first threshold.

[0173] The voice command receiving unit 102 adjusts the voice command recognition rate based on whether or not an object obstructing a person's face or mouth is detected by the detection unit 104, and receives the voice command. For example, if it is determined that there is no object obstructing a person's face or mouth, the voice command receiving unit 102 receives the voice command at a recognition rate of at least a first threshold. For example, if it is determined that there is an object obstructing a person's face or mouth, the voice command receiving unit 102 receives the voice command at a second threshold or higher than the first threshold.

[0174] The sound command receiving unit 102 receives sound commands by adjusting the sound command recognition rate based on whether the volume of the background noise is above a predetermined value. For example, if the volume of the background noise is not determined to be above a predetermined value, the sound command receiving unit 102 receives the sound command at a recognition rate of at least a first threshold. If the volume of the background noise is determined to be above a predetermined value, the sound command receiving unit 102 receives the sound command at a recognition rate of at least a second threshold, which is lower than the first threshold.

[0175] The voice command receiving unit 102 receives voice commands by adjusting the recognition rate based on whether the volume of the voice command being emitted is above a predetermined value. For example, if the volume of a voice command not determined to be a voice command is above a predetermined value, the voice command receiving unit 102 receives the voice command at a recognition rate of at least a first threshold. If the volume of a voice command determined to be a voice command is below a predetermined value, the voice command receiving unit 102 receives the voice command at a recognition rate of at least a second threshold, which is lower than the first threshold.

[0176] The voice command receiving unit 102 receives a voice command by adjusting its recognition rate based on whether the volume of the voice command being emitted is greater than or equal to the volume of the background noise by a predetermined value. For example, if the volume of the voice command is determined to be greater than or equal to the volume of the background noise by a predetermined value, the voice command receiving unit 102 receives the voice command at a recognition rate of at least a first threshold. If the volume of the voice command is not determined to be greater than or equal to the volume of the background noise by a predetermined value, the voice command receiving unit 102 receives the voice command at a recognition rate of at least a second threshold, which is lower than the first threshold.

[0177] The voice command receiving unit 102 receives voice commands by adjusting the recognition rate of the voice command based on the distance between the microphone 110 and the speaker of the voice command. For example, if the distance between the microphone 110 and the speaker of the voice command is determined to be greater than or equal to a predetermined distance, the voice command receiving unit 102 receives the voice command at a recognition rate of greater than or equal to a first threshold. If the distance between the microphone 110 and the speaker of the voice command is determined to be less than or equal to a predetermined distance, the voice command receiving unit 102 receives the voice command at a second threshold or higher than the first threshold.

[0178] The voice command receiving unit 102 receives voice commands with a recognition rate of at least a second threshold for voice commands that are highly urgent or immediacy-sensitive. In the third embodiment, voice commands that are highly urgent or immediacy-sensitive refer to voice commands for functions such as emergency calls, emergency communications, recording start instructions for broadcast content, and stop instructions for functions with high ongoing risks, where there is no desire for delays from the start or end of the function's execution, or where delays would have adverse effects or risks.

[0179] (Processing of voice command receiving device)

[0180] use Figure 12 The processing flow of the voice command receiving device according to the eighth embodiment will be explained. Figure 12 This is a flowchart illustrating the processing flow of the voice command receiving device according to the eighth embodiment.

[0181] The detection unit 104 begins orientation detection (step S150). Specifically, the detection unit 104 begins detecting the orientation of the speaker's face. Then, it proceeds to step S152.

[0182] The detection unit 104 determines whether the speaker is facing the microphone 110 (step S152). Specifically, the detection unit 42 determines whether the speaker is facing the microphone 110 for a predetermined time or more. If the speaker is facing the microphone 110 for a predetermined time or more, the detection unit 42 determines that the speaker is facing the microphone 110. The predetermined time is, for example, 2 seconds or more, but is not limited to this. If the speaker is determined to be facing the microphone 110 (step S152; yes), proceed to step S154. If the speaker is not determined to be facing the microphone 110 (step S152; no), proceed to step S158.

[0183] If the determination in step S152 is "yes", the voice command receiving unit 102 determines whether a voice command has been obtained from the speaker through the microphone 110 (step S154). If it is determined that a voice command has been obtained (step S154; yes), proceed to step S156. If it is not determined that a voice command has been obtained (step S154; no), proceed to step S164.

[0184] If the determination in step S154 is "yes", the voice command receiving unit 102 determines whether the recognition rate of the acquired voice command is above a first threshold (step S156). If the recognition rate of the voice command is determined to be above the first threshold (step S156; yes), proceed to step S162. If the recognition rate of the voice command is not determined to be above the first threshold (step S156; no), proceed to step S164.

[0185] If the determination in step S152 is "No", the voice command receiving unit 102 determines whether a voice command has been obtained from the speaker through the microphone 110 (step S158). If it is determined that a voice command has been obtained (step S158; Yes), proceed to step S160. If it is not determined that a voice command has been obtained (step S158; No), proceed to step S164.

[0186] If the determination in step S158 is "yes", the voice command receiving unit 102 determines whether the recognition rate of the acquired voice command is above the second threshold (step S160). If the recognition rate of the voice command is determined to be above the second threshold (step S160; yes), proceed to step S162. If the recognition rate of the voice command is not determined to be above the second threshold (step S160; no), proceed to step S164.

[0187] In steps S154 and S158, in addition to determining whether a sound command has been obtained, it is also possible to determine whether the obtained sound command is an urgent or immediate sound command.

[0188] If the determination is "yes" in step S156 or "yes" in step S160, the control unit 106 executes the function of executing the voice command (step S162). Then, proceed to step S164.

[0189] If the determination is "No" in steps S154 to S160, or after step S162, the voice command receiving device 100 determines whether to end the process (step S164). Specifically, the voice command receiving device 100 determines to end the process when it receives an operation to disconnect the power or an operation indicating the end of the process. If the determination is to end the process (step S164; Yes), the process ends. Figure 12 If the process is not determined to be terminated (step S164; no), proceed to step S152.

[0190] As described above, the eighth embodiment changes the recognition rate used to identify sound as a sound command and executes the sound command function when the speaker is facing away from the microphone and when the speaker is facing away from the microphone. In the eighth embodiment, when the speaker is facing away from the microphone, the recognition rate is reduced to execute the sound command function compared to when the speaker is facing away from the microphone. Therefore, the eighth embodiment can appropriately execute the sound command function even when the microphone has difficulty collecting the speaker's sound because the speaker is facing away from the microphone.

[0191] [Ninth Implementation Method]

[0192] The ninth embodiment will be described. The structure of the voice command receiving device according to the ninth embodiment is different from that of the previous one. Figure 11 The structure of the sound command receiving device 100 shown is the same, so the description is omitted.

[0193] (Processing of voice command receiving device)

[0194] use Figure 13The processing flow of the voice command receiving device according to the ninth embodiment will be explained. Figure 13 This is a flowchart illustrating the processing flow of the voice command receiving device according to the ninth embodiment.

[0195] The detection unit 104 begins detection (step S170). Specifically, the detection unit 104 begins detecting objects that are obstructing the mouth of the speaker. Then, it proceeds to step S172.

[0196] The detection unit 104 determines whether an object is obstructing the speaker's face or mouth (step S172). Specifically, if, for example, an object obstructs more than a predetermined area of ​​the speaker's mouth, the detection unit 104 determines that an object is obstructing the speaker's mouth. If an object is determined to be obstructing the speaker's mouth (step S172; yes), the process proceeds to step S174. If no object is determined to be obstructing the speaker's mouth (step S172; no), the process proceeds to step S178.

[0197] The processing in steps S174 and S176 is respectively related to Figure 12 The processes of steps S158 and S160 are the same, therefore their descriptions are omitted. The processes of steps S178 and S180 are respectively the same as those of... Figure 12 The processes of steps S154 and S156 are the same, therefore their descriptions are omitted. The processes of steps S182 and S184 are respectively the same as... Figure 12 The processes in steps S162 and S164 shown are the same, so the explanation is omitted.

[0198] As described above, the ninth embodiment changes the recognition rate used to identify the sound as a voice command and executes the voice command function, depending on whether the speaker's mouth is obstructed by an object or not. In the ninth embodiment, when the speaker's mouth is obstructed by an object, the recognition rate is reduced to execute the voice command function compared to when the mouth is not obstructed. Therefore, the ninth embodiment can appropriately execute the voice command function even when the microphone has difficulty collecting the speaker's voice because the speaker's mouth is obstructed by an object.

[0199] [Tenth Implementation Method]

[0200] The tenth embodiment will be described. The structure of the voice command receiving device according to the tenth embodiment is similar to... Figure 11 The structure of the sound command receiving device 100 shown is the same, so the description is omitted.

[0201] (Processing of voice command receiving device)

[0202] use Figure 14The processing flow of the voice command receiving device according to the tenth embodiment will be explained. Figure 14 This is a flowchart illustrating the processing flow of the voice command receiving device according to the tenth embodiment.

[0203] The detection unit 104 begins volume detection (step S190). Specifically, the detection unit 104 begins detecting the volume of the background sound. Then, it proceeds to step S192.

[0204] The detection unit 104 determines whether the volume of the background sound is above a predetermined value (step S192). If the volume of the background sound is determined to be above the predetermined value (step S192; Yes), the process proceeds to step S194. If the volume of the background sound is not determined to be above the predetermined value (step S192; No), the process proceeds to step S198.

[0205] The processing in steps S194 and S196 is respectively related to Figure 12 The processes of steps S158 and S160 are the same, therefore their descriptions are omitted. The processes of steps S198 and S200 are respectively the same as... Figure 12 The processes of steps S154 and S156 shown are the same, therefore their descriptions are omitted. The processes of steps S202 and S204 are respectively the same as... Figure 12 The processes in steps S162 and S164 shown are the same, so the explanation is omitted.

[0206] As described above, the tenth embodiment changes the recognition rate for recognizing sound as a sound command and executes the sound command function when the background sound volume is above a predetermined value or below a predetermined value. In the tenth embodiment, when the background sound volume is above a predetermined value, the recognition rate is reduced to execute the sound command function compared to when the background sound volume is below a predetermined value. Therefore, the tenth embodiment can appropriately execute the sound command function even when the microphone has difficulty collecting the speaker's voice because the background sound volume is above a predetermined value.

[0207] [Eleventh Implementation Method]

[0208] The eleventh embodiment will be described. The structure of the voice command receiving device according to the eleventh embodiment is... Figure 11 The structure of the sound command receiving device 100 shown is the same, so the description is omitted.

[0209] (Processing of voice command receiving device)

[0210] use Figure 15 The processing flow of the voice command receiving device according to the eleventh embodiment will be explained. Figure 15 This is a flowchart illustrating the processing flow of the voice command receiving device according to the eleventh embodiment.

[0211] The processing of step S210 and Figure 12 The process of step S154 shown is the same, so the explanation is omitted.

[0212] If the determination in step S210 is "yes", the detection unit 104 determines whether the volume of the speaker's voice is above a predetermined value (step S212). If it is not determined that the volume of the speaker's voice is above the predetermined value (step S212: no), proceed to step S214. If it is determined that the volume of the speaker's voice is above the predetermined value (step S212: yes), proceed to step S216.

[0213] The processes in steps S214 and S216 are the same as those in steps S160 and S156, respectively, and therefore their descriptions are omitted. Since the processes in steps S218 and S220 are respectively the same as those in steps S160 and S156... Figure 12 The processes in steps S162 and S164 shown are the same, so the explanation is omitted.

[0214] As described above, the eleventh embodiment changes the recognition rate for recognizing the sound as a voice command and executes the voice command function when the volume of the emitted sound is above or below a predetermined value. In the eleventh embodiment, when the volume of the emitted sound is below the predetermined value, the recognition rate is reduced to execute the voice command function compared to when the volume of the emitted sound is above the predetermined value. Therefore, the eleventh embodiment can appropriately execute the voice command function even when the microphone has difficulty collecting the speaker's voice because the volume of the emitted sound is below the predetermined value.

[0215] [Twelfth Implementation Method]

[0216] The twelfth embodiment will be described. The structure of the voice command receiving device according to the twelfth embodiment is similar to... Figure 11 The structure of the sound command receiving device 100 shown is the same, so the description is omitted.

[0217] (Processing of voice command receiving device)

[0218] use Figure 16 The processing flow of the voice command receiving device according to the twelfth embodiment will be explained. Figure 16 This is a flowchart illustrating the processing flow of the voice command receiving device according to the twelfth embodiment.

[0219] Processing in step S230 and Figure 14 The process of step S190 is the same as shown, therefore the description is omitted. The process of step S232 is the same as... Figure 12 The process of step S154 shown is the same, so the explanation is omitted.

[0220] If the determination in step S232 is "yes", the detection unit 104 determines whether the volume difference between the speaker's voice and the background sound exceeds a predetermined value (step S234). If the determination is not that the volume difference between the speaker's voice and the background sound exceeds a predetermined value, that is, if the volume difference between the speaker's voice and the background sound is less than a predetermined value, or the volume difference between the background sound and the speaker's voice exceeds a predetermined value (step S234; no), proceed to step S236. If the determination is that the volume difference between the speaker's voice and the background sound exceeds a predetermined value (step S234; yes), proceed to step S238.

[0221] The processes in steps S236 and S238 are the same as those in steps S160 and S156, respectively, and therefore their descriptions are omitted. Since the processes in steps S240 and S242 are respectively the same as those in steps S160 and S156... Figure 12 The processes in steps S162 and S164 shown are the same, so the explanation is omitted.

[0222] As described above, the twelfth embodiment changes the recognition rate for recognizing the sound as a sound command and executes the sound command function when the volume difference between the volume of the spoken sound and the volume difference between the volume of the background sound and the volume difference between the volume of the spoken sound and the volume of the background sound is not greater than the predetermined value. In the twelfth embodiment, when the volume of the spoken sound is less than the predetermined value of the background sound volume, the recognition rate is reduced to execute the sound command function compared to when the volume of the spoken sound is greater than or equal to the predetermined value of the background sound volume. Therefore, the twelfth embodiment can appropriately execute the sound command function even when the microphone has difficulty collecting the speaker's voice because the volume of the spoken sound is less than the predetermined value of the background sound volume.

[0223] [Thirteenth Implementation Method]

[0224] The thirteenth embodiment will be described. The structure of the voice command receiving device according to the thirteenth embodiment is... Figure 11 The structure of the sound command receiving device 100 shown is the same, so the description is omitted.

[0225] (Processing of voice command receiving device)

[0226] use Figure 17 The processing flow of the voice command receiving device according to the thirteenth embodiment will be explained. Figure 17 This is a flowchart illustrating the processing flow of the voice command receiving device according to the thirteenth embodiment.

[0227] Processing in step S250 and Figure 12The process of step S154 shown is the same, so the explanation is omitted.

[0228] If the determination in step S250 is "yes", the detection unit 104 determines the speaker of the voice command (step S252). Then, it proceeds to step S254.

[0229] The detection unit 104 determines whether the distance from the microphone 110 to the speaker of the sound command is greater than or equal to a predetermined distance (step S254). If it is determined that the distance from the microphone 110 to the speaker of the sound command is greater than or equal to the predetermined distance (step S254; Yes), proceed to step S256. If it is not determined that the distance from the microphone 110 to the speaker of the sound command is greater than or equal to the predetermined distance (step S254; No), proceed to step S258.

[0230] The processes in steps S256 and S258 are the same as those in steps S160 and S156, respectively, and therefore their descriptions are omitted. Since the processes in steps S260 and S262 are respectively the same as those in steps S160 and S156... Figure 12 The processes in steps S162 and S164 shown are the same, so the explanation is omitted.

[0231] As described above, the thirteenth embodiment changes the recognition rate for identifying sound as a sound command and executes the sound command function when the distance from the microphone 110 to the speaker of the sound command is greater than or equal to a predetermined distance, and when the distance is less than the predetermined distance. In the thirteenth embodiment, when the distance from the microphone 110 to the speaker of the sound command is greater than or equal to a predetermined distance, the recognition rate is reduced to execute the sound command function compared to when the distance is less than the predetermined distance. Therefore, even in situations where the microphone 110 has difficulty collecting the speaker's sound due to the distance between the microphone 110 and the speaker being greater than the predetermined distance, the thirteenth embodiment can still appropriately execute the sound command function.

[0232] The embodiments of this disclosure have been described above, but this disclosure is not limited to these embodiments. Furthermore, the aforementioned constituent elements include elements readily conceived by those skilled in the art, substantially identical elements, and elements of equal scope. Moreover, the aforementioned constituent elements can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the constituent elements can be made without departing from the spirit of the aforementioned embodiments.

[0233] Industrial availability

[0234] The voice command receiving device, voice command receiving method, and computer program products disclosed herein can be applied to home devices such as smart speakers and TV receivers, information devices such as smartphones, tablet terminals, and PCs, navigation devices used in vehicles, and infotainment systems.

[0235] Explanation of reference numerals in the attached figures

[0236] 1. Recording devices 1A and 1B

[0237] 10 First Camera

[0238] 12 Second Camera

[0239] 14 Records Department

[0240] 16 Display Section

[0241] 18, 110 microphones

[0242] 20 accelerometers

[0243] 22 Operations Department

[0244] 24GNSS receiver

[0245] 26, 26A, 26B Control Unit (Recording Control Device)

[0246] 30 Image Data Acquisition Department

[0247] 32 Buffer Memory

[0248] 34 Image Data Processing Department

[0249] 36 Record Control Department

[0250] 38 Reproduction Control Unit

[0251] 40 Display Control Unit

[0252] 42, 42A, 104 Testing Department

[0253] 44 Voice Command Receiver

[0254] 46 Incident Detection Department

[0255] 48 Operation Control Department

[0256] 50 Location Information Acquisition Department

[0257] 52 Scale Calculation Department

[0258] 54 Voice Detection Department

[0259] 100 Voice Command Receiver

[0260] 102 Voice Command Receiver

[0261] 106 Execution Control Department

[0262] 120 camera

Claims

1. A voice command receiving device, used in a vehicle recording control device, comprising: The voice command receiving unit receives voice commands. The detection unit detects conditions that prevent the sound command from being properly recognized in the environment in which the sound command is issued, based on image data obtained by photographing the interior of the vehicle. as well as The execution control unit, when the voice command receiving unit receives a voice command, executes the function of the received voice command. When the detection unit determines that a condition is not a condition that would cause the voice command to be unable to be properly recognized, the voice command receiving unit receives the voice command with a recognition rate of at least a first threshold. When the detection unit determines that a condition is a condition that would cause the voice command to be unable to be properly recognized, the voice command receiving unit receives the voice command with a recognition rate of at least a second threshold that is less than the first threshold.

2. The voice command receiving device according to claim 1, wherein, The detection unit uses the image data to detect the facial orientation of the vehicle's occupant as a condition that could cause the voice command to be inappropriately recognized; the occupant is the person issuing the voice command. When the detection unit determines that the face of the vehicle occupant is facing the direction of the microphone that receives the sound command, the sound command receiving unit receives the sound command with a recognition rate of at least a first threshold. When the detection unit determines that the face of the vehicle occupant is facing a direction other than the direction of the microphone, the sound command receiving unit receives the sound command with a recognition rate of at least a second threshold that is less than the first threshold.

3. The voice command receiving device according to claim 1, wherein, The detection unit detects whether there is an object obstructing the mouth of a passenger in the vehicle, which would prevent the voice command from being properly recognized. The passenger in the vehicle is the person issuing the voice command. When the detection unit determines that there is no object obstructing the mouth of the vehicle occupant, the sound command receiving unit receives the sound command with a recognition rate of at least a first threshold. When the detection unit determines that there is an object obstructing the mouth of the vehicle occupant, the sound command receiving unit receives the sound command with a recognition rate of at least a second threshold that is less than the first threshold.

4. The voice command receiving device according to claim 1, wherein, The detection unit detects the distance between the vehicle occupant and the microphone that receives the sound of the voice command, as a condition that would cause the voice command to be improperly recognized, wherein the vehicle occupant is the person who issued the voice command. When the detection unit determines that the distance is less than a specified distance, the sound command receiving unit receives the sound command with a recognition rate of at least a first threshold. When the detection unit determines that the distance is at least a specified distance, the sound command receiving unit receives the sound command with a recognition rate of at least a second threshold that is less than the first threshold.

5. The voice command receiving device according to any one of claims 1 to 4, wherein, The voice command receiving unit receives voice commands that are urgent or immediacy-critical, in a manner where the recognition rate of the voice command obtained by the voice command receiving unit is less than or equal to a second threshold that is less than the first threshold.

6. The voice command receiving device according to any one of claims 1 to 4, wherein, The voice command receiving unit receives an event recording indication based on a voice command. When the voice command receiving unit receives an event recording instruction based on a voice command, the execution control unit saves the image data obtained by taking pictures of the vehicle's surroundings at the time the event recording instruction was received as event data.

7. A method for receiving voice commands, comprising the following steps performed by a voice command receiving device, wherein the voice command receiving device is a vehicle recording and control device used in a vehicle: The conditions that cause a voice command to be inappropriately recognized are detected based on image data obtained by photographing the interior of the vehicle. When it is determined that the condition is not a condition that would cause the voice command to be unable to be properly recognized, the voice command is received with a recognition rate of at least a first threshold. When it is determined that the condition is a condition that would cause the voice command to be unable to be properly recognized, the voice command is received with a recognition rate of at least a second threshold, where the second threshold is less than the first threshold. as well as When the voice command is received, the function of the received voice command is executed.

8. A computer program product for a vehicle recording control device used in a vehicle, comprising a computer program that causes a computer to perform the following steps: The conditions that cause a voice command to be inappropriately recognized are detected based on image data obtained by photographing the interior of the vehicle. When it is determined that the condition is not a condition that would cause the voice command to be unable to be properly recognized, the voice command is received with a recognition rate of at least a first threshold. When it is determined that the condition is a condition that would cause the voice command to be unable to be properly recognized, the voice command is received with a recognition rate of at least a second threshold, where the second threshold is less than the first threshold. as well as When the voice command is received, the function of the received voice command is executed.

Images