JP2023094516A - Voice command reception device, voice command reception method and program - Google Patents

Abstract

To appropriately perform an operation by voice command.SOLUTION: A voice command reception device includes: a voice command reception unit that accepts a voice command; a detection unit that detects a direction of a face of a person uttering the voice command; and an execution control unit that executes a function for the accepted voice command when the voice command reception unit accepts the voice command. If the detection unit determines that the direction of the person's face faces the direction of a microphone from which utterance sound of the voice command is acquired, the voice command reception unit accepts the voice command with a recognition rate of the voice command acquired by the voice command reception unit equal to or higher than a first threshold value, and if the detection unit determines that the direction of the person's face does not face the microphone, the voice command reception unit accepts the voice command with the recognition rate of the voice command acquired by the voice command reception unit equal to or higher than a second threshold value lower than the first threshold value.SELECTED DRAWING: Figure 5

Description

The present invention relates to a voice command receiving device, a voice command receiving method, and a program.

Devices that are operated by voice commands are diversifying. For example, some recording devices for vehicles, so-called drive recorders, perform event recording by voice commands in addition to impact detection by acceleration sensors (eg, Non-Patent Document 1). Event recording by voice commands enables safe event recording without the need to operate a touch panel or the like while driving, such as when recording an accident in which the driver is not a party to the accident. Patent Literature 1 discloses a drive recorder that records an event by issuing a voice instruction in response to event detection based on acceleration.

JP 2020-154904 A

DRV-MR760 [searched on December 20, 2021], Internet (URL: https://www.kenwood.com/jp/car/drive-recorders/products/drv-mr760/)

A voice command for instructing the drive recorder to record an event is set in advance so that a voice command such as "Rokugakushi" can be accepted, for example. A voice command is required to consist of a certain number of syllables in order to prevent erroneous detection by other voices. For example, "Rokuga Kaishi" consists of six syllables. Therefore, in order to accurately recognize the voice command, the speaker often speaks while facing the direction of the microphone for inputting the spoken voice of the voice command, such as the direction of the drive recorder. A typical drive recorder is installed in front of the vehicle when viewed from the passenger, who is the speaker, so voice commands input while facing the direction of travel, which is the front of the vehicle, are properly recognized. .

However, if a voice command is uttered in a situation where the voice command is not properly recognized, the recognition rate of the voice command becomes low, so there are cases where the instruction by the voice command cannot be accepted. In such a case, for example, a voice command for instructing an operation requiring urgency or immediacy, such as a voice command for event recording in a drive recorder, may cause a delay in operation due to rephrasing the voice command. end up A situation in which a voice command is not properly recognized can occur, for example, if the person speaking the voice command is not facing the microphone that captures the spoken voice of the voice command.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a voice command receiving device, a voice command receiving method, and a program capable of appropriately performing operations using voice commands.

A voice command reception device of the present invention comprises a voice command reception unit that receives a voice command, a detection unit that detects the face orientation of a person who utters the voice command, and when the voice command reception unit receives a voice command, and an execution control unit that executes a function corresponding to the received voice command, wherein the detection unit is configured such that the face of the person faces a microphone that acquires the spoken voice of the voice command. If it is determined that the voice command is received by the voice command receiving unit, the recognition rate of the voice command acquired by the voice command receiving unit is equal to or higher than the first threshold value, and the voice command is received, and the face direction of the person is determined to be in a direction other than the direction of the microphone. In this case, the voice command is accepted when the recognition rate of the voice command acquired by the voice command accepting unit is equal to or higher than the second threshold lower than the first threshold.

A method for accepting a voice command according to the present invention includes steps of detecting the orientation of the face of a person who utters a voice command, and determining that the orientation of the face of the person faces the direction of a microphone that acquires the spoken voice of the voice command. If the recognition rate of the acquired voice command is equal to or higher than the first threshold, the voice command is accepted, and if it is determined that the face of the person faces in a direction other than the direction of the microphone, the acquired voice command is recognized. A voice command receiving device executes a step of receiving a voice command at a rate equal to or higher than a second threshold lower than the first threshold, and a step of executing a function corresponding to the received voice command when the voice command is received. .

A program of the present invention detects the face orientation of a person who speaks a voice command;
When it is determined that the direction of the person's face is facing the direction of the microphone that acquires the uttered voice of the voice command, the voice command is accepted when the recognition rate of the acquired voice command is equal to or higher than a first threshold, and the person's face If it is determined that the face is directed in a direction other than the direction of the microphone, the step of accepting the voice command at a recognition rate of the acquired voice command equal to or higher than a second threshold lower than the first threshold; causing the computer to execute a function corresponding to the received voice command when the voice command is received.

ADVANTAGE OF THE INVENTION According to this invention, operation by a voice command can be performed appropriately.

FIG. 1 is a block diagram showing a configuration example of a printing apparatus according to the first embodiment. FIG. 2 is a flow chart showing the flow of processing by a control unit according to the first embodiment. FIG. 3 is a block diagram showing a configuration example of a printing apparatus according to the second embodiment. FIG. 4 is a flow chart showing the flow of processing by a control unit according to the second embodiment. FIG. 5 is a block diagram showing a configuration example of a voice command accepting device according to the third embodiment. FIG. 6 is a flow chart showing the flow of processing of the voice command accepting device according to the third embodiment.

DETAILED DESCRIPTION OF THE INVENTION Embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. In addition, the present invention is not limited by this embodiment, and in the following embodiments, the same parts are denoted by the same reference numerals, thereby omitting redundant explanations. Also, the voice command receiving device according to the present invention assumes various devices that operate using voice commands, and the following embodiments do not limit the applicable devices.

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

(recording device)
A configuration example of the recording apparatus according to the first embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration example of a printing apparatus according to the first embodiment.

The recording device 1 is a so-called drive recorder that records images based on events occurring in a vehicle. The recording device 1 may be a device mounted on a vehicle, or may be a portable device that can be used in the vehicle. The recording device 1 may be realized by including the function or configuration of a device pre-installed in the vehicle, a navigation device, or the like. The recording device 1 executes a process of changing the recognition rate of the received voice command according to whether or not the passengers including the driver of the vehicle are facing the traveling direction of the vehicle.

As shown in FIG. 1, 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 acceleration sensor 20, an operation unit 22, and a GNSS ( Global Navigation Satellite System) 24 and a control section (recording control device) 26 . The recording device 1 may be a device that integrally includes the first camera 10, the second camera 12, and the microphone 18, or the first camera 10, the second camera 12, and the microphone 18 are separate units. It may be a device configured with

The first camera 10 is a camera that photographs the surroundings of the vehicle. The first camera 10 is, for example, a camera unique to the recording device 1 or a plurality of cameras that capture images in the front and rear directions of the vehicle. In the first embodiment, the first camera 10 is composed of, for example, a plurality of cameras arranged facing forward and rearward of the vehicle, and photographs the surroundings centering on the front and rear of the vehicle. The first camera 10 may be, for example, a single camera capable of taking full-dome or half-dome shots. The first camera 10 outputs the captured first image data to the image data acquisition unit 30 of the control unit 26 . The first video data is, for example, a moving image composed of images of 30 frames per second.

The second camera 12 is a camera that captures the interior of the vehicle. The second camera 12 is arranged at a position capable of photographing at least the face of the passenger of the vehicle. The occupant of the vehicle may be only the driver of the vehicle, or may include other occupants in addition to the driver of the vehicle. The second camera 12 is arranged, for example, in the instrument panel of the vehicle, or inside or around the rearview mirror of the vehicle. The second camera 12 has a fixed or substantially fixed shooting range and shooting direction. The second camera 12 is composed of, for example, a visible light camera or a near-infrared camera. The second camera 12 may be composed of, 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 video data is, for example, a moving image composed of images of 30 frames per second. In addition, when it is not necessary to distinguish between the first video data and the second video data, they are referred to as video data.

The first camera 10 and the second camera 12 may be composed of, for example, a single camera capable of taking full-dome or half-dome shots. In this case, in the video data captured in full-dome or half-dome, the range in which the entire video data is shot, the area around the vehicle, or the area in front of the vehicle is taken as the first image data. . Further, in the image data obtained by photographing the full-dome or half-dome, the range in which the face of the passenger sitting on the seat of the vehicle can be photographed is referred to as the second image data. The entire image data obtained by capturing the full-dome or half-dome may be treated as the first image data and the second image data.

The recording unit 14 is used for temporary storage of data in the recording device 1 . The recording unit 14 is, for example, a RAM (Random Access Memory), a semiconductor memory device such as a 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 loop recording video data or event data based on the control signal output from the recording control unit 36 of the control unit 26 .

The display unit 16 is, for example, a display device unique to the recording device 1 or a display device shared with other systems including a navigation system. The display unit 16 may be formed integrally with the first camera 10 . The display unit 16 is 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 arranged on the dashboard, instrument panel, center console, etc. in front of the driver of the vehicle. The display unit 16 displays images based on the video signal 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 in the recording unit 14 .

A microphone 18 picks up the sound in the cabin of the vehicle. In the first embodiment, the microphone 18 is arranged at a position capable of acquiring voices spoken by passengers of the vehicle including the driver. The microphone 18 is arranged, for example, on a dashboard, an instrument panel, a center console, or the like. A microphone 18 picks up the voice related to the voice command to the recording device 1 . The microphone 18 outputs the voice related to the voice command to the voice command receiving section 44 . The recording control unit 36 may record loop-recorded video data or event data including audio by outputting the picked-up audio from the microphone 18 to the video data acquiring unit 30 .

The acceleration sensor 20 is a sensor that detects acceleration that occurs with respect to the vehicle. The acceleration sensor 20 outputs the detection result to the event detection section 46 of the control section 26 . The acceleration sensor 20 is, for example, a sensor that detects acceleration in three axial directions. The three axial directions are the longitudinal direction, the lateral direction, and the vertical direction of the vehicle.

The operation unit 22 can receive various operations for the recording apparatus 1 . For example, the operation unit 22 can accept an operation to manually store captured video data in the recording unit 14 as event data. For example, the operation unit 22 can accept an operation to reproduce loop-recorded video data or event data recorded in the recording unit 14 . For example, the operation unit 22 can accept an operation to erase event data recorded in the recording unit 14 . For example, the operation unit 22 can accept an operation to end loop recording. The operation unit 22 outputs operation information to the operation control unit 48 of the control unit 26 .

The GNSS receiver 24 is configured by a GNSS receiver or the like that receives GNSS signals from GNSS satellites. The GNSS reception unit 24 outputs the received GNSS signal to the position information acquisition unit 50 of the control unit 26 .

The control section 26 controls each section of the recording apparatus 1 . The control unit 26 has, 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 a RAM (Random Access Memory) or a ROM (Read Only Memory). The control section 26 executes a program for controlling the operation of the recording apparatus 1 according to the invention. The control unit 26 may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 26 may be realized by a combination of hardware and software.

The control unit 26 includes a video data acquisition unit 30, a buffer memory 32, a video data processing unit 34, a recording control unit 36, a reproduction control unit 38, a display control unit 40, a detection unit 42, and an audio command reception unit. A unit 44, an event detection unit 46, an operation control unit 48, and a position information acquisition unit 50 are provided as functional blocks realized by the configuration of the control unit 26 or execution of a program.

The image data acquisition unit 30 acquires first image data obtained by photographing the surroundings of the vehicle and second image data obtained by photographing the interior of the vehicle. Specifically, the video data acquisition unit 30 acquires the first video data captured by the first camera 10 and the second video data captured by the second camera 12 . The video data acquisition unit 30 outputs the acquired first video data and second video data to the buffer memory 32 . The first video data and the second video data acquired by the video data acquisition unit 30 are not limited to data of video only, and may be video data including video and audio. The image data acquisition unit 30 may acquire image data obtained by photographing the full-dome or half-dome as the first image data and the second image data.

The buffer memory 32 is an internal memory provided in the recording apparatus 1, and is a memory that temporarily records video data for a certain period of time acquired by the video data acquiring section 30 while updating the video data.

The video data processing unit 34 converts the video data temporarily stored in the buffer memory 32 into H.264, for example. 264, MPEG-4 (Moving Picture Experts Group), or any other codec, and converted into any file format, such as MP4 format. The video data processing unit 34 generates video data as a file for a certain time from the video data temporarily stored in the buffer memory 32 . As a specific example, the video data processing unit 34 generates a file of 60 seconds of video data temporarily stored in the buffer memory 32 in order of recording. The video data processing unit 34 outputs the generated video data to the recording control unit 36 . The video data processing unit 34 outputs the generated video data to the display control unit 40 . The period of video data generated as a file is set to 60 seconds as an example, but is not limited to this.

The recording control unit 36 controls the recording unit 14 to record the video data filed by the video data processing unit 34 . The recording control unit 36 converts the video data filed by the video data processing unit 34 to the recording unit 14 as overwritable video data during a period in which the loop recording process is executed, such as when the accessory power source of the vehicle is ON. to record. The recording control unit 36 continues to record the video data generated by the video data processing unit 34 in the recording unit 14 during the period in which the loop recording process is executed. overwrites new video data on the

When the voice command receiving unit 44 receives an instruction to record an event by a voice command, the recording control unit 36 saves the first video data including the point of time when the instruction to record the event is received as event data. The recording control unit 36 stores the event data in the recording unit 14 as overwrite-prohibited data. For example, the recording control unit 36 copies the first video data in a predetermined period of about 10 seconds before and after the time when the voice command receiving unit 44 receives the event detection by the voice command from the buffer memory 32, and saves it as event data. do.

When the event detection unit 46 detects the occurrence of an event based on the output value of the acceleration sensor 20, the recording control unit 36 saves the first video data including the point of time when the event was detected as event data. The recording control unit 36 stores the event data in the recording unit 14 as overwrite-prohibited data. For example, the recording control unit 36 copies the first video data for a predetermined period of about 10 seconds before and after the event detection unit 46 detects the event from the buffer memory 32 and saves it as event data.

The reproduction control unit 38 reproduces the loop-recorded video data or event data recorded in the recording unit 14 based on the reproduction operation control signal output from the operation control unit 48, and displays the reproduced video or the like on the display control unit 40. is controlled to output to the display unit 16.

The display control unit 40 controls display of video data on the display unit 16 . The display control unit 40 outputs a video signal that causes the display unit 16 to output video data. More specifically, the display control unit 40 outputs a video signal to be displayed by reproducing the video captured by the first camera 10 or the loop-recorded video data or event data recorded in the recording unit 14 .

The detection unit 42 detects a condition in which the voice command is not properly recognized in the environment where the voice command is uttered. In this embodiment, the detection unit 42 detects the orientation of the face of the person who speaks the voice command. If the direction of the face of the person who utters the voice command is not facing the direction of the microphone that acquires the uttered voice of the voice command, it can be a condition that the voice command is not properly recognized. Therefore, the detection unit 42 recognizes the passenger of the vehicle from the second image data. In the first embodiment, passengers include the driver and passengers other than the driver. A passenger may be only the driver of the vehicle. The detection unit 42 recognizes a person's face from the second video data and detects the orientation of the face. For example, the detection unit 42 detects a person's face based on the positional relationship of the feature parts that make up the person's face, and determines the orientation of the face based on the positional relationship between the facial center line and each element that makes up the face. To detect. Known methods can be used for these detection methods, and are not limited.

The detection unit 42 detects the orientation of the vehicle passenger's face from the second image data, and determines whether the vehicle passenger is facing in a direction in which the microphone 18 can appropriately pick up the voice of the vehicle passenger. to judge whether For example, the detection unit 42 detects the orientation of the face of the vehicle occupant from the second image data, and determines whether the vehicle occupant is facing the traveling direction of the vehicle or facing a direction other than the traveling direction. The traveling direction of the vehicle refers to a direction within a range of about ±30 degrees, for example, when the angle in which the passenger faces the front of the vehicle is 0 degrees.

In the present embodiment, the detection unit 42 will be described as determining whether the vehicle occupant is facing the traveling direction of the vehicle or facing a direction other than the traveling direction, but the present disclosure is not limited to this. For example, the detection unit 42 may determine from the second video data whether the vehicle occupant is facing the direction of the microphone 18 or facing away from the microphone 18 .

The voice command accepting unit 44 accepts voice commands by recognizing voices collected by the microphone 18 . The voice command reception unit 44 performs, for example, sound source separation processing and voice recognition processing on voice collected by the microphone 18, and recognizes a voice command for starting event recording. A voice command for starting event recording is, for example, "start recording". When the voice command receiving unit 44 recognizes six consecutive syllables of "Ro, Ku, Ga, Ka, I, and Shi" in the voice collected by the microphone 18, the voice command receiving unit 44 issues a control signal for starting the event recording process. Output to the recording control unit 36 . Alternatively, the voice command reception unit 44 outputs a control signal for starting the event recording process to the recording control unit 36 when the voice indicating the word “RoKuGaKaIShi” is recognized in the voice collected by the microphone 18 . The voice command reception unit 44 issues a voice command according to whether or not the vehicle occupant is facing the direction of travel, that is, whether or not the vehicle occupant is facing the direction of the microphone 18 for acquiring the uttered voice of the voice command. Change the speech recognition rate for determining whether or not it has been acquired.

The voice command reception unit 44, in a situation where the voice command can be properly recognized, such as when the passenger of the vehicle is facing the direction of travel of the vehicle, recognizes the sequence of "Ro, Ku, Ga, Ka, I, Shi". If all the syllables out of the 6 syllables obtained match, it is determined that the voice command has been acquired. The voice command reception unit 44 sets, for example, 90% as the first threshold of the recognition rate for determining whether the voice command has been acquired. In this case, if 90% or more of the six syllables of "Ro, Ku, Ga, Ka, I, and Shi" are recognized, the voice command reception unit 44 determines that the voice command has been acquired.

When the voice command is not properly recognized, such as when the occupant of the vehicle is facing in a direction other than the traveling direction of the vehicle, the voice command reception unit 44 outputs "Ro, Ku, Ga, Ka, I, Shi". If 5 or more of the 6 consecutive syllables match, it is determined that the voice command has been acquired. In this case, the voice command reception unit 44 sets the recognition rate for determining that the voice command has been acquired to a second threshold lower than the first threshold. The voice command reception unit 44 sets the second threshold to 80%, for example. In this case, the voice command reception unit 44 determines that the voice command has been acquired when 80% or more of the consecutive six syllables of "Ro, Ku, Ga, Ka, I, and Shi" can be recognized. In other words, in a situation where the voice command is not properly recognized, such as when the passenger of the vehicle is facing in a direction other than the traveling direction of the vehicle, even if the passenger's utterance cannot be completely recognized, it is assumed that the voice command was spoken. A voice command is appropriately recognized by judging.

In addition, when the passenger of the vehicle is facing the traveling direction of the vehicle, the voice command reception unit 44 determines the rate of matching between the acoustic model of the voice waveform representing the word "RoKuGaKaIShi" and the waveform of the input voice. is set to, for example, 90% as the first threshold of the recognition rate for determining that the voice command has been acquired. In this case, if the acoustic model of the voice waveform representing the word "RoKuGaKaIShi" matches the waveform of the input voice at a rate of 90% or higher, the voice command reception unit 44 determines that the voice command has been acquired. judge.

In addition, when the passenger of the vehicle is facing in a direction other than the traveling direction of the vehicle, the voice command reception unit 44 matches the acoustic model of the voice waveform representing the word "RoKuGaKaIShi" with the waveform of the input voice. The rate is set to 80%, for example, as a second threshold that is lower than the first threshold of the recognition rate for determining that voice commands have been acquired. In this case, if the acoustic model of the voice waveform representing the word "RoKuGaKaIShi" matches the waveform of the input voice at a rate of 80% or higher, the voice command reception unit 44 determines that the voice command has been acquired. judge. That is, when the passenger of the vehicle is facing in a direction other than the traveling direction of the vehicle, the passenger's voice is likely to be recognized as a voice command.

The event detector 46 detects an event based on acceleration applied to the vehicle. The event detection unit 46 detects events based on the detection result of the acceleration sensor 20 . The event detection unit 46 detects that an event has occurred when the acceleration information is greater than or equal to a preset threshold that corresponds to a vehicle collision.

The operation control unit 48 acquires operation information of operations accepted by the operation unit 22 . For example, the operation control unit 48 acquires storage operation information indicating a manual storage operation of video data, playback operation information indicating a playback operation, or erasing operation information indicating a video data erasing operation, and outputs a control signal. For example, the operation control unit 48 acquires end operation information indicating an operation for ending loop recording, and outputs a control signal.

The operation control unit 48 receives an event recording operation by a voice command recognized and received by the voice command receiving unit 44 .

The position information acquisition unit 50 acquires position information indicating the current position of the vehicle. The position information acquisition unit 50 calculates the position information of the current position of the vehicle by a known method based on the GNSS signals received by the GNSS reception unit 24 .

(Processing of control unit)
The processing flow of the control unit according to the first embodiment will be described with reference to FIG. FIG. 2 is a flow chart showing the flow of processing by a control unit according to the first embodiment. The flowchart shown in FIG. 2 is started when power such as an engine of a vehicle in which the recording apparatus 1 is mounted is started.

With the start of processing, the control unit 26 starts normal recording and orientation detection (step S10). Specifically, the recording control unit 36 transmits video data captured by the first camera 10 and the second camera 12 to the buffer memory 32, and saves a video file every video of a predetermined period, such as every 60 seconds. It is generated and recorded in the recording unit 14 . The detection unit 42 starts detecting the direction of the face of the passenger of the vehicle. Then, the process proceeds to step S12.

The detection unit 42 determines whether or not the occupant of the vehicle is facing in a direction other than the traveling direction of the vehicle (step S12). Specifically, the detection unit 42 determines whether or not the occupant of the vehicle faces a direction other than the traveling direction for a predetermined time or longer. The detection unit 42 determines that the vehicle occupant is facing the direction other than the direction of travel when the occupant of the vehicle faces the direction other than the direction of travel for a predetermined time or longer. The predetermined time is, for example, two seconds or more, but is not limited to this. If it is determined that the passenger is facing in a direction other than the traveling direction of the vehicle (step S12; Yes), the process proceeds to step S14. If it is determined that the occupant is not facing the traveling direction of the vehicle (step S12; No), the process proceeds to step S18.

When it is determined as Yes in step S12, the voice command reception unit 44 determines whether or not a voice command has been received from the passenger of the vehicle through the microphone 18 (step S14). If it is determined that the voice command has been acquired (step S14; Yes), the process proceeds to step S16. If it is not determined that the voice command has been acquired (step S14; No), the process proceeds to step S24.

When determined as Yes in step S14, the voice command reception unit 44 determines whether or not the recognition rate of the acquired voice command is equal to or higher than the second threshold (step S16). If it is determined that the voice command recognition rate is equal to or higher than the second threshold (step S16; Yes), the process proceeds to step S22. If it is not determined that the voice command recognition rate is equal to or higher than the second threshold (step S16; No), the process proceeds to step S24.

When determined as No in step S12, the voice command reception unit 44 determines whether or not a voice command has been received from the passenger of the vehicle through the microphone 18 (step S18). If it is determined that the voice command has been acquired (step S18; Yes), the process proceeds to step S20. If it is not determined that the voice command has been acquired (step S18; No), the process proceeds to step S24.

When determined as Yes in step S18, the voice command reception unit 44 determines whether or not the recognition rate of the acquired voice command is equal to or higher than the first threshold (step S20). If it is determined that the voice command recognition rate is equal to or higher than the first threshold (step S20; Yes), the process proceeds to step S22. If it is not determined that the voice command recognition rate is equal to or higher than the second threshold (step S20; No), the process proceeds to step S24.

In steps S14 and S18, in addition to determining whether or not a voice command has been acquired, it may be determined whether or not the acquired voice command is a highly urgent or immediacy voice command. In other words, in steps S14 and S18, it is determined whether or not a highly urgent or immediacy voice command has been acquired. A voice command with high urgency or immediacy is a voice command that requests an operation for a function that is required to start operation without delay when the voice command is accepted. For example, an urgent or immediacy voice command in the recording device 1 is a voice command instructing event recording.

If Yes in step S16 or Yes in step S20, the recording control unit 36 stores the event data in the recording unit 14 (step S22). Specifically, the recording control unit 36 stores the first video data before and after the voice command receiving unit 44 acquires the voice command in the recording unit 14 as event data. Then, the process proceeds to step S24.

When it is determined No in steps S14 to S20, or after step S22, the control unit 26 determines whether or not to end the process (step S24). Specifically, when the operation unit 22 receives an operation to turn off the power or an operation to end processing, the control unit 26 changes the power of the engine of the vehicle in which the recording device 1 is mounted. is turned off, it is determined that the process is finished. If it is determined to end the process (step S24; Yes), the process of FIG. 2 ends. If it is not determined to end the process (step S24; No), the process proceeds to step S12.

As described above, in the first embodiment, the recognition rate for recognizing a voice as a voice command is changed depending on whether the passenger of the vehicle is facing in the direction of travel or in the direction other than the direction of travel. , save the event data. In the first embodiment, when facing in a direction other than the direction of travel, the recognition rate is lowered compared to when facing in the direction of travel, and the event data storage process is executed. As a result, the first embodiment appropriately saves the event data by the voice command even in a situation where it is difficult for the microphone 18 to pick up the voice of the passenger because the passenger is facing in a direction other than the traveling direction. be able to.

[Second embodiment]
A second embodiment will be described. The second embodiment differs from the first embodiment in that when a vehicle is occupied by multiple passengers, the voice command recognition rate is changed based on the direction in which the multiple passengers are facing. .

(recording device)
A configuration example of the recording apparatus according to the second embodiment will be described with reference to FIG. FIG. 3 is a block diagram showing a configuration example of a printing apparatus according to the second embodiment.

As shown in FIG. 3, the recording apparatus 1A differs from the recording apparatus 1 shown in FIG. 1 in that the control section 26A includes a ratio calculation section 52.

The detection unit 42A detects the direction in which each of the multiple passengers is facing when multiple passengers are riding in the vehicle. The detection unit 42A detects whether each of the plurality of passengers is facing in the direction of travel or in the direction other than the direction of travel. The detection unit 42A determines that the occupants of the vehicle are facing in a direction other than the traveling direction of the vehicle when a predetermined ratio or more of the plurality of occupants are facing the same direction other than the traveling direction of the vehicle. .

The ratio calculation unit 52 calculates the ratio of passengers facing a predetermined direction among the plurality of passengers. The ratio calculation unit 52 calculates the ratio of passengers facing in a direction other than the direction of travel among the plurality of passengers. The ratio calculation unit 52 determines whether or not the ratio of passengers facing in a direction other than the traveling direction is equal to or greater than a predetermined ratio among the plurality of passengers. The predetermined percentage is, for example, 50% or more. Specifically, the ratio calculation unit 52 calculates that when there are two passengers, there are one or more passengers, when there are three passengers, there are two or more passengers, and when there are four passengers, there are two or more passengers. If they are facing the same direction other than the direction of travel, it is determined that a predetermined proportion or more of the passengers are facing the direction other than the direction of travel. Note that the predetermined ratio is not limited to 50%, and may be another value.

(Processing of control unit)
The processing flow of the control unit according to the second embodiment will be described with reference to FIG. FIG. 4 is a flow chart showing the flow of processing by a control unit according to the second embodiment.

The controller 26A starts normal recording and orientation detection (step S30). Since the processing of normal recording is the same as that of step S10 shown in FIG. 2, the description thereof is omitted. The detection unit 42A detects the face orientation of each of a plurality of passengers riding in the vehicle. Then, the process proceeds to step S22.

The detection unit 42A determines whether or not a predetermined percentage or more of the passengers are facing in a direction other than the traveling direction of the vehicle (step S32). Specifically, the ratio calculation unit 52 determines whether or not a predetermined ratio or more of the passengers are facing in a direction other than the traveling direction of the vehicle, based on the detection result of the detection unit 42A. Then, the detection unit 42A detects that the vehicle occupant is facing the direction other than the traveling direction of the vehicle when a predetermined ratio or more of the plurality of passengers are facing the same direction other than the traveling direction of the vehicle. to decide. If it is determined that a predetermined percentage or more of the passengers are facing in a direction other than the traveling direction of the vehicle (step S32; Yes), the process proceeds to step S34. If it is not determined that the predetermined percentage or more of the passengers are facing in a direction other than the traveling direction of the vehicle (step S32; No), the process proceeds to step S38.

The processing from step S34 to step S44 is the same as the processing from step S14 to step S24 shown in FIG. 2, respectively, so description thereof will be omitted.

As described above, the second embodiment increases the recognition rate for recognizing a voice as a voice command according to the ratio of passengers facing in a direction other than the direction of travel, among the plurality of passengers in the vehicle. Change and save the event data. In the second embodiment, when the percentage of passengers facing in a direction other than the traveling direction is equal to or greater than a predetermined percentage, the recognition rate is lowered and the event data storage process is executed. As a result, in the second embodiment, even in a situation where it is difficult for the microphone 18 to pick up the voices of the passengers because a plurality of passengers are facing in a direction other than the traveling direction, it is possible to appropriately save the event data using the voice commands. can be done.

[Third Embodiment]
A third embodiment will be described. The third embodiment is a general-purpose device that operates using voice commands. For example, it is used in home devices such as smart speakers and television receivers, information devices such as smartphones, tablet terminals, and PCs, and vehicles. It can be applied to navigation devices, infotainment systems, etc.

A configuration example of the voice command reception device according to the third embodiment will be described with reference to FIG. FIG. 5 is a block diagram showing a configuration example of a voice command accepting device according to the third embodiment.

As shown in FIG. 5, the voice command reception device 100 includes a voice command reception unit 102, a detection unit 104, and an execution control unit 106. The voice command reception device 100 has, for example, an information processing device such as a CPU or MPU, and a storage device such as a RAM or ROM. Voice command receiving device 100 executes a program according to the present invention. The voice command reception device 100 may be realized by an integrated circuit such as ASIC or FPGA, for example. Voice command accepting device 100 may be realized by a combination of hardware and software.

The microphone 110 picks up the voice uttered by the speaker. The microphone 110 outputs voice related to the collected voice to the voice command accepting device 100 . Microphone 110 may be configured integrally with voice command receiving device 100 or may be configured separately.

Camera 120 captures the speaker. Camera 120 captures at least the speaker's face. Camera 120 outputs video data relating to the captured video to voice command reception device 100 . The camera 120 may be configured integrally with the voice command receiving device 100, or may be configured separately.

The voice command accepting unit 102 accepts voice commands. The voice command receiving unit 102 receives voice commands by recognizing voices picked up by the microphone 110, for example.

The detection unit 104 detects a condition in which a voice command is not properly recognized in an environment where the voice command is uttered. In this embodiment, the detection unit 104 detects the orientation of the face of the person who speaks the voice command. The detection unit 104 detects the orientation of the face of the person who speaks the voice command based on the video data captured by the camera 120, for example.

When the voice command receiving unit 102 receives a voice command, the execution control unit 106 executes a function corresponding to the received voice command.

The voice command reception unit 102 changes the recognition rate of the voice command according to whether the detection unit 104 is pointing the face of the person in the direction of the microphone 110 that acquires the uttered voice of the voice command. accept. For example, when it is determined that the person's face is directed toward the microphone 110, the voice command reception unit 102 receives the voice command with a recognition rate equal to or higher than the first threshold. For example, when it is determined that the person's face is directed in a direction other than the microphone 110, the voice command reception unit 102 receives the voice command at a second threshold value lower than the first threshold value.

The voice command accepting unit 102 accepts voice commands with a recognition rate equal to or higher than the second threshold for voice commands with high urgency or immediacy. In the third embodiment, the voice command with high urgency or immediacy is an instruction to start or end the execution of a function, such as an emergency call, an emergency communication, an instruction to start recording broadcast content, or an instruction to stop a function with a high continuation risk. are voice commands for functions where delays from the point of operation are undesirable, or where delays adversely affect or risk.

(Processing of voice command receiving device)
The flow of processing of the voice command accepting device according to the third embodiment will be described with reference to FIG. FIG. 6 is a flow chart showing the flow of processing of the voice command accepting device according to the third embodiment.

The detection unit 104 starts orientation detection (step S50). Specifically, the detection unit 104 starts detecting the orientation of the speaker's face. Then, the process proceeds to step S52.

The detection unit 104 determines whether or not the speaker is facing the direction of the microphone 110 (step S52). Specifically, the detection unit 42 determines whether or not the speaker faces the microphone 110 for a predetermined time or longer. The detection unit 42 determines that the speaker is facing the microphone 110 when the speaker is facing the microphone 110 for a predetermined time or longer. The predetermined time is, for example, two seconds or more, but is not limited to this. If it is determined that the speaker is facing the direction of the microphone 110 (step S52; Yes), the process proceeds to step S54. If it is not determined that the speaker is facing the direction of the microphone 110 (step S52; No), the process proceeds to step S58.

If determined as Yes in step S52, the voice command reception unit 102 determines whether or not a voice command has been received from the speaker through the microphone 110 (step S54). If it is determined that the voice command has been acquired (step S54; Yes), the process proceeds to step S56. If it is not determined that the voice command has been acquired (step S54; No), the process proceeds to step S64.

If determined as Yes in step S54, the voice command reception unit 102 determines whether or not the recognition rate of the acquired voice command is equal to or higher than the first threshold (step S56). If it is determined that the voice command recognition rate is equal to or higher than the first threshold (step S56; Yes), the process proceeds to step S62. If it is not determined that the voice command recognition rate is equal to or higher than the first threshold (step S56; No), the process proceeds to step S64.

When determined as No in step S52, the voice command reception unit 102 determines whether or not a voice command has been received from the speaker through the microphone 110 (step S58). If it is determined that the voice command has been acquired (step S58; Yes), the process proceeds to step S60. If it is not determined that the voice command has been acquired (step S58; No), the process proceeds to step S64.

When determined as Yes in step S58, the voice command reception unit 102 determines whether or not the recognition rate of the acquired voice command is equal to or higher than the second threshold (step S60). If it is determined that the voice command recognition rate is equal to or higher than the second threshold (step S60; Yes), the process proceeds to step S62. If it is not determined that the voice command recognition rate is equal to or higher than the second threshold (step S60; No), the process proceeds to step S64.

In steps S54 and S58, in addition to determining whether or not a voice command has been acquired, it may be determined whether or not the acquired voice command is a highly urgent or immediacy voice command.

If Yes in step S56 or Yes in step S60, the execution control unit 106 executes the function corresponding to the voice command (step S62). Then, the process proceeds to step S64.

When it is determined No in steps S54 to S60, or after step S62, the voice command receiving device 100 determines whether or not to end the process (step S64). Specifically, the voice command receiving apparatus 100 determines to end the process when an operation to turn off the power or an operation to end the process is received. If it is determined to end the process (step S64; Yes), the process of FIG. 6 ends. If it is not determined to end the process (step S64; No), the process proceeds to step S52.

As described above, in the third embodiment, the recognition rate for recognizing a voice as a voice command is changed depending on whether the speaker is facing the microphone or when the speaker is facing something other than the microphone. perform a function. In the third embodiment, when facing in a direction other than the microphone, the recognition rate is lowered compared to when facing in the direction of the microphone, and the function for the voice command is executed. As a result, in the third embodiment, since the speaker is facing something other than the microphone, even in a situation where it is difficult for the microphone to pick up the speaker's voice, it is possible to appropriately execute the function corresponding to the voice command.

Although the embodiments of the present invention have been described above, the present invention is not limited by the contents of these embodiments. In addition, the components described above include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those within the so-called equivalent range. Furthermore, the components described above can be combined as appropriate. Furthermore, various omissions, replacements, or modifications of components can be made without departing from the gist of the above-described embodiments.

Reference Signs List 1, 1A recording device 10 first camera 12 second camera 14 recording unit 16 display unit 18, 110 microphone 20 acceleration sensor 22 operation unit 24 GNSS receiving unit 26, 26A control unit (recording control device)
30 video data acquisition unit 32 buffer memory 34 video data processing unit 36 recording control unit 38 playback control unit 40 display control unit 42, 42A, 104 detection unit 44 voice command reception unit 46 event detection unit 48 operation control unit 50 position information acquisition unit 52 ratio calculator 100 voice command reception device 102 voice command reception unit 106 execution control unit 120 camera

Claims (7)

a voice command reception unit that receives a voice command;
a detection unit that detects the orientation of the face of the person who utters the voice command;
an execution control unit that executes a function corresponding to the received voice command when the voice command receiving unit receives the voice command;
with
The voice command reception unit, when the detection unit determines that the direction of the face of the person faces the direction of the microphone for acquiring the uttered voice of the voice command, the voice command received by the voice command reception unit When the voice command is received with the recognition rate of above the first threshold and it is determined that the person's face is facing in a direction other than the direction of the microphone, the recognition rate of the voice command acquired by the voice command receiving unit is , accepting voice commands at or above a second threshold lower than the first threshold;
Voice command reception device. The voice command reception unit accepts a voice command with a recognition rate of the voice command acquired by the voice command reception unit equal to or higher than a second threshold lower than the first threshold, with respect to voice commands with high urgency or immediacy. ,
The voice command accepting device according to claim 1. The voice command reception device is a vehicle recording control device used in a vehicle,
a video data acquisition unit that acquires first video data captured by a first capturing unit that captures the surroundings of the vehicle and second video data captured by a second capturing unit that captures the interior of the vehicle,
The voice command reception unit receives an event recording instruction by a voice command,
The detection unit detects the orientation of the face of the passenger of the vehicle from the second image data,
When the voice command reception unit receives an event recording instruction by a voice command, the execution control unit saves the first video data including the time point when the event recording instruction is received as event data.
The voice command accepting device according to claim 1. The detection unit determines that the occupant of the vehicle is facing in a direction other than the direction of the microphone when the occupant of the vehicle is facing a direction other than the traveling direction of the vehicle for a predetermined time or longer.
4. The voice command accepting device according to claim 3. The detection unit detects face orientations of a plurality of passengers of the vehicle from the second image data, and detects a direction of faces of a plurality of passengers of the vehicle, and a predetermined ratio or more of the passengers face the same direction other than the traveling direction of the vehicle. , determining that the occupant of the vehicle is facing in a direction other than the direction of travel of the vehicle,
5. The voice command accepting device according to claim 3 or 4. detecting the face orientation of the person speaking the voice command;
When it is determined that the direction of the person's face is facing the direction of the microphone that acquires the uttered voice of the voice command, the voice command is accepted when the recognition rate of the acquired voice command is equal to or higher than a first threshold, and the person's face If it is determined that the face is oriented in a direction other than the direction of the microphone, the recognition rate of the acquired voice command is a second threshold value lower than the first threshold value or higher.
a step of executing a function corresponding to the received voice command when the voice command is received;
is executed by the voice command receiving device. detecting the face orientation of the person speaking the voice command;
When it is determined that the direction of the person's face is facing the direction of the microphone that acquires the uttered voice of the voice command, the voice command is accepted when the recognition rate of the acquired voice command is equal to or higher than a first threshold, and the person's face If it is determined that the face is oriented in a direction other than the direction of the microphone, the recognition rate of the acquired voice command is a second threshold value lower than the first threshold value or higher.
a step of executing a function corresponding to the received voice command when the voice command is received;
A program that causes a computer to run

Images