Voice-operated control device and voice-operated method

Abstract

To properly record a video or a still image with voice commands.SOLUTION: A control device 100 comprises: a voice command determination unit 116 for recognizing a user's utterance to determine whether the recognized utterance is a voice command; a voice command reception unit 117 for receiving the received voice command when the voice command determination unit 116 determines that the voice command is uttered; and a recording control unit 122 for performing the operation based upon the voice command that the voice command reception unit 117 receives. The voice command determination unit 116 determines that the recognized utterance is the voice command when the recognition result of the received utterance indicates that the utterance matching the previously set voice command by a first threshold or more is detected, and also determines that the recognized utterance is the voice command when the recognized result of the received utterance indicates that the utterance equal to or larger than a second threshold indicative of a lower degree of matching than the first threshold and less than the first threshold is detected a plurality of times within a predetermined period.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a voice-operated control device and a voice-operated method. [Background technology]

[0002] Various devices, such as smartphone apps and video cameras, support operation via voice commands. These devices can be operated without physical manipulation and can also be remotely controlled over short distances. Patent Document 1 discloses an imaging device that can be operated via voice commands. Some vehicle recording devices, known as drive recorders, record events via voice commands in addition to detecting impacts using acceleration sensors. Recording instructions via voice commands can safely record event data and still images without requiring touch panel or other operations while driving. Patent Document 2 discloses the saving of still images in addition to event recording. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-205637 [Patent Document 2] Japanese Patent Publication No. 2020-154904 Summary of the Invention [Problem to be solved by the invention]

[0004] For example, when using a video camera such as a smartphone or an action camera to control the recording of video or still images using voice commands, it is often difficult for the user to perform physical operations, such as while riding a bicycle or snowboarding. In such situations, the user may not be able to accurately utter the voice command, or even if the voice command is uttered accurately, the voice command may not be properly recognized due to the influence of surrounding sounds. In such cases, the timing of recording the video or still image may be delayed.

[0005] Furthermore, with a drive recorder, when a driver wants to capture an interesting facility or scenery or record an event while driving, the driver of the vehicle may use a voice command to instruct the recording of video or still images. However, the voice commands used to record video or still images vary depending on the model, redundancy is required to prevent malfunctions, and the voice commands are used infrequently. Therefore, when recording video or still images using a voice command, the driver may not be able to immediately utter the correct voice command, which may result in a delay in the timing of recording the video or still image.

[0006] The present disclosure has been made in view of the above, and aims to appropriately record video or still images in response to a voice command. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the objectives, the voice operation control device of the present disclosure includes a voice command determination unit that recognizes utterances by a user and determines whether the recognized utterance is a voice command; a voice command reception unit that receives the received voice command when the voice command determination unit determines that a voice command has been uttered; and an operation control unit that performs an operation based on the voice command received by the voice command reception unit, wherein the voice command determination unit determines that the recognized utterance is a voice command when the recognition result of the received utterance indicates that an utterance that matches a predetermined voice command to a degree equal to or greater than a first threshold has been detected, and determines that the recognized utterance is a voice command when the recognition result of the received utterance indicates that an utterance that matches a second threshold or greater, which indicates a degree of match lower than the first threshold, and is less than the first threshold has been detected multiple times within a predetermined period.

[0008] The voice operation method of the present disclosure includes a voice command determination step of recognizing a user's utterance, and determining that the recognized utterance is a voice command if the recognition result of the received utterance indicates that an utterance that matches a predetermined voice command to a degree equal to or greater than a first threshold has been detected, and determining that the recognized utterance is a voice command if the recognition result of the received utterance indicates that an utterance that is equal to or greater than a second threshold indicating a degree of match lower than the first threshold and less than the first threshold has been detected multiple times within a predetermined period; a voice command reception step of accepting the received voice command if it is determined in the voice command determination step that a voice command has been uttered; and an operation control step of performing an operation based on the voice command received in the voice command reception step. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to provide an effect that video or still images can be appropriately recorded in response to a voice command. [Brief explanation of the drawings]

[0010] [Figure 1]FIG. 1 is a block diagram showing an example of the configuration of a vehicle recording device having a control device according to the first embodiment. [Figure 2] FIG. 2 is a diagram showing an example of a recording period of event data. [Figure 3] FIG. 3 is a flowchart showing an example of a processing flow in the control device according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the recording time of a still image. [Figure 5] FIG. 5 is a flowchart showing an example of a processing flow in the control device according to the second embodiment. [Figure 6] FIG. 6 is a block diagram showing an example of the configuration of a video recording device having a control device according to the third embodiment. [Figure 7] FIG. 7 is a diagram showing an example of the start time of video capture. [Figure 8] FIG. 8 is a flowchart showing an example of the flow of processing in the control device according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A voice-operated control device and a voice-operated method according to embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. However, the present invention is not limited to the following embodiments.

[0012] [First embodiment] <Vehicle Recording Device> FIG. 1 is a block diagram showing an example of the configuration of a vehicle recording device (voice-operated device) 10 having a voice-operated control device (hereinafter referred to as the "control device") 100 according to a first embodiment. The vehicle recording device 10, which is an example of a voice-operated device, is a so-called drive recorder that records video and the like based on events that occur in the vehicle. For example, even if an accurate voice command cannot be uttered immediately, if utterances with a low degree of match are detected multiple times, the vehicle recording device 10 determines that the command is a voice command and records event data.

[0013] The vehicular recording device 10 is used in a vehicle. The vehicular recording device 10 may be a device installed in the vehicle, or may be a portable device that can be used in the vehicle. The vehicular recording device 10 may also be realized by including the functions or configuration of a device pre-installed in the vehicle or a navigation device. The vehicular recording device 10 includes a camera 211, a microphone 212, a recording unit 213, an operation unit 214, an acceleration sensor 215, a GNSS (Global Navigation Satellite System) receiving unit 216, a display unit 217, and a control device 100. The vehicular recording device 10 may be a device that integrally includes the camera 211 and the microphone 212, or may be a device in which the camera 211 and the microphone 212 are configured separately.

[0014] The camera 211 captures images of the periphery of the vehicle. The camera 211 may be a group of multiple cameras. The camera 211 is arranged, for example, at a position in the front of the vehicle interior where it can capture images of the area in front of the vehicle. In this embodiment, the camera 211 constantly captures images while the accessory power of the vehicle is ON. The camera 211 outputs the captured image data to the image data acquisition unit 111 of the control device 100. The image data is, for example, a moving image composed of images at 27.5 frames per second.

[0015] The microphone 212 is a microphone that picks up voice commands indicating various operations for the vehicular recording device 10. The microphone 212 may also be used as a microphone that inputs voice in addition to video from the camera 211 to the image data acquisition unit 111. For example, the microphone 212 can accept an operation to store captured image data as event data in the recording unit 213. The microphone 212 outputs the picked-up voice data to the voice command determination unit 116 of the control device 100.

[0016] The recording unit 213 is used for temporary storage of data in the vehicle recording device 10. The recording unit 213 is, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a recording medium such as a memory card. The recording unit 213 may be an external recording unit that is wirelessly connected via a communication device (not shown). The recording unit 213 records loop-recorded video data or event data based on a control signal output from the recording control unit 122 of the control device 100.

[0017] The operation unit 214 can accept various operations for the vehicular recording device 10. The operation unit 214 is, for example, a touch panel superimposed on the display screen of the display unit 217. For example, the operation unit 214 can accept an operation to manually save captured image data as event data in the recording unit 213. For example, the operation unit 214 can accept an operation to play back loop recorded video data or event data recorded in the recording unit 213. For example, the operation unit 214 can accept an operation to erase event data recorded in the recording unit 213. For example, the operation unit 214 can accept an operation to end loop recording. The operation unit 214 outputs operation information to the operation control unit 118 of the control device 100.

[0018] The acceleration sensor 215 is a sensor that detects acceleration occurring with respect to the vehicle. The acceleration sensor 215 outputs the detection result to the event detection unit 114 of the control device 100. The acceleration sensor 215 is a sensor that detects acceleration in, for example, three axial directions. The three axial directions are the front-rear direction, the left-right direction, and the up-down direction of the vehicle.

[0019] The GNSS receiving unit 216 is configured with a GNSS receiver that receives GNSS signals from GNSS satellites, etc. The GNSS receiving unit 216 outputs the received position information signal to the position information acquisition unit 115 of the control device 100.

[0020] The display unit 217 is, for example, a display device specific to the vehicular recording device 10, or a display device shared with other systems including a navigation system. The display unit 217 may be formed integrally with the camera 211. The display unit 217 is, for example, a display including a liquid crystal display or an organic EL (Electro-Luminescence) display. In this embodiment, the display unit 217 is disposed in front of the driver of the vehicle on a dashboard, an instrument panel, a center console, or the like. The display unit 217 displays an image based on a video signal output from the display control unit 119 of the control device 100. The display unit 217 displays an image captured by the camera 211 or an image recorded in the recording unit 213.

[0021] <Voice-operated control device> The control device 100 controls each part of the vehicle recording device 10. The control device 100 is an arithmetic processing device (control device) configured with, for example, a CPU (Central Processing Unit) and an MPU (Micro Processing Unit), and has a storage device such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The control device 100 loads a stored program into the memory and executes instructions included in the program. The control device 100 includes an internal memory such as the RAM described above, which is used for temporary storage of data in the control device 100. The control device 100 includes, as components such as functional blocks realized by executing the program, an image capture data acquisition unit 111, a buffer memory 112, an image capture data processing unit 113, an event detection unit 114, a position information acquisition unit 115, a voice command determination unit 116, a voice command reception unit 117, an operation control unit 118, a display control unit 119, a playback control unit 121, and an operation control unit (recording control unit) 122.

[0022] The image data acquisition unit 111 acquires image data of the surroundings captured by the camera 211 that captures the surroundings of the vehicle. The image data acquisition unit 111 outputs the acquired image data to the buffer memory 112.

[0023] The buffer memory 112 is an internal memory such as a RAM provided in the control device 100, and is a memory that temporarily records the photographic data for a certain period of time acquired by the photographic data acquisition unit 111 while updating it.

[0024] The image capture data processing unit 113 converts the image capture data temporarily stored in the buffer memory 112 into an arbitrary file format, such as MP4 format, encoded using an arbitrary codec, such as H.264 or MPEG-4 (Moving Picture Experts Group). The image capture data processing unit 113 generates image capture data as files for a certain period of time from the image capture data temporarily stored in the buffer memory 112. As a specific example, the image capture data processing unit 113 generates 60 seconds of image capture data as files in the order of recording from the image capture data temporarily stored in the buffer memory 112. The image capture data processing unit 113 outputs the generated image capture data to the operation control unit (recording control unit) 122. The image capture data processing unit 113 also decodes the generated image capture data via the playback control unit 121 and then outputs it to the display control unit 119. The period of the image capture data generated as a file is set to 60 seconds as an example, but is not limited to this. The image capture data referred to here may be data including audio in addition to video captured by the camera 211.

[0025] The event detection unit 114 detects an event based on the acceleration applied to the vehicle. More specifically, the event detection unit 114 detects an event based on the detection result of the acceleration sensor 215. The event detection unit 114 detects that an event has occurred when the acceleration information acquired by the event detection unit 114 from the acceleration sensor 215 is equal to or greater than a threshold value.

[0026] The position information acquisition unit 115 acquires position information indicating the current position of the vehicle. The position information acquisition unit 115 calculates the position information of the current position of the vehicle using a known method based on the GNSS signal received by the GNSS receiver unit 216. The position information acquisition unit 115 outputs the calculated position information to the recording control unit 122.

[0027] The voice command determination unit 116 recognizes an utterance by the user and determines whether the recognized utterance is a voice command. The voice command determination unit 116 analyzes the voice input from the microphone 212 and recognizes the content of the utterance contained in the voice. The voice command determination unit 116 performs acoustic model analysis for each phoneme or each word of the voice input from the microphone 212 and recognizes the content of the utterance by comparing it with a phoneme model or a language model. The voice command determination unit 116 recognizes a voice command for the vehicular recording device 100. When the voice command determination unit 116 recognizes a voice command such as a voice command instructing the vehicular recording device 100 to record an event, it outputs the recognition result to the voice command reception unit 117.

[0028] In this embodiment, the voice command determination unit 116 determines whether the recognized utterance is a voice command for recording photographed data. In this embodiment, the voice command determination unit 116 determines whether the recognized utterance is a voice command for recording an event of photographed data.

[0029] In this embodiment, the voice command determination unit 116 determines that the recognized utterance is a voice command when the recognition result of the received utterance indicates that an utterance that matches a predetermined voice command by a first threshold or more has been detected.

[0030] To prevent malfunction, a voice command is composed of, for example, 4 to 5 or more syllables. For example, a voice command for recording an event is set to "roku ga kai shi" consisting of 6 syllables. The voice command determination unit 116 determines that a voice command is a voice command when the recognition rate of the voice command is equal to or higher than a first threshold. The voice command determination unit 116 does not determine that a voice command is a voice command when the recognition rate of the voice command is lower than the first threshold. For example, the first threshold is set to 70%. The voice command determination unit 116 determines that a voice command is a voice command when the recognition rate of the voice command is, for example, 70% or higher. The voice command determination unit 116 does not determine that a voice command is a voice command when the recognition rate of the voice command is lower than 70%. The recognition rate of a voice command is the rate at which the recognized voice matches a preset voice command. The rate at which the recognized voice matches is the rate of matching syllables to the syllables that make up the preset voice command, or the rate at which the recognized voice matches the entire preset voice command. language For example, the degree of agreement with the model.

[0031] A case where the preset voice command is "rokuga kai shi" will be described. For example, if the voice recognition rate of the recognized utterance for "rokuga kai shi" is 70% or higher, the voice command determination unit 116 determines that "rokuga kai shi" has been input by voice, and accepts a voice operation by the voice command.

[0032] Voice commands for drive recorders require redundancy to prevent malfunctions, and are expected to be difficult for users to remember due to their low frequency of use, making it difficult for users to utter them accurately in an instant. On the other hand, voice commands for drive recorders used to record events such as accidents may require urgency and speed. Therefore, the voice command determination unit 116 has the following functions.

[0033] The voice command determination unit 116 determines that the recognized utterance is a voice command when the recognition result of the received utterance indicates that an utterance that is equal to or greater than a second threshold indicating a degree of matching lower than the first threshold and less than the first threshold has been detected multiple times within a predetermined period T1.

[0034] The predetermined period T1 is, for example, 5 seconds.

[0035] For example, the second threshold is set to 50%. If the recognition rate of the recognized voice for the voice command is, for example, 50% or more and less than 70%, and if a voice with a recognition rate of 50% or more and less than 70% is detected multiple times within the predetermined period T1, the voice command determination unit 116 determines that the recognized voice is a voice command, that is, that a voice command has been uttered. If the recognition rate of the recognized voice for the voice command is, for example, less than 50%, or if a voice with a recognition rate of 50% or more and less than 70% is not detected multiple times within the predetermined period T1, the voice command determination unit 116 does not determine that the recognized voice is a voice command, that is, that the recognized voice is not a voice command.

[0036] A case where the preset voice command is "rokuga kaishi" will be described. For example, if the voice recognition rate for the recognized voice is 50% or more and less than 70% for "rokuga kaishi" and a voice with a voice recognition rate of 50% or more and less than 70% is detected multiple times within a predetermined period T1, the voice command determination unit 116 determines that "rokuga kaishi" has been voice input. For example, if "rokuga" is uttered twice within a predetermined period T1, the voice command determination unit 116 determines that "rokuga kaishi" has been voice input. For example, if "kaishi" and "rokuga" are uttered within a predetermined period T1, the voice command determination unit 116 determines that "rokuga kaishi" has been voice input. For example, if the voice recognition rate for "rokuga kaishi" is less than 50%, or if a voice with a voice recognition rate of 50% or more and less than 70% is not detected multiple times within a predetermined period T1, the voice command determination unit 116 does not determine that "rokuga kaishi" has been voice input. For example, if "Rokuga" is uttered once within a predetermined period T1, it is not determined that "Rokuga kaishi" has been input by voice. For example, if "Satsuei" is uttered twice within a predetermined period T1, it is not determined that "Rokuga kaishi" has been input by voice.

[0037] When the voice command determination unit 116 determines that a voice command has been uttered, the voice command reception unit 117 accepts the received voice command. Based on the recognition result of the voice command determination unit 116 for the voice input from the microphone 212, the voice command reception unit 117 receives the voice input from the microphone 212 as a voice command instructing various operations. For example, the voice command reception unit 117 receives a voice command instructing a playback operation or a voice command instructing an operation to erase captured data, and outputs a control signal. For example, the voice command reception unit 117 receives a voice command instructing to end loop recording, and outputs a control signal. The voice command reception unit 117 receives a voice command instructing to record an event, and outputs a control signal. For example, the voice command reception unit 117 receives the voice command "Record record" as a voice command instructing to record an event, and outputs a control signal.

[0038] When the voice command receiving unit 117 receives from the voice command determining unit 116 that it has recognized an utterance instructing to record an event, it outputs a control signal instructing to record the event to the recording control unit 122. When the voice command receiving unit 117 receives from the voice command determining unit 116 that it has recognized an utterance instructing to perform a playback operation, it outputs a control signal instructing to perform a playback operation to the playback control unit 121.

[0039] The operation control unit 118 acquires operation information for various operations accepted by the operation unit 214. More specifically, the operation control unit 118 accepts operations on a physical interface such as a touch panel. For example, the operation control unit 118 acquires playback operation information indicating a playback operation or deletion operation information indicating an deletion operation of captured data, and outputs a control signal. For example, the operation control unit 118 acquires end operation information indicating an operation to end loop recording, and outputs a control signal.

[0040] The display control unit 119 controls the display of the captured data on the display unit 217. The display control unit 119 outputs a video signal that causes the captured data to be output to the display unit 217. More specifically, the display control unit 119 outputs a video signal that displays the video captured by the camera 211, or the loop recorded video data or event data recorded in the recording unit 213 by playing back the video.

[0041] The playback control unit 121 controls playback of loop recorded video data or event data recorded in the recording unit 213, based on a playback operation control signal output from the operation control unit 118. The playback control unit 121 includes a decoder (not shown), and plays back various types of data by decoding the supplied compressed data.

[0042] The operation control unit 122 performs an operation based on the voice command received by the voice command receiving unit 117. In this embodiment, the recording control unit 122 will be described as an example of the operation control unit 122. The recording control unit 122 controls the recording unit 213 to record the shooting data filed by the shooting data processing unit 113. During a period in which a loop recording process is being performed, such as when the vehicle accessory power is ON, the recording control unit 122 records the shooting data filed by the shooting data processing unit 113 in the recording unit 213 as overwritable shooting data. More specifically, during a period in which the loop recording process is being performed, the recording control unit 122 continues to record the shooting data generated by the shooting data processing unit 113 in the recording unit 213, and when the capacity of the recording unit 213 becomes full, it overwrites the oldest shooting data with new shooting data.

[0043] When an event is detected by the event detection unit 114, the recording control unit 122 stores the photographed data corresponding to the detected event. The photographed data corresponding to the detected event is photographed data for a predetermined period of time in the photographed data generated by the photographed data processing unit 113. The recording control unit 122 stores the photographed data corresponding to the detected event in the recording unit 213 as event data that is prohibited from being overwritten.

[0044] When an event is detected by the event detection unit 114, the recording control unit 122 saves, as event data, photographed data for a predetermined period before and after the time point at which the event was detected. FIG. 2 is a diagram showing an example of a recording period for event data. As shown in FIG. 2, the recording control unit 122 saves, as event data, photographed data for a period from a time point P1 before the time point t1 at which the event was detected by the event detection unit 114 to a time point at which the time point P1 has elapsed since t1. When an event is detected by the event detection unit 114, the recording control unit 122 copies, from the buffer memory 112, photographed data for a predetermined period before and after the time point t1 at which the event was detected, such as approximately 10 seconds before and after the time point t1, and saves the copied data as event data.

[0045] The predetermined period before and after a certain point in time is, for example, 10 seconds, which is the sum of a period P1 (for example, 5 seconds) before a certain point in time and a period P1 (for example, 5 seconds) after the certain point in time. The period before a certain point in time and the period after the certain point in time may be different periods.

[0046] In this embodiment, the recording control unit 122 stores the photographic data acquired by the photographic data acquisition unit 111 based on the voice command accepted by the voice command acceptance unit 117 .

[0047] In this embodiment, when the voice command determination unit 116 detects a voice command by detecting an utterance that matches a predetermined voice command by a first threshold or more, the recording control unit 122 saves, as event data, captured data for a predetermined period before and after the time point at which the voice command was detected. As shown in Fig. 2, the recording control unit 122 saves, as event data, captured data for a period from a time point prior to the voice command reception time point t2 by a period P1 to a time point at which the voice command reception time point t2 has elapsed. For example, the recording control unit 122 saves, as event data, captured data for 10 seconds before and after the voice command reception time point.

[0048] When the voice command determination unit 116 detects a voice command by detecting multiple utterances with a recognition rate of a predetermined voice command equal to or greater than the second threshold and less than the first threshold within a predetermined period T1, the recording control unit 122 saves, as event data, captured data for a predetermined period before and after the time t3 at which the first utterance among the multiple detected utterances was detected (hereinafter referred to as the "utterance detection time"). In this embodiment, the recording control unit 122 saves, as event data, captured data for a predetermined period before and after the first utterance detection time t3. As shown in FIG. 2, when multiple utterances equal to or greater than the second threshold and less than the first threshold are detected within the predetermined period T1, such as at utterance detection times t3 and t4, the recording control unit 122 saves, as event data, captured data for a period from a time period P1 before the first utterance detection time t3 to a time period P1 after the first utterance detection time t3. For example, the recording control unit 122 saves, as event data, captured data for 10 seconds before and after the utterance detection time t3.

[0049] When an event needs to be recorded urgently, for example, there is a high possibility that the voice command cannot be uttered accurately in an emergency. In such a case, the voice command may not be uttered accurately, and a voice command with a low recognition rate may be uttered multiple times. Therefore, if a voice command with a low recognition rate is received multiple times within a predetermined period T1, the event data is saved starting from the time when the first utterance was detected. This allows event data for an appropriate period to be saved even if the voice command is not uttered accurately.

[0050] <Information processing in voice-operated control devices> Next, the flow of processing in the control device 100 will be described with reference to Fig. 3. When the vehicle recording device 10 is started, the processing of the flowchart shown in Fig. 3 begins. While the vehicle recording device 10 is running, the control device 100 detects acceleration using the acceleration sensor 215 at a set acceleration threshold. The control device 100 starts event detection based on the detected acceleration using the event detection unit 114. A description of event detection based on acceleration detection will be omitted here. Furthermore, while the vehicle recording device 10 is running, the control device 100 performs recognition processing of voice input from the microphone 212.

[0051] When the process starts, the control device 100 starts loop recording, which is normal recording (step S101). More specifically, the recording control unit 122 starts loop recording to overwriteably record the file generated by the shooting data processing unit 113 in the recording unit 213. The loop recording by the recording control unit 122 and the event detection by the event detection unit 114 and the voice command receiving unit 117 continue until the process ends. The control device 100 proceeds to step S102.

[0052] The control device 100 determines whether or not an event has been detected based on the detection result by the event detection unit 114 (step S102). If the acceleration detected by the event detection unit 114 is equal to or greater than a threshold, the control device 100 determines that an event has been detected (Yes in step S102) and proceeds to step S103. If the event detection unit 114 determines that the acceleration detected is not equal to or greater than the threshold, the control device 100 determines that an event has not been detected (No in step S102) and proceeds to step S104.

[0053] If it is determined that an event has been detected (Yes in step S102), the control device 100 causes the recording control unit 122 to store the photographed data for a predetermined period before and after the event detection time as event data (step S103). More specifically, the control device 100 causes the recording control unit 122 to store the photographed data taken from a time period P1 before the event detection time to a time period P1 after the event detection time as event data in the recording unit 213 while prohibiting overwriting. The control device 100 proceeds to step S109.

[0054] If it is determined that an event has not been detected (No in step S102), the control device 100 determines whether a voice command instructing event recording has been accepted (step S104). More specifically, the control device 100 determines that a voice command instructing event recording has been accepted when the voice command determination unit 116 indicates that the recognition result of the accepted utterance indicates that an utterance matching a predetermined voice command by a first threshold or more has been detected. If the voice command determination unit 116 determines that a voice command instructing event recording has been accepted (Yes in step S104), the control device 100 proceeds to step S105. Alternatively, if the voice command determination unit 116 does not determine that a voice command instructing event recording has been accepted (No in step S104), the control device 100 proceeds to step S109.

[0055] When it is determined that a voice command instructing event recording has been received (Yes in step S104), the control device 100 causes the recording control unit 122 to store, as event data, the photographed data for a predetermined period before and after the time point at which the voice command is received (step S105). More specifically, the control device 100 causes the recording control unit 122 to store, as event data, the photographed data taken during the period from the time point prior to the time point at which the voice command is received by a period P1, to the time point after the time point at which the voice command is received by the recording unit 213, while prohibiting overwriting. The control device 100 proceeds to step S109.

[0056] If the control device 100 does not determine that a voice command instructing event recording has been received (No in step S104), it determines whether or not an utterance that has a low degree of match with the voice command instructing event recording has been detected (step S106). More specifically, the control device 100 determines that an utterance that has a low degree of match with the voice command instructing event recording has been detected when the voice command determination unit 116 indicates that an utterance that is equal to or greater than the second threshold and less than the first threshold has been detected. If the control device 100 determines that an utterance that has a low degree of match with the voice command instructing event recording has been detected (Yes in step S106), it proceeds to step S107. If the control device 100 does not determine that an utterance that has a low degree of match with the voice command instructing event recording has been detected (No in step S106), it proceeds to step S109.

[0057] When it is determined that an utterance with a low degree of match with the voice command instructing event recording has been detected (Yes in step S106), the control device 100 determines whether an utterance with a low degree of match with the voice command for event recording has been detected within a predetermined period T1 (step S107). If the voice command determination unit 116 has detected an utterance with a low degree of match multiple times within the predetermined period T1 (Yes in step S107), the control device 100 proceeds to step S108. If the voice command determination unit 116 has not detected an utterance with a low degree of match multiple times within the predetermined period T1 (No in step S107), the control device 100 proceeds to step S109.

[0058] If an utterance with a low degree of match is not detected multiple times within the predetermined period T1 (No in step S107), the control device 100 causes the recording control unit 122 to store, as event data, the captured data for a predetermined period before and after the first detection of a voice command with a low degree of match with the voice command instructing event recording (step S108). More specifically, the control device 100 causes the recording control unit 122 to store, as event data, the captured data captured during the period from the time point preceding the time point of the first utterance detection by the period P1 to the time point following the time point of the first utterance detection, in the recording unit 213, with overwriting prohibited. The control device 100 proceeds to step S109.

[0059] The control device 100 determines whether or not to end the process (step S109). For example, the control device 100 determines to end the process when the power or motive power of the vehicle is turned off or the operation unit 214 is operated. If the control device 100 determines to end the process (Yes in step S109), it ends this process. If the control device 100 does not determine to end the process (No in step S109), it executes the process of step S102 again.

[0060] <Effects> As described above, according to this embodiment, when an utterance that has a low degree of match with a preset voice command is detected multiple times within a predetermined period, it can be determined that the recognized utterance is a voice command. According to this embodiment, when a user is unable to immediately remember a voice command and utters an utterance that has a low degree of match multiple times, it can be determined that the utterance is a voice command.

[0061] According to this embodiment, when an utterance with a low degree of match to a voice command instructing recording of photographed data is detected multiple times within a predetermined period, it can be determined that the recognized utterance is a voice command. According to this embodiment, when a user wants to record photographed data but is unable to immediately remember the voice command and utters a plurality of utterances with a low degree of match, it is possible to record the photographed data.

[0062] According to this embodiment, if an utterance with a low degree of match to a voice command instructing event recording is detected multiple times within a predetermined period, it can be determined that the recognized utterance is a voice command. According to this embodiment, if a person is unable to immediately remember a voice command when an event occurs and utters utterances with a low degree of match multiple times, it is possible to record the captured data as event data.

[0063] According to this embodiment, it is possible to appropriately determine a voice command for a drive recorder that requires redundancy, is infrequently used, is difficult for a user to remember, and is difficult to utter accurately on the spot, from utterances with a low degree of coincidence. According to this embodiment, it is possible to record captured data for an appropriate period without delaying the timing of recording, even though the recording of captured data may require urgency or speed.

[0064] [Second embodiment] The vehicle recording device 10 according to this embodiment will be described with reference to FIGS. 4 and 5. FIG. 4 is a diagram showing an example of the recording time of a still image. FIG. 5 is a flowchart showing an example of the processing flow in a control device according to a second embodiment. The basic configuration of the vehicle recording device 10 is similar to that of the vehicle recording device 10 according to the first embodiment. In the following description, components similar to those of the vehicle recording device 10 are denoted by the same or corresponding reference numerals, and detailed description thereof will be omitted. In this embodiment, the processing in the operation unit 214, the voice command determination unit 116, the voice command reception unit 117, the operation control unit 118, and the recording control unit 122 differs from that in the first embodiment.

[0065] The operation unit 214 can accept an operation to record a still image.

[0066] The voice command determination unit 116 determines whether the recognized utterance is a voice command for recording a still image of the captured data. If the voice command determination unit 116 recognizes a voice command instructing to record a still image, it outputs the recognition result to the voice command reception unit 117.

[0067] The voice command receiving unit 117 receives a voice command instructing still image recording. For example, the voice command receiving unit 117 receives the voice command "take a photo" as a voice command instructing still image recording, and outputs a control signal. When the voice command receiving unit 117 obtains from the voice command determining unit 116 that it has recognized an utterance instructing still image recording, it outputs a control signal instructing still image recording to the recording control unit 122.

[0068] The operation control unit 118 acquires operation information indicating still image recording and outputs a control signal.

[0069] When the voice command determination unit 116 detects a voice command by detecting an utterance that matches a predetermined voice command indicating still image recording by a first threshold value or more, the recording control unit 122 saves the still image at the time of receiving the voice command. When the voice command receiving unit 117 receives a voice command instructing still image recording, the recording control unit 122 saves the still image at the time of receiving the voice command. As shown in Fig. 4, for example, the recording control unit 122 saves the still image at the time of receiving the voice command t6.

[0070] If the voice command determination unit 116 detects an utterance that is equal to or greater than the second threshold and less than the first threshold multiple times within the predetermined period T1, the recording control unit 122 determines that a voice command has been detected, and saves a still image at time t7 when the first utterance was detected. As shown in FIG. 4, if an utterance that is equal to or greater than the second threshold and less than the first threshold is detected at time t7 and time t8 within the predetermined period T1, the recording control unit 122 saves a still image at time t7 when the first utterance was detected. If the preset voice command is, for example, "take a picture," the recording control unit 122 determines that a voice command has been detected if utterances such as "take a picture" and "take a picture" are detected multiple times within the predetermined period T1 as utterances whose voice recognition rate is equal to or greater than the second threshold and less than the first threshold.

[0071] Next, the flow of processing in the control device 100 will be described with reference to Fig. 5. The processing in steps S111 and S117 shown in Fig. 5 is the same as that in steps S101 and S109 in the flowchart shown in Fig. 3.

[0072] The control device 100 determines whether a voice command instructing still image recording has been accepted (step S112). More specifically, the control device 100 determines that a voice command instructing still image recording has been accepted when the voice command judgment unit 116 indicates that the recognition result of the accepted utterance indicates that an utterance matching a predetermined voice command by a first threshold or more has been detected. If the voice command judgment unit 116 determines that a voice command instructing still image recording has been accepted (Yes in step S112), the control device 100 proceeds to step S113. Alternatively, if the voice command judgment unit 116 does not determine that a voice command instructing still image recording has been accepted (No in step S112), the control device 100 proceeds to step S114.

[0073] If it is determined that a voice command to record a still image has been received (Yes in step S112), the control device 100 causes the recording control unit 122 to store the captured data at the time of receiving the voice command as a still image (step S113). The control device 100 proceeds to step S117.

[0074] If the control device 100 does not determine that a voice command instructing still image recording has been received (No in step S112), it determines whether or not an utterance that has a low degree of match with the voice command instructing still image recording has been detected (step S114). More specifically, the control device 100 determines that an utterance that has a low degree of match with the voice command instructing still image recording has been detected when the voice command determination unit 116 indicates that an utterance that is equal to or greater than the second threshold and less than the first threshold has been detected. If the control device 100 determines that an utterance that has a low degree of match with the voice command instructing still image recording has been detected (Yes in step S114), it proceeds to step S115. If the control device 100 does not determine that an utterance that has a low degree of match with the voice command instructing still image recording has been detected (No in step S114), it proceeds to step S117.

[0075] When it is determined that an utterance with a low degree of match with the voice command for instructing still image recording has been detected (Yes in step S114), the control device 100 determines whether an utterance with a low degree of match with the voice command for still image recording has been detected within a predetermined period T1 (step S115). If the voice command determination unit 116 has detected an utterance with a low degree of match multiple times within the predetermined period T1 (Yes in step S115), the control device 100 proceeds to step S116. If the voice command determination unit 116 has not detected an utterance with a low degree of match multiple times within the predetermined period T1 (No in step S115), the control device 100 proceeds to step S117.

[0076] If an utterance with a low degree of match is detected multiple times within the predetermined period T1 (Yes in step S115), the control device 100 causes the recording control unit 122 to store, as a still image, the captured data at the time of the first detection of the voice command with a low degree of match with the voice command instructing still image recording (step S116). The control device 100 proceeds to step S117.

[0077] As described above, according to this embodiment, if an utterance that has a low degree of match with a voice command instructing recording of a still image is detected multiple times within a specified period, the recognized utterance is determined to be a voice command, and a still image can be recorded at the appropriate time.

[0078] [Third embodiment] <Video Recording Device> A video recording device (voice-operated device) 20 having a voice-operated control device (hereinafter referred to as the "control device") 100 according to this embodiment will be described with reference to FIGS. 6 to 8. FIG. 6 is a block diagram showing an example of the configuration of a video recording device 20 having a control device 100 according to a third embodiment. FIG. 7 is a diagram showing an example of the start point of video capture. FIG. 8 is a flowchart showing an example of the processing flow in the control device 100 according to the third embodiment. The video recording device 20, which is an example of a voice-operated device, is a device that records video and audio, such as a smartphone or a video camera. Video cameras also include so-called action cameras. For example, even if a voice command cannot be accurately uttered or the voice command cannot be properly recognized, if multiple utterances with low matching are detected, the video recording device 20 determines that the voice command is a voice command and starts capturing video, in other words, starts recording the captured video and audio. Components similar to those of the vehicular recording device 10 of the first embodiment are designated by the same or corresponding reference numerals, and detailed descriptions thereof will be omitted.

[0079] As shown in FIG. 6, the video recording device 20 includes a camera 211, a microphone 212, a recording unit 213, an operation unit 214, a display unit 217, and the control device 100.

[0080] The camera 211 captures video. In this embodiment, the camera 211 captures video in response to a video capture instruction given by a voice command.

[0081] The microphone 212 is a microphone that picks up voice commands that indicate various operations for the video recording device 20. For example, the microphone 212 can accept a shooting instruction by voice command.

[0082] The operation unit 214 can accept various operations for the video recording device 20. For example, the operation unit 214 can accept an instruction indicating whether or not to accept a voice operation. When an instruction to accept a voice operation is accepted, the voice command determination unit 116, which will be described later, puts the unit 214 into standby to accept the voice operation.

[0083] The display unit 217 is disposed in a position visible to the user.

[0084] <Voice-operated control device> The control device 100 has components such as functional blocks realized by executing a program, including a shooting data acquisition unit 111, a buffer memory 112, a shooting data processing unit 113, a voice command determination unit 116, a voice command reception unit 117, an operation control unit 118, a display control unit 119, a playback control unit 121, and an operation control unit (recording control unit) 122.

[0085] The photographing data acquisition unit 111 acquires photographing data captured by the camera 211. The photographing data acquisition unit 111 outputs the acquired photographing data to the photographing data processing unit 113 or the buffer memory 112.

[0086] When it becomes possible to accept a shooting instruction by voice command, the buffer memory 112 starts buffering the shooting data for a certain period of time acquired by the shooting data acquisition unit 111 .

[0087] The shooting data processing unit 113 generates shooting data as a file for a certain period of time from the shooting data acquired by the shooting data acquisition unit 111 or the shooting data temporarily stored in the buffer memory 112. As a specific example, the shooting data processing unit 113 generates 60 seconds of shooting data as a file in recording order from the shooting data acquired by the shooting data acquisition unit 111 or the shooting data temporarily stored in the buffer memory 112. The shooting data processing unit 113 outputs the generated shooting data to the operation control unit (recording control unit) 122. The shooting data processing unit 113 also decodes the images from the generated shooting data via the playback control unit 121 and then outputs it to the display control unit 119.

[0088] When the voice command determination unit 116 recognizes a voice command such as a voice command instructing the video recording device 20 to start shooting or a voice command instructing the video recording device 20 to end shooting, it outputs the recognition result to the voice command reception unit 117.

[0089] In this embodiment, the voice command determination unit 116 determines whether the recognized utterance is a voice command for starting image capture, and whether it is a voice command for ending image capture.

[0090] To prevent malfunctions, the voice command to start shooting is also configured with, for example, 4 to 5 syllables or more, similar to the first embodiment. For example, the voice command to start shooting is set to "roku ga kai shi" (roku ga kai shi) consisting of 6 syllables.

[0091] The voice commands of the video recording device 20 require redundancy to prevent malfunction, and depending on the usage pattern, it is expected that accurate utterance or appropriate recognition may be difficult. On the other hand, since the instruction to start shooting is often given at the timing when the user wants to start shooting, shooting needs to start quickly when the instruction to start shooting is received. Therefore, the voice command determination unit 116 has the following functions.

[0092] The voice command receiving unit 117 receives a voice command instructing the start of shooting and a voice command instructing the end of shooting, and outputs a control signal. For example, the voice command receiving unit 117 receives the voice command "6 ga kaishi" as a voice command instructing the start of shooting, and outputs a control signal. When the voice command receiving unit 117 obtains from the voice command determining unit 116 that an utterance instructing the start of shooting has been recognized, it outputs a control signal instructing the start of shooting to the recording control unit 122. For example, the voice command receiving unit 117 receives the voice command "6 ga shuryo" as a voice command instructing the end of shooting, and outputs a control signal. When the voice command receiving unit 117 obtains from the voice command determining unit 116 that an utterance instructing the end of shooting has been recognized, it outputs a control signal instructing the end of shooting to the recording control unit 122.

[0093] The operation control unit 118 acquires operation information indicating whether or not a voice operation is to be accepted by the operation unit 214, and outputs a control signal.

[0094] The operation control unit 122 performs an operation based on the voice command received by the voice command receiving unit 117. In this embodiment, the recording control unit 122 will be described as an example of the operation control unit 122. The recording control unit 122 controls the recording unit 213 to record the shooting data filed by the shooting data processing unit 113. The recording control unit 122 records the shooting data filed by the shooting data processing unit 113 in the recording unit 213 during the period from when a shooting start operation is performed to when a shooting end operation is performed in the video recording device 20.

[0095] In this embodiment, when the voice command determination unit 116 detects a voice command by detecting an utterance that matches a predetermined voice command by a first threshold value or more, the recording control unit 122 starts recording the captured data from the time the voice command is detected. As shown in Fig. 7, recording of the captured data starts from time t21 when the voice command is received.

[0096] When the voice command determination unit 116 detects a voice command by detecting an utterance having a recognition rate of equal to or greater than the second threshold and less than the first threshold for a preset voice command multiple times within a predetermined period T1, the recording control unit 122 saves, as event data, captured data for a predetermined period before and after the first utterance detection point in time of the multiple detected utterances. As shown in Fig. 7, when an utterance equal to or greater than the second threshold and less than the first threshold is detected multiple times within the predetermined period T1, such as at utterance detection points t22 and t23, recording of captured data starts from the first utterance detection point t22.

[0097] <Information processing in voice-operated control devices> Next, the flow of processing in the control device 100 will be described with reference to Fig. 8. When the video recording device 20 is started, the processing of the flowchart shown in Fig. 8 begins. While the video recording device 20 is running, the control device 100 performs a recognition process for the voice input from the microphone 212.

[0098] When the process starts, the control device 100 determines whether to stand by to accept a voice operation to start shooting (step S201). More specifically, the operation control unit 118 determines whether to acquire operation information indicating an operation indicating whether to accept a voice operation. When the operation information indicating an operation indicating whether to accept a voice operation is acquired, the control device 100 determines to stand by to accept a voice operation to start shooting. When the control device 100 determines to stand by to accept a voice operation to start shooting (Yes in step S201), the control device 100 proceeds to step S207. The processes of steps S207 to S218 are processes based on a voice command. When the control device 100 does not determine to stand by to accept a voice operation to start shooting (No in step S201), the control device 100 proceeds to step S202. The processes of steps S202 to S206 are processes based on various operations on the operation unit 214.

[0099] When it is not determined that the control device 100 is on standby for receiving a voice operation to start shooting (No in step S201), the control device 100 determines whether or not a shooting start operation has been received (step S202). More specifically, the operation control unit 118 determines whether or not operation information indicating a shooting start operation has been acquired from the operation unit 214. When operation information indicating a shooting start operation has been acquired, the control device 100 determines that a shooting start operation has been received. When the control device 100 determines that a shooting start operation has been received (Yes in step S202), the control device 100 proceeds to step S203. When the control device 100 does not determine that a shooting start operation has been received (No in step S202), the control device 100 proceeds to step S206.

[0100] If it is determined that the shooting start operation has been accepted (Yes in step S202), the control device 100 causes the recording control unit 122 to start recording of the shooting data from the time when the shooting start operation was accepted (step S203). The control device 100 proceeds to step S204.

[0101] The control device 100 determines whether or not an operation to end shooting has been accepted (step S204). More specifically, the operation control unit 118 determines whether or not operation information indicating an operation to end shooting has been acquired from the operation unit 214. If operation information indicating an operation to end shooting has been acquired, the control device 100 determines that an operation to end shooting has been accepted. If the control device 100 determines that an operation to end shooting has been accepted (Yes in step S204), the control device 100 proceeds to step S205. If the control device 100 does not determine that an operation to end shooting has been accepted (No in step S204), the control device 100 executes the processing of step S204 again.

[0102] If it is determined that the shooting end operation has been accepted (Yes in step S204), the control device 100 causes the recording control unit 122 to end recording of the photographed data at the time of accepting the shooting end operation (step S205). The control device 100 proceeds to step S206.

[0103] The control device 100 determines whether or not to end the process (step S206). For example, the control device 100 determines to end the process when the power or motive force of the video recording device 20 is turned off or the operation unit 214 is operated. If the control device 100 determines to end the process (Yes in step S206), it ends this process. If the control device 100 does not determine to end the process (No in step S206), it executes the process of step S202 again.

[0104] When it is determined that the control device 100 is on standby for receiving a voice command to start shooting (Yes in step S201), the control device 100 starts buffering the shooting data (step S207). More specifically, the recording control unit 122 starts buffering the shooting data for a certain period of time acquired by the shooting data acquisition unit 111 in the buffer memory 112. The control device 100 proceeds to step S208.

[0105] The control device 100 determines whether a voice command instructing to start shooting has been accepted (step S208). More specifically, the control device 100 determines that a voice command instructing to start shooting has been accepted when the voice command judgment unit 116 indicates that the recognition result of the accepted utterance indicates that an utterance matching a predetermined voice command by a first threshold or more has been detected. If the voice command judgment unit 116 determines that a voice command instructing to start shooting has been accepted (Yes in step S208), the control device 100 proceeds to step S209. Alternatively, if the voice command judgment unit 116 does not determine that a voice command instructing to start shooting has been accepted (No in step S208), the control device 100 proceeds to step S210.

[0106] When it is determined that a voice command to start shooting has been received (Yes in step S208), the control device 100 causes the recording control unit 122 to start recording the shooting data from the time the voice command was received (step S209). More specifically, the control device 100 causes the recording control unit 122 to permit the recording unit 213 to overwrite and store the shooting data shot from the time the voice command was received. The control device 100 proceeds to step S210.

[0107] If the control device 100 does not determine that a voice command instructing to start shooting has been received (No in step S208), it determines whether or not an utterance that has a low degree of match with the voice command instructing to start shooting has been detected (step S210). More specifically, the control device 100 determines that an utterance that has a low degree of match with the voice command instructing to start shooting has been detected when the voice command determination unit 116 indicates that an utterance that is equal to or greater than the second threshold and less than the first threshold has been detected. If the control device 100 determines that an utterance that has a low degree of match with the voice command instructing to start shooting has been detected (Yes in step S210), it proceeds to step S211. If the control device 100 does not determine that an utterance that has a low degree of match with the voice command instructing to start shooting has been detected (No in step S210), it proceeds to step S213.

[0108] When it is determined that an utterance with a low degree of match with the voice command instructing to start shooting has been detected (Yes in step S210), the control device 100 determines whether an utterance with a low degree of match with the voice command instructing to start shooting has been detected within a predetermined period T1 (step S211). When the voice command determination unit 116 has detected an utterance with a low degree of match multiple times within the predetermined period T1 (Yes in step S211), the control device 100 proceeds to step S212. When the voice command determination unit 116 has not detected an utterance with a low degree of match multiple times within the predetermined period T1 (No in step S211), the control device 100 proceeds to step S213.

[0109] If an utterance with a low degree of match is detected multiple times within the predetermined period T1 (Yes in step S211), the control device 100 causes the recording control unit 122 to start recording the captured data from the first time a voice command with a low degree of match with the voice command instructing the start of capture is detected (step S212). More specifically, the control device 100 causes the recording control unit 122 to permit the recording unit 213 to overwrite and store the captured data from the first time the utterance is detected. The control device 100 proceeds to step S213.

[0110] The control device 100 determines whether a voice command instructing to end image capture has been accepted (step S213). More specifically, the control device 100 determines that a voice command instructing to end image capture has been accepted when the voice command judgment unit 116 indicates that the recognition result of the accepted utterance indicates that an utterance matching a predetermined voice command by a first threshold or more has been detected. If the voice command judgment unit 116 judges that a voice command instructing to end image capture has been accepted (Yes in step S213), the control device 100 proceeds to step S214. Alternatively, if the voice command judgment unit 116 does not judge that a voice command instructing to end image capture has been accepted (No in step S213), the control device 100 proceeds to step S215.

[0111] If it is determined that a voice command to end shooting has been received (Yes in step S213), the control device 100 causes the recording control unit 122 to end recording of the shooting data at the time the voice command is received (step S214). The control device 100 proceeds to step S218.

[0112] If the control device 100 does not determine that a voice command instructing to end image capture has been received (No in step S213), it determines whether or not an utterance that has a low degree of match with the voice command instructing to end image capture has been detected (step S215). More specifically, the control device 100 determines that an utterance that has a low degree of match with the voice command instructing to end image capture has been detected when the voice command determination unit 116 indicates that an utterance that is equal to or greater than the second threshold and less than the first threshold has been detected. If the control device 100 determines that an utterance that has a low degree of match with the voice command instructing to end image capture has been detected (Yes in step S215), it proceeds to step S216. If the control device 100 does not determine that an utterance that has a low degree of match with the voice command instructing to end image capture has been detected (No in step S215), it proceeds to step S218.

[0113] When it is determined that an utterance with a low degree of match with the voice command instructing to end shooting has been detected (Yes in step S215), the control device 100 determines whether an utterance with a low degree of match with the voice command instructing to end shooting has been detected within the predetermined period T1 (step S216). If the voice command determination unit 116 has detected an utterance with a low degree of match multiple times within the predetermined period T1 (Yes in step S216), the control device 100 proceeds to step S217. If the voice command determination unit 116 has not detected an utterance with a low degree of match multiple times within the predetermined period T1 (No in step S216), the control device 100 proceeds to step S218.

[0114] If an utterance with a low degree of match is detected multiple times within the predetermined period T1 (Yes in step S216), the control device 100 causes the recording control unit 122 to end recording of the captured data at the first detection of a voice command with a low degree of match with the voice command instructing to end capturing (step S217). More specifically, the control device 100 causes the recording control unit 122 to store the captured data up to the first detection of the utterance in the recording unit 213. The control device 100 proceeds to step S218.

[0115] The control device 100 determines whether or not to end the process (step S218). For example, the control device 100 determines to end the process when the power or motive power of the vehicle is turned off or the operation unit 214 is operated. If the control device 100 determines to end the process (Yes in step S218), it ends this process. If the control device 100 does not determine to end the process (No in step S218), it executes the process of step S208 again.

[0116] <Effects> As described above, according to this embodiment, when a voice command cannot be spoken accurately, or when the voice command cannot be properly recognized due to the influence of surrounding sounds even if the voice command is spoken accurately, video or still images can be recorded at an appropriate time.

[0117] The vehicle recording device 10 according to the present disclosure may be implemented in various different forms other than the above-described embodiment. In the above-described embodiment, the vehicle recording device 10 including the voice-operated control device 100 has been described as an example, but the technology of the present disclosure can be applied to devices other than the vehicle recording device 10. For example, the technology can be applied to various devices that control devices using voice commands. For this reason, in the above-described embodiment, the recording control unit 122 has been described as an example of the operation control unit 122, but the operation control unit 122 can be applied to audio recording and various other controls in addition to video recording control.

[0118] In the above-described embodiment, the speech detection time points have been described without including the concept of a time span for the utterance to be detected, but the speech detection time points t3 and t7 include a time span in which an utterance such as "rokuga" is made from the start to the end. Therefore, the speech detection time points t3 and t7 may be set to the start or end of such an utterance, and can be set arbitrarily within the period from the start to the end of the utterance.

[0119] The components of the illustrated vehicle recording device 10 are conceptual and functional, and do not necessarily have to be physically configured as shown. In other words, the specific form of each device is not limited to that shown, and all or part of the devices may be functionally or physically distributed or integrated in any unit depending on the processing load and usage status of each device.

[0120] The configuration of the vehicle recording device 10 is realized, for example, as software, by a program loaded into a memory. In the above embodiment, the configuration has been described as functional blocks realized by the cooperation of these hardware and software. In other words, these functional blocks can be realized in various forms, using only hardware, only software, or a combination of both.

[0121] The above-described components include those that can be easily imagined by a person skilled in the art and those that are substantially the same. Furthermore, the above-described configurations can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the configurations are possible within the scope of the gist of the present invention. [Explanation of symbols]

[0122] 10 Vehicle recording device (voice-operated device) 100 Control device (voice-operated control device) 111 Shooting data acquisition unit 112 buffer memory 113 Shooting data processing section 114 Event detection unit 115 Location information acquisition unit 116 Voice command determination unit 117 Voice command reception unit 118 Operation control section 119 Display control unit 121 Playback control unit 122 Recording control section 211 Camera 212 microphones 213 Recording Department 214 Operation section 215 Acceleration Sensor 216 GNSS receiver 217 Display section P1 period T1 period

Claims

1. a voice command determination unit that recognizes an utterance by a user and determines whether the recognized utterance is a preset voice command; a voice command receiving unit that receives the voice command when the voice command determining unit determines that the preset voice command has been uttered; a photographic data acquisition unit that acquires photographic data captured by a camera that captures video; an operation control unit that stores the photographing data acquired by the photographing data acquisition unit based on a voice command for storing the photographing data accepted by the voice command acceptance unit; Equipped with the voice command determination unit determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that an utterance matching a first threshold or more with the predetermined voice command has been detected, and determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that the utterance is an utterance that is equal to or greater than a second threshold indicating a matching rate lower than the first threshold and is less than the first threshold, and that has been detected multiple times within a predetermined period; the voice command determination unit determines whether the recognized utterance is a voice command for performing an event recording of the photographed data; When the voice command determination unit detects the predetermined voice command by detecting an utterance in which the match rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more, the operation control unit saves, as event data, photographed data for a predetermined period before and after the time point at which the predetermined voice command was detected as a reference, and when the voice command determination unit detects the predetermined voice command by detecting an utterance in which the match rate of the recognized voice from the received utterance matches the second threshold or more and less than the first threshold multiple times within a predetermined period, the operation control unit saves, as event data, photographed data for a predetermined period before and after the time point at which the first utterance of the multiple detected utterances was detected as a reference. Voice-operated control device.

2. a voice command determination unit that recognizes an utterance by a user and determines whether the recognized utterance is a preset voice command; a voice command receiving unit that receives the voice command when the voice command determining unit determines that the preset voice command has been uttered; a photographic data acquisition unit that acquires photographic data captured by a camera that captures video; an operation control unit that stores the photographing data acquired by the photographing data acquisition unit based on a voice command for storing the photographing data accepted by the voice command acceptance unit; Equipped with the voice command determination unit determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that an utterance matching a first threshold or more with the predetermined voice command has been detected, and determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that the utterance is an utterance that is equal to or greater than a second threshold indicating a matching rate lower than the first threshold and is less than the first threshold, and that has been detected multiple times within a predetermined period; the voice command determination unit determines whether the recognized utterance is a voice command for saving a still image of the photographed data; When the voice command determination unit detects the predetermined voice command by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more, the operation control unit saves a still image at the time when the predetermined voice command is detected; when the voice command determination unit detects the predetermined voice command by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a second threshold or more and less than the first threshold multiple times within a predetermined period, the operation control unit saves a still image at the time when the first utterance of the multiple detected utterances is detected. Voice-operated control device.

3. a voice command determination unit that recognizes an utterance by a user and determines whether the recognized utterance is a preset voice command; a voice command receiving unit that receives the voice command when the voice command determining unit determines that the preset voice command has been uttered; a photographic data acquisition unit that acquires photographic data captured by a camera that captures video; an operation control unit that stores the photographing data acquired by the photographing data acquisition unit based on a voice command for storing the photographing data accepted by the voice command acceptance unit; Equipped with the voice command determination unit determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that an utterance matching a first threshold or more with the predetermined voice command has been detected, and determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that the utterance is an utterance that is equal to or greater than a second threshold indicating a matching rate lower than the first threshold and is less than the first threshold, and that has been detected multiple times within a predetermined period; the voice command determination unit determines whether the recognized utterance is a voice command for starting photography; When the voice command determination unit detects the predetermined voice command by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more, the operation control unit starts recording the captured data based on the time point at which the predetermined voice command was detected; when the voice command determination unit detects the predetermined voice command by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more within a predetermined period, the operation control unit starts recording the captured data based on the time point at which the first utterance from the utterance detected multiple times was detected. Voice-operated control device.

4. A voice command determination step of recognizing an utterance by a user and determining whether the recognized utterance is a preset voice command; a voice command receiving step of receiving a received voice command when it is determined in the voice command determining step that the predetermined voice command has been uttered; a photographic data acquisition step of acquiring photographic data photographed by a camera that photographs video; an operation step of storing the photographing data acquired in the photographing data acquisition step based on the voice command for storing the photographing data accepted in the voice command acceptance step; Including, the voice command determination step determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that an utterance matching a first threshold or more with the predetermined voice command has been detected, and determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that the utterance is an utterance that is equal to or greater than a second threshold indicating a matching rate lower than the first threshold and is less than the first threshold, and that has been detected multiple times within a predetermined period; the voice command determination step determines whether the recognized utterance is a voice command for recording an event of the photographed data; In the operation step, if the predetermined voice command is detected by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more in the voice command determination step, photographed data for a predetermined period before and after the time point at which the predetermined voice command is detected is stored as event data; and if the predetermined voice command is detected by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the second threshold or more and less than the first threshold multiple times within the predetermined period, photographed data for a predetermined period before and after the time point at which the first utterance of the multiple detected utterances is detected is stored as event data. A voice operation method executed by a voice operation control device.

5. A voice command determination step of recognizing an utterance by a user and determining whether the recognized utterance is a preset voice command; a voice command receiving step of receiving a received voice command when it is determined in the voice command determining step that the predetermined voice command has been uttered; a photographic data acquisition step of acquiring photographic data photographed by a camera that photographs video; an operation step of storing the photographing data acquired in the photographing data acquisition step based on the voice command for storing the photographing data accepted in the voice command acceptance step; Including, the voice command determination step determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that an utterance matching a first threshold or more with the predetermined voice command has been detected, and determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that the utterance is an utterance that is equal to or greater than a second threshold indicating a matching rate lower than the first threshold and is less than the first threshold, and that has been detected multiple times within a predetermined period; the voice command determination step determines whether the recognized utterance is a voice command for saving a still image of the photographed data; In the operation step, if the predetermined voice command is detected by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more in the voice command determination step, a still image at the time when the predetermined voice command is detected is saved; and if the predetermined voice command is detected by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the second threshold or more and less than the first threshold multiple times within a predetermined period, a still image at the time when the first utterance of the multiple detected utterances is saved. A voice operation method executed by a voice operation control device.

6. A voice command determination step of recognizing an utterance by a user and determining whether the recognized utterance is a preset voice command; a voice command receiving step of receiving a received voice command when it is determined in the voice command determining step that the predetermined voice command has been uttered; a photographic data acquisition step of acquiring photographic data photographed by a camera that photographs video; an operation step of storing the photographing data acquired in the photographing data acquisition step based on the voice command for storing the photographing data accepted in the voice command acceptance step; Including, the voice command determination step determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that an utterance matching a first threshold or more with the predetermined voice command has been detected, and determines that the recognized utterance is the predetermined voice command when a matching rate of the recognized voice from the received utterance indicates that the utterance is an utterance that is equal to or greater than a second threshold indicating a matching rate lower than the first threshold and is less than the first threshold, and that has been detected multiple times within a predetermined period; the voice command determination step determines whether the recognized utterance is a voice command for starting photography; In the operation step, if the predetermined voice command is detected by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the predetermined voice command by a first threshold or more in the voice command determination step, recording of the photographed data is started based on the time point at which the predetermined voice command was detected; and if the predetermined voice command is detected by detecting an utterance in which a matching rate of the recognized voice from the received utterance matches the second threshold or more and is less than the first threshold multiple times within a predetermined period, recording of the photographed data is started based on the time point at which the first utterance of the multiple detected utterances was detected. A voice operation method executed by a voice operation control device.

Images