Voice output device

Abstract

To provide a voice output device which can provide an appropriate voice service.SOLUTION: A voice interaction unit 42 determines a state of a driver represented by whether his or her driving load is high or not, whether he or she is listening to voice of traffic information or not, and whether he or she is talking with another crew or not. When a determination result indicates that his or her driving load is high, the voice interaction unit 42 stops output of voice or reduces the number of characters of the voice until the determination result indicates that his or her driving load is low. When he or she is listening to the voice of traffic information or when he or she is talking with another crew, the voice interaction unit 42 stops output of voice.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an audio output device. [Background technology]

[0002] A voice service has been proposed that responds to a driver's speech with a voice (Patent Document 1). Also proposed is a voice service that conveys warnings, alerts, notifications, etc. to the driver by voice inside the vehicle.

[0003] However, conventional voice services have the problem that they cannot provide appropriate voice services because they are provided without understanding the driver's state. For example, if a voice service is provided when the driver is concentrating on driving operations under high driving load or when the driver is talking to other passengers, the following problems (1) to (3) are likely to occur.

[0004] (1) There is a possibility that the driver may not be able to hear or fully understand the contents of the voice service. (2) Some people may find voice services annoying when they are under heavy driving load or while talking to a passenger. (3) There is a possibility that the driver's attention may be drawn to the conversation when they should be concentrating on driving. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-98844 Summary of the Invention [Problem to be solved by the invention]

[0006] The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an audio output device that can provide an appropriate audio service. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, the audio output device according to the present invention has the following features. An audio output device mounted on a vehicle, the audio output device comprising: an audio output unit that outputs audio; and an audio control unit that controls the audio output from the audio output unit, a state determination unit for determining the state of the driver, the voice control unit changes at least one of an output timing of the voice, a number of characters of the voice, an output speed of the voice, and a volume of the voice, without changing the content of the voice, according to the determination result of the state determination unit. It is an audio output device. [Effects of the Invention]

[0008] The audio output device according to the present invention has the effect of being able to provide an appropriate audio service.

[0009] The present invention has been briefly described above. The details of the present invention will become clearer by reading the following detailed description of the invention (hereinafter referred to as "embodiments") with reference to the accompanying drawings. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing an embodiment of a vehicle dialogue system as a voice output device of the present invention. [Figure 2] FIG. 2 is an explanatory diagram for explaining the operation of the vehicle dialogue system shown in FIG. [Figure 3] FIG. 3 is a diagram showing an example of a display on the display shown in FIG. [Figure 4] FIG. 4 is a diagram showing an example of a display on the display shown in FIG. [Figure 5] FIG. 5 is a flowchart for explaining the operation of the vehicle dialogue system shown in FIG. [Figure 6] FIG. 6 is a flowchart for explaining the operation of the vehicle dialogue system shown in FIG. [Figure 7]FIG. 7 is a flowchart for explaining the operation of the vehicle dialogue system in the determination process shown in FIG. [Figure 8] FIG. 8 is a flowchart for explaining the operation of the vehicle dialogue system in the determination process shown in FIG. [Figure 9] FIG. 9 is a flowchart for explaining the operation of the vehicular dialogue system in the change process shown in FIG. [Figure 10] FIG. 10 is a block diagram of a vehicle dialogue system according to another embodiment. [Figure 11] FIG. 11 is a block diagram of a vehicle dialogue system according to another embodiment. [Figure 12] FIG. 12 is a block diagram of a vehicle dialogue system according to another embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Specific embodiments of the present invention will be described below with reference to the accompanying drawings.

[0012] The vehicle dialogue system 1 of this embodiment is a system that is mounted on a vehicle and that dialogues with the driver using a dialogue type AI (Artificial Intelligence) 10. The dialogue type AI 10 is configured, for example, by ChatGPT, and when input information S1 made up of text data is input, it outputs response information S2 made up of text data.

[0013] The vehicle dialogue system 1 includes a microphone 2 as a voice input unit, a communication module 3, a microcomputer 4 (hereinafter abbreviated as "microcomputer 4"), a speaker 5 as a voice output unit, a display 6, and a ROM (Read Only Memory) 7. The microphone 2 inputs the voice uttered by the driver to the microcomputer 4. The communication module 3 is for communicating with the interactive AI 10 via an Internet communication network (not shown), and is composed of a circuit, an antenna, etc. for connecting to the Internet communication network. In this embodiment, the communication module 3, the microcomputer 4, and a ROM 7 (described later) are mounted on the same control board 100.

[0014] The microcomputer 4 has a memory such as a RAM (Random Access Memory) or a ROM, and a CPU (Central Processing Unit) that operates according to a program stored in the memory, and controls the entire vehicle dialogue system 1.

[0015] The microcomputer 4 has a voice recognition unit 41, a voice dialogue unit 42, a voice synthesis unit 44, and a drawing processing unit 45. The voice recognition unit 41 converts the voice input by the microphone 2 into text data and inputs it to the voice dialogue unit 42. The voice dialogue unit 42 inputs the text data converted by the voice recognition unit 41 to the interactive AI 10 as input information S1.

[0016] Vehicle information S3, person information S4, ADAS (Advanced Driving Assistant System) information S5, and audio information S6 are also input to the voice dialogue unit 42. The microcomputer 4 is connected to sensors and devices mounted on the vehicle via a communication network provided in the vehicle, such as a CAN (Controller Area Network). The vehicle information S3 is information indicating the state of the vehicle obtained from sensors and devices mounted on the vehicle.

[0017] The person information S4 is the detection result from the driver monitor that detects the driver's state (face direction, line of sight) based on an image of the driver's face. The ADAS information S5 is the detection result from the ADAS that detects the distance to the vehicle ahead and the presence or absence of an object of attention. The audio information S6 is information from the audio equipment installed in the vehicle.

[0018] The voice dialogue unit 42 is also connected to an in-vehicle device 11 mounted on the vehicle, and can control the in-vehicle device 11. The in-vehicle device 11 may be, for example, an air conditioner mounted on the vehicle, a motor for opening and closing windows, a headlight, an ECU (Electronic Control Unit) for controlling an ACC (Adaptive Cruise Control) function, and the like.

[0019] The voice dialogue unit 42 determines the driver's state, such as the driver's driving load, whether the driver is listening to audio traffic information, and whether the driver is talking to other passengers, and changes the voice output timing, the number of characters in the voice, and the voice output speed according to the determination result, without changing the content of the voice. An example of this will be described with reference to Fig. 2.

[0020] The voice dialogue unit 42 detects whether the turn signal is on or off based on the vehicle information S3. When outputting a voice, if the voice dialogue unit 42 detects that the turn signal is on, it infers that the vehicle is turning right or left or changing lanes, determines that the driving load is high, and puts the voice dialogue unit 42 into a standby state. The voice dialogue unit 42 does not output a voice while the turn signal remains on and the driving load remains high. Thereafter, the voice dialogue unit 42 immediately outputs a voice when the turn signal is turned off and the driving load becomes low.

[0021] The voice dialogue unit 42 detects the vehicle speed based on the vehicle information S3. When outputting the voice, if the vehicle speed is, for example, 60 km / h or higher, the voice dialogue unit 42 presumes that the vehicle is traveling on an expressway, determines that the driving load is high, and outputs a voice that is shortened to, for example, 50 characters or less. If the vehicle speed is less than 60 km / h, the voice dialogue unit 42 presumes that the vehicle is traveling on an ordinary road, determines that the driving load is low, and does not limit the number of characters in the voice output.

[0022] The voice dialogue unit 42 detects the distance between the vehicle and the preceding vehicle based on the ADAS information S5. When outputting voice, if the distance between the vehicle and the preceding vehicle is short, the voice dialogue unit 42 determines that the driving load is high, and outputs a voice that is shortened to, for example, 50 characters or less. If the distance between the vehicle and the preceding vehicle is long, the voice dialogue unit 42 determines that the driving load is low, and does not limit the number of characters in the voice output.

[0023] The voice dialogue unit 42 detects whether there is an object of attention, such as a pedestrian about to cross the road, based on the ADAS information S5. When outputting a voice, if the voice dialogue unit 42 detects that there is an object of attention, it determines that the driver needs to pay attention to their surroundings and that the driving load is high. If the voice dialogue unit 42 determines that the driving load is high, it puts the voice output into a standby state. The voice dialogue unit 42 does not output a voice while the object of attention continues to exist and the driving load remains high. Thereafter, when there is no object of attention and the driving load becomes low, the voice dialogue unit 42 immediately outputs a voice.

[0024] The voice dialogue unit 42 detects the direction of the driver's face based on the person information S4. When the voice dialogue unit 42 detects that the driver's face is frequently turning from side to side while outputting voice, it presumes that the driver is checking left and right at an intersection with poor visibility, and determines that the driving load is high. When it determines that the driving load is high, the voice dialogue unit 42 puts the voice output into a standby state. The voice dialogue unit 42 does not output voice while the driver's face is frequently turning from side to side and the driving load remains high. Thereafter, the voice dialogue unit 42 immediately outputs voice when the driver's face is stably facing forward and the driving load becomes low.

[0025] The voice dialogue unit 42 detects the driver's line of sight based on the person information S4. When outputting a voice, if the voice dialogue unit 42 detects that the driver is looking at the rearview mirror or side mirror, it infers that the driver is changing lanes or merging, and determines that the driving load is high. When it determines that the driving load is high, the voice dialogue unit 42 puts the voice output into a standby state. The voice dialogue unit 42 does not output a voice while the driver continues to look at the rearview mirror or side mirror continuously or intermittently, and the driving load continues to be high. Thereafter, when the driver continues not to look at the rearview mirror or side mirror for a certain period of time or more, and the driving load becomes low, the voice dialogue unit 42 immediately outputs a voice.

[0026] The voice dialogue unit 42 determines whether the driver is listening to the audio of the traffic information based on the audio information S6. If the radio setting frequency included in the audio information S6 is the frequency (AM 11620 kHz) that broadcasts traffic information, the voice dialogue unit 42 determines that the driver is listening to the audio of the traffic information. Because traffic information is repeated on the radio at a maximum interval of 120 seconds, when the voice dialogue unit 42 determines that the driver is listening to the audio of the traffic information, it waits for, for example, 120 seconds before outputting the audio. After a predetermined time has elapsed, the voice dialogue unit 42 outputs the audio.

[0027] The voice dialogue unit 42 may change the timing of voice output, the number of voice characters, and the voice output speed in response to the driver's command via the voice content input to the microphone 2, as well as the driver's state. In this embodiment, for example, when the driver requests that the voice content be output repeatedly, such as "Say it again," the voice dialogue unit 42 slows down the voice output speed and outputs the content that was output immediately afterwards more slowly or at an increased volume. Also, for example, when the driver requests that the voice output be stopped, such as "Please be a little quieter," the voice dialogue unit 42 puts the voice output into a standby state and starts voice output after a predetermined time.

[0028] The voice dialogue unit 42 determines whether the driver is conversing with another passenger based on the input from the microphone 2. When outputting voice, if the voice dialogue unit 42 detects that the driver is conversing with another passenger, the voice dialogue unit 42 puts the voice output into a standby state. The voice dialogue unit 42 outputs voice when the sound picked up by the microphone 2 is silent or when only one passenger is speaking.

[0029] When responding to something spoken to by the driver, even if a condition for waiting for a voice is established, the voice dialogue unit 42 may output a voice immediately without waiting for a voice if the content is a predetermined content (for example, a request to operate a device that requires an immediate response, a question about how to operate it, etc.).

[0030] When the voice dialogue unit 42 responds to what the driver has said, if a condition for waiting for a voice is established, it may immediately output a voice such as "It is dangerous now, so I will talk to you later," to inform the driver that the response is being delayed intentionally and not due to a malfunction, thereby preventing the driver from feeling anxious.

[0031] When the conditions for waiting for voice, limiting the number of characters, and slowing down the output speed occur simultaneously, the voice dialogue unit 42 may change the voice output according to the condition with the highest priority, according to a pre-set priority.

[0032] For example, the turn signal condition is set in advance as priority 1, and the speed condition as priority 2. If the conditions of the turn signal being ON and the speed being 60 km / h or more are met simultaneously, the voice dialogue unit 42 gives priority to the condition when the turn signal is ON and does not output voice while the turn signal ON condition is met. If the turn signal is turned OFF and the condition of the speed being 60 km / h or more is still met, the character limit becomes effective.

[0033] While the voice dialogue unit 42 is outputting voice from the speaker 5, it outputs a display request to the drawing processing unit 45 to display character C on the display 6. The display 6 is disposed on the instrument panel between the driver's seat and the passenger seat. The drawing processing unit 45 outputs to the display 6 an image that appears to show character C speaking the voice output from the speaker 5.

[0034] 3 and 4, examples of display on the display 6 will be described. As shown in Fig. 3, when the driver utters, for example, "Find a nearby restaurant," if the condition for entering a voice waiting state is met (turn signal ON), the voice dialogue unit 42 displays character C on the display 6 and outputs a voice saying, "It's dangerous now, so I'll talk to you later." Thereafter, the voice dialogue unit 42 temporarily erases character C from the display 6, and then, if the condition for canceling the voice waiting state is met (turn signal OFF), it displays character C on the display 6 again and outputs a voice response to the driver's utterance.

[0035] 4, after the driver sets a destination in the navigation device, the voice dialogue unit 42 outputs "The weather around the destination is sunny" from the speaker 5 and displays character C on the display 6. If there is no further speech from the driver for a predetermined period of time, the voice dialogue unit 42 temporarily erases the display of character C. The voice dialogue unit 42 may also reduce the display of character C and switch it to a simplified display. If the driver then speaks, the voice dialogue unit 42 causes character C to be displayed on the display 6 again.

[0036] Next, the operation of the vehicle dialogue system 1 outlined above will be described with reference to the flowcharts of Figures 5 and 6. The microcomputer 4 acquires vehicle information S3, person information S4, ADAS information S5, audio information S6, and input from the microphone 2 (Sp1 to Sp5). When the driver speaks (Y in Sp6), a voice recognition process is performed to convert the driver's voice into text data (Sp7). Next, the microcomputer 4 performs a determination process to determine the driver's state and the content of the driver's utterance (Sp8).

[0037] The operation of the vehicular dialogue system 1 in this determination process will be described in detail with reference to the flowcharts of Figures 7 and 8. First, the microcomputer 4 checks the vehicle information S3 acquired in Sp1 (Sp801). If the vehicle information S3 meets a condition for limiting the number of characters (vehicle speed of 60 km / h or more in the example of Figure 2) (Y in Sp802), the microcomputer 4 turns on a character number limit flag (Sp803). If the vehicle information S3 meets a condition for putting voice into a voice output standby state (turn signal ON in the example of Figure 2) (Y in Sp804), the microcomputer 4 turns on a voice output standby flag (vehicle) (Sp805).

[0038] If the vehicle information S3 satisfies the conditions for changing the audio output speed (Y in Sp806), the microcomputer 4 turns on the audio output speed change flag (vehicle) (Sp807). The microcomputer 4 determines whether the processes in Sp802 to Sp807 have been executed for all data in the vehicle information S3 (Sp808).

[0039] After executing the processes of Sp802 to Sp807 for all data of the vehicle information S3, the microcomputer 4 performs the same processes for the ADAS information S5, the person information S4, the audio information S6, and the microphone input.

[0040] In detail, the microcomputer 4 checks the ADAS information S5, person information S4, audio information S6, and microphone input acquired in Sp1 (Sp809, Sp817, Sp825, Sp833). If the ADAS information S5, person information S4, audio information S6, and microphone input meet the conditions for limiting the number of characters (Y in Sp810, Sp818, Sp826, Sp834), the microcomputer 4 turns on the character limit flag (Sp811, Sp819, Sp827, Sp835). If the ADAS information S5, person information S4, audio information S6, and microphone input are conditions that put audio into an output waiting state (Y in Sp812, Sp820, Sp828, and Sp836), the microcontroller 4 turns on the audio output waiting flags (vehicle), (ADAS), (person), (audio), and (microphone) (Y in Sp813, Sp821, Sp829, and Sp837).

[0041] If the ADAS information S5, person information S4, audio information S6, and microphone input are conditions for changing the audio output rate (Y in Sp814, Sp822, Sp830, and Sp838), the microcomputer 4 turns on the audio output rate change flags (vehicle), (ADAS), (person), (audio), and (microphone) (Sp815, Sp823, Sp831, and Sp839). The microcomputer 4 determines whether or not the processes in Sp810 to Sp815, Sp818 to Sp823, and Sp826 to Sp831 have been executed for all data in the ADAS information S5, person information S4, and audio information S6 (Y in Sp816, Sp824, and Sp832).

[0042] After performing the above determination process (Sp8), the microcomputer 4 performs priority processing (Sp9 in FIG. 5). In the priority processing, the microcomputer 4 determines the priority of the character count flag, voice output wait flag, and voice output speed change flag that are turned ON, for example, according to a predetermined priority order, and turns OFF flags with lower priority. If the character count limit flag is ON (Y in Sp10), the microcomputer 4 generates a prompt that further adds text data such as "Please respond to the driver's utterance in 50 characters or less" to the text data of the driver's utterance converted in Sp7 (Sp11), and then proceeds to Sp13.

[0043] On the other hand, if the character limit flag is OFF (N in Sp10), the microcomputer 4 generates the text data of the driver's utterance converted in Sp7 as a prompt (Sp12), and then proceeds to Sp 13. The prompts generated in Sp11 and Sp12 may further include vehicle information such as the vehicle speed and the state of the in-vehicle device 11.

[0044] In Sp13, the microcomputer 4 functions as an input unit and transmits the prompt generated in Sp11 or Sp12 to the interactive AI 10. When the microcomputer 4 receives response information S2 from the interactive AI 10 (Y in Sp14), it determines whether the voice output waiting flag and voice output speed change flag are on and whether the voice output method needs to be changed from normal (Sp15). If no change is necessary (N in Sp15), the microcomputer 4 outputs and reads the response information S2 (text data) from the interactive AI 10 from the speaker 5 in the normal way (Sp19).

[0045] If a change is necessary (Y in Sp15), the microcomputer 4 determines whether the voice output waiting flag is ON (Sp16). If the voice output waiting flag is ON (Y in Sp16), the microcomputer 4 outputs a voice message to notify the user that it is waiting for a response, such as "It's dangerous now, so I'll talk to you later" (Sp17), and then performs processing to change the voice output method (Sp18), before proceeding to Sp20.

[0046] When the vehicle dialogue system 1 is turned off (Y in Sp20), the microcomputer 4 ends the process. If the vehicle dialogue system 1 is not turned off (N in Sp20), the microcomputer 4 returns to Sp1 again.

[0047] Next, the process of changing the audio output method in Sp18 will be described with reference to Fig. 9. If the audio output wait flag is OFF (N in Sp1801), the microcomputer 4 immediately proceeds to Sp1804. If the audio output wait flag is ON (Sp1801), the microcomputer 4 checks the information that turned ON the audio wait output flag from among the vehicle information S3, ADAS information S5, person information S4, audio information S6, and microphone input (Sp1802). If the condition for putting audio into an output wait state continues based on the checked information (Y in Sp1803), the microcomputer 4 returns to Sp1802 again. On the other hand, if the condition for putting audio into an output wait state based on the checked information is not met (N in Sp1803), the microcomputer 4 proceeds to Sp1804.

[0048] In Sp1804, the microcomputer 4 determines whether the audio output speed change flag is ON. If the audio output speed change flag is ON (Y in Sp1804), the microcomputer 4 changes the audio output speed and reads out the response information S2 from the compatible AI 10 (Sp1805), and then proceeds to Sp1807. If the audio output speed change flag is OFF (N in Sp1804), the microcomputer 4 reads out the response information S2 from the compatible AI 10 at the normal speed (Sp1806), and then proceeds to Sp1807. Thereafter, the microcomputer 4 turns off the audio output wait flag and the audio output speed change flag (Sp1807, Sp1808), and then ends the change processing.

[0049] On the other hand, if there is no utterance from the driver (N in Sp6 in FIG. 5), the microcomputer 4 proceeds to Sp21 in FIG. 6. In Sp21, the microcomputer 4 determines whether there is a voice notification to the driver (such as an alarm or a greeting when getting in). If there is no voice notification to the driver (N in Sp21), the microcomputer 4 returns to Sp1 in FIG. 5.

[0050] If there is a voice notification to the driver (Y in Sp21 of FIG. 6), the microcomputer 4 performs a determination process to determine the driver's state and the content of the driver's utterance (Sp8). The determination process of Sp8 has already been described, so a detailed description will be omitted here. The microcomputer 4 determines whether the voice notification to the driver is a voice notification that needs to be created by the interactive AI 10 (Sp23). If it is a voice notification that needs to be created by the interactive AI 10 (Y in Sp23), the microcomputer 4 executes Sp10 to Sp16, Sp18, and Sp19. Sp10 to Sp16, Sp18, and Sp19 have already been described, so a detailed description will be omitted here.

[0051] If the voice notification does not need to be created by the interactive AI 10 (N in Sp23), the microcontroller 4 retrieves the template stored in the internal memory that corresponds to the notification (Sp24) and proceeds to Sp15 to output it as voice.

[0052] According to the above-described embodiment, the microcomputer 4 determines the driver's state and, depending on the determination result, changes the voice output timing, the number of characters, and the voice output speed without changing the voice content. This allows the voice to be output at the voice output timing, the number of characters, and the voice output speed that match the driver's state, making it possible to provide an appropriate voice service.

[0053] According to the above-described embodiment, when the microcomputer 4 determines that the driving load is high, it stops outputting audio until it determines that the driving load is low. This stops outputting audio to a driver who is in a high driving load state, thereby reducing the load on the driver, and thus providing a more appropriate audio service.

[0054] According to the above-described embodiment, the microcomputer 4 reduces the number of characters in the voice when the driving load is determined to be high, and increases the number of characters in the voice when the driving load is determined to be low. This reduces the amount of information in the voice for a driver who is in a high driving load, thereby reducing the load on the driver, and thus providing a more appropriate voice service.

[0055] According to the above-described embodiment, when the number of characters is to be reduced based on the result of the determination of the driver's state, the microcomputer 4 creates a prompt to reduce the number of characters in the response information to the driver's utterance and inputs the created prompt to the interactive AI 10. This allows the interactive AI 10 to respond appropriately to the driver's utterance.

[0056] According to the above-described embodiment, the voice output to the driver who is listening to the traffic information can be stopped, thereby reducing the burden on the driver, and therefore, a more appropriate voice service can be provided.

[0057] According to the above-described embodiment, audio output can be stopped for a driver who is talking to other passengers, thereby reducing the burden on the driver and providing a more appropriate audio service.

[0058] According to the above-described embodiment, the output timing, the number of characters in the voice, and the voice output speed are changed according to the contents of the driver's voice input to the microphone 5. This makes it possible to output voice in accordance with the driver's requests, and to provide a more appropriate voice service.

[0059] The present invention is not limited to the above-described embodiments, and can be appropriately modified, improved, etc. Furthermore, the material, shape, size, number, location, etc. of each component in the above-described embodiments are arbitrary and not limited as long as they can achieve the present invention.

[0060] According to the above-described embodiment, in the vehicle dialogue system 1 shown in Fig. 1, the dialogue AI 10 communicates with the vehicle dialogue system 1 via the Internet communication network, but this is not limited to this. As in the vehicle dialogue system 1B shown in Fig. 10, the dialogue AI 10B consisting of a microcomputer may be mounted on the control board 100. The vehicle dialogue system 1B shown in Fig. 10 allows dialogue even in a poor communication environment.

[0061] 1 and 10, the microcomputer 4 functions as a voice recognition unit, but this is not limiting. As in the vehicle dialogue systems 1C and 1D shown in FIGS. 11 and 12, the microcomputer 4 may be configured to communicate with a server 12 that functions as a voice recognition unit.

[0062] In this case, the microcomputer 4 transmits the voice input from the microphone 2 to the server 12. The server 12 converts the received voice into text data. The server 12 also transmits the text data of the voice to the microcomputer 4. This eliminates the need for the microcomputer 4 to have a voice recognition unit 41, thereby reducing the processing load.

[0063] 11 and 12, the microcomputer 4 does not have the speech recognition unit 41, but it may have the speech recognition unit 41. In this case, the microcomputer 4 converts part of the speech into text data in the speech recognition unit 41, and converts the rest of the speech into text data in the server 12. In this case, the processing load on the microcomputer 4 can be reduced compared to when all speech recognition is performed by the microcomputer 4.

[0064] According to the above-described embodiment, the voice dialogue unit 42 changes the timing, number of characters, and speed of voice output in accordance with the driver's state and the contents of the driver's speech, but this is not limiting. The volume may also be changed.

[0065] According to the above-described embodiment, the voice output device of the present invention is applied to the vehicle dialogue system 1 that responds to the driver's utterances, but the present invention is not limited to this. It is also conceivable that the voice output device of the present invention is applied to an in-vehicle device that issues warnings and the like by voice.

[0066] Here, the features of the above-described embodiments of the vehicle dialogue system according to the present invention will be briefly summarized and listed below in [1] to [7].

[0067] [1] An audio output device (1) mounted on a vehicle, the audio output device (1) including an audio output unit (5) that outputs audio, and an audio control unit (42) that controls the audio output from the audio output unit (5), a state determination unit (42) for determining the state of the driver; The voice control unit (42) changes at least one of the output timing of the voice, the number of characters of the voice, the output speed of the voice, and the volume of the voice, without changing the content of the voice, according to the determination result of the state determination unit (42). Audio output device (1).

[0068] According to the voice output device (1) having the configuration [1] above, voice can be output at a voice output timing, number of characters, and output speed that are suited to the driver's condition, thereby providing an appropriate voice service.

[0069] [2] In the audio output device (1) described in [1], The state determination unit (42) determines a driving load of the driver, When the driving load is determined to be high, the voice control unit (42) stops outputting the voice until the driving load is determined to be low. Audio output device (1).

[0070] According to the audio output device (1) having the configuration [2] above, audio output can be stopped for a driver who is under high driving load, thereby reducing the load on the driver, and therefore, more appropriate audio services can be provided.

[0071] [3] In the audio output device (1) described in [1], The state determination unit (42) determines a driving load of the driver, The voice control unit (42) reduces the number of characters in the voice when the determination result indicates that the driving load is high, and increases the number of characters in the voice when the determination result indicates that the driving load is low. Audio output device (1).

[0072] According to the audio output device (1) having the configuration [3] above, the amount of audio information can be reduced for a driver who is under high driving load, thereby reducing the load on the driver, and therefore, more appropriate audio services can be provided.

[0073] [4] In the audio output device (1) described in [1], a voice input unit (2) for inputting the voice uttered by the driver; a voice recognition unit (41) that converts the voice input by the voice input unit (2) into text data; an input unit (42) that inputs input information including the text data converted by the voice recognition unit (41) to an interactive AI (10); a voice synthesis unit (44) that converts response information consisting of text data output from the interactive AI (10) in response to input of the input information into voice, when the number of characters is to be reduced based on the determination result of the driving state, the voice control unit (42) creates a prompt to reduce the number of characters of the response information for the text data converted by the voice recognition unit (41), and controls the input unit to input the prompt as the input information to the interactive AI; The voice output unit (5) outputs the voice converted by the voice synthesis unit (44). Audio output device (1).

[0074] According to the voice output device (1) configured as described above in [4], it is possible to use the conversational AI (10) to respond appropriately to the driver's utterances.

[0075] [5] In the audio output device (1) described in [1], The state determination unit (42) determines whether the driver is listening to audio of traffic information, When the voice control unit (42) determines that the driver is listening to the audio of the traffic information, it waits for a predetermined time and then outputs the audio. Audio output device (1).

[0076] According to the audio output device (1) having the configuration [5] above, audio output can be stopped for the driver who is listening to traffic information, thereby reducing the burden on the driver, and therefore, more appropriate audio services can be provided.

[0077] [6] In the audio output device (1) described in [1], The state determination unit (42) determines whether the driver is in a conversation with another passenger, When the determination result indicates that the driver is in a conversation with the other passenger, the voice control unit (42) stops outputting the voice until the determination result indicates that the driver is not in a conversation with the other passenger. Audio output device (1).

[0078] According to the configuration [6] above, audio output can be stopped for a driver who is talking to another passenger, thereby reducing the burden on the driver and providing a more appropriate audio service.

[0079] [7] In the audio output device (1) described in [1], a voice input unit (2) for inputting the voice uttered by the driver, The voice control unit (42) changes at least one of the output timing of the voice, the number of characters of the voice, the output speed of the voice, and the volume of the voice, in accordance with the voice content input by the voice input unit (2), without changing the content of the voice. Audio output device (1).

[0080] According to the configuration [7] above, it is possible to output audio in accordance with the driver's request, and to provide a more appropriate audio service. [Explanation of symbols]

[0081] 1. Vehicle dialogue system (voice output device) 2 Microphone (audio input) 5. Speaker (audio output section) 10 Conversational AI 41 Voice Recognition Unit 42 Voice dialogue unit (voice control unit, state determination unit, input unit) 44 Speech synthesis unit

Claims

1. An audio output device mounted on a vehicle, the audio output device comprising: an audio output unit that outputs audio; and an audio control unit that controls the audio output from the audio output unit, a state determination unit for determining the state of the driver, the voice control unit changes at least one of an output timing of the voice, a number of characters of the voice, an output speed of the voice, and a volume of the voice, without changing the content of the voice, according to the determination result of the state determination unit. Audio output device.

2. 2. The audio output device according to claim 1, The state determination unit determines a driving load of the driver, When the driving load is determined to be high, the voice control unit stops outputting the voice until the driving load is determined to be low. Audio output device.

3. 2. The audio output device according to claim 1, The state determination unit determines a driving load of the driver, the voice control unit reduces the number of characters in the voice when the determination result indicates that the driving load is high, and increases the number of characters in the voice when the determination result indicates that the driving load is low. Audio output device.

4. 2. The audio output device according to claim 1, a voice input unit for inputting a voice uttered by the driver; a voice recognition unit that converts the voice input by the voice input unit into text data; an input unit that inputs input information including the text data converted by the speech recognition unit to an interactive AI; a speech synthesis unit that converts response information consisting of text data output from the interactive AI in response to input of the input information into speech, When the number of characters is reduced based on the determination result of the driving state, the voice control unit creates a prompt to reduce the number of characters of the response information for the text data converted by the voice recognition unit, and controls the input unit to input the prompt as the input information to the interactive AI; the audio output unit outputs the audio converted by the audio synthesis unit. Audio output device.

5. 2. The audio output device according to claim 1, the state determination unit determines whether the driver is listening to audio of traffic information; When the voice control unit determines that the driver is listening to the audio of the traffic information, the voice control unit outputs the audio after waiting for a predetermined time. Audio output device.

6. 2. The audio output device according to claim 1, The state determination unit determines whether the driver is in a conversation with another passenger, When the determination result indicates that the driver is in a conversation with the other occupant, the voice control unit stops outputting the voice until the determination result indicates that the driver is not in a conversation with the other occupant. Audio output device.

7. 2. The audio output device according to claim 1, a voice input unit for inputting a voice uttered by the driver, the voice control unit changes at least one of an output timing of the voice, a number of characters of the voice, an output speed of the voice, and a volume of the voice, in accordance with the voice content input by the voice input unit, without changing the content of the voice; Audio output device.

Images