Speech recognition device

Abstract

The invention provides a voice recognition device, which solves the technical problem that a user can easily know whether the voice input cannot be recognized originally or a function corresponding to the voice input cannot be utilized under the condition that the voice input from the user is not accepted. A voice recognition device (20) is provided with a control unit that recognizes a voice input from an occupant of a vehicle (12), controls a function corresponding to the recognized voice input, and controls the function corresponding to the recognized voice input when the voice input cannot be recognized and when the voice input is recognized and the function cannot be utilized. And outputting different notifications.

Description

Technical Field

[0001] The present disclosure relates to a speech recognition device. Background Art

[0002] Patent document 1 discloses a device having a voice recognition unit. The voice recognition unit determines whether the voice information of the passenger acquired by the microphone in the vehicle contains the specified voice information. If the specified voice information is contained, the ignition switch is turned on. If the specified voice information is not contained, the ignition switch is not turned on.

[0003] Prior Art Literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2021-107192 Summary of the invention

[0006] Problems to be solved by the invention

[0007] In conventional devices, when a voice input from a user is not accepted, the user does not know whether the voice input cannot be recognized in the first place or the function corresponding to the voice input cannot be used.

[0008] The purpose of the present disclosure is to allow the user to easily know whether the voice input cannot be recognized in the first place or the function corresponding to the voice input cannot be used when the voice input from the user is not accepted.

[0009] Methods for solving problems

[0010] The voice recognition device involved in the present disclosure includes a control unit, which recognizes voice input from a vehicle occupant and controls a function corresponding to the recognized voice input, and the control unit outputs different notifications when the voice input cannot be recognized and when the voice input is recognized but the function is not available.

[0011] Effects of the Invention

[0012] According to the present disclosure, when a voice input from a user is not accepted, the user can easily know whether the voice input cannot be recognized in the first place or the function corresponding to the voice input cannot be used. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a diagram showing the configuration of a system according to an embodiment of the present disclosure.

[0014] Figure 2 It is a block diagram showing the structure of a speech recognition device according to an embodiment of the present disclosure.

[0015] Figure 3 This is a table showing an example of definition data related to the embodiment of the present disclosure.

[0016] Figure 4 It is a flowchart showing the operation of the speech recognition device involved in the embodiment of the present disclosure.

[0017] Figure 5 This is a table showing an example of data stored in a database of the server device according to the embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] Hereinafter, one embodiment of the present disclosure will be described with reference to the drawings.

[0019] In each of the drawings, the same or corresponding parts are denoted by the same reference numerals. In the description of the present embodiment, the description of the same or corresponding parts will be appropriately omitted or simplified.

[0020] Reference Figure 1 , the structure of the system 10 involved in this embodiment is described.

[0021] The system 10 according to the present embodiment includes a speech recognition device 20 and a server device 30 . The speech recognition device 20 can communicate with the server device 30 via a network 40 .

[0022] The speech recognition device 20 is a computer having a speech recognition function and mounted on the vehicle 12. The speech recognition device 20 is used by a user 11. The user 11 is a passenger of the vehicle 12.

[0023] The server device 30 is a computer that is installed in a data center or other facilities and belongs to a cloud computing system or other computing systems. The server device 30 is operated by a business operator that provides services such as web services.

[0024] The vehicle 12 is any type of vehicle, such as a gasoline vehicle, a diesel vehicle, a hydrogen vehicle, a HEV, a PHEV, a BEV, or a FCEV. "HEV" is an abbreviation for a hybrid electric vehicle. "PHEV" is an abbreviation for a plug-in hybrid electric vehicle. "BEV" is an abbreviation for a battery electric vehicle. "FCEV" is an abbreviation for a fuel cell electric vehicle. The vehicle 12 can be driven by the user 11, or the driving can be automated at any level. The level of automation is, for example, any level from level 1 to level 5 in the SAE classification. "SAE" is an abbreviation for the Society of Automotive Engineers. The vehicle 12 can be a dedicated MaaS vehicle. "MaaS" is an abbreviation for Mobility as a Service.

[0025] The network 40 includes the Internet, at least one WAN, at least one MAN, or any combination thereof. "WAN" is short for wide area network. "MAN" is short for metropolitan area network. The network 40 may also include at least one wireless network, at least one optical network, or any combination thereof. The wireless network is, for example, an ad hoc network, a cellular network, a wireless LAN, a satellite communication network, or a terrestrial microwave network. "LAN" is short for local area network.

[0026] Reference Figure 1 , an overview of this embodiment is described.

[0027] The voice recognition device 20 recognizes the voice input from the user 11 and controls the function corresponding to the recognized voice input. However, when the voice recognition device 20 cannot recognize the voice input, it does not control any function and outputs a third notification. When the function corresponding to the recognized voice input cannot be used even if the voice recognition device 20 recognizes the voice input, it does not control the function and outputs a second notification different from the third notification. That is, the voice recognition device 20 outputs different notifications when it cannot recognize the voice input and when it recognizes the voice input and the function cannot be used.

[0028] According to the present embodiment, when the voice input from the user 11 is not accepted, the user 11 can easily know whether the voice input cannot be recognized in the first place or the function corresponding to the voice input cannot be used.

[0029] In this embodiment, when the speech recognition device 20 recognizes the speech input from the user 11, it refers to the following Figure 3 The usability of the function corresponding to the voice input is determined by using the definition data 50 that defines the plurality of functions and the usability of each function as shown. Figure 3 As shown, the definition data 50 may be data that defines whether each function is usable or not according to the state of the vehicle 12. Figure 3 As shown, the definition data 50 may also include data defining the reason for the unavailability of a function that is unavailable among the multiple functions. The voice recognition device 20 may also include in the second notification a description of the reason for the function corresponding to the voice input and defined by the definition data 50 when the voice input is recognized and the function corresponding to the voice input is unavailable. In addition, the voice recognition device 20 may also send data identifying the vehicle model of the vehicle 12 and data indicating the function corresponding to the voice input to the server device 30 when the voice input is recognized and the function corresponding to the voice input is unavailable. The definition data 50 may also be different for each vehicle model, and further, may be different for each year or each grade. Although the definition data 50 is stored in the voice recognition device 20 in the present embodiment, it may also be stored in the server device 30 or an external storage device.

[0030] exist Figure 3In the example shown, the definition data 50 is constructed as a table including four columns: function, state of the vehicle 12, availability, and reason. In the function column, controllable functions and uncontrollable functions are defined according to the voice input recognized by the voice recognition device 20 mounted on the vehicle 12. For example, in the function column, No. 1 "search destination" to No. 5 "turn on the TV" are included as functions corresponding to the voice input. In the vehicle 12 state column, the state of the vehicle 12 is defined. In the availability column, the availability of each function corresponding to the state of the vehicle 12 is defined. In the reason column, when the corresponding field in the availability column is "not available", the reason why the function defined in the corresponding field in the function column is not available is defined. For example, with respect to No. 1 "search destination" of the definition data 50, the state of the vehicle 12 is defined as "normal" and "availability" is defined as "available". Therefore, when the voice recognition device 20 recognizes the voice input "I want to go to X" from the user 11, the function of "searching for a destination" is always controlled regardless of the state of the vehicle 12. In this case, the control unit 21 causes the navigation system mounted on the vehicle 12 to search for the location X, and sets the searched X as the destination. For example, regarding No. 3 of the definition data 50 "reading weather forecast", the state of the vehicle 12 is defined as "normal", the availability is defined as "not available", and the reason is defined as "non-corresponding vehicle model". Therefore, even if the voice recognition device 20 recognizes the voice input "please tell me the weather forecast" from the user 11, the function of "reading weather forecast" is not controlled. For example, regarding No. 5 of the definition data 50 "turn on the TV", the state of the vehicle 12 is defined as "driving" and "parking", the availability in the case of "driving" is defined as "not available", the reason is defined as "not available in driving", and the availability in the case of "parking" is defined as "available". Therefore, when the voice recognition device 20 recognizes the voice input "Turn on the TV" from the user 11, the "Turn on the TV" function is not controlled when the vehicle 12 is moving, and the "Turn on the TV" function is controlled when the vehicle 12 is parked. In the latter case, the control unit 21 displays the TV program on the multimedia screen of the display mounted on the vehicle 12.

[0031] Reference Figure 2 , the structure of the speech recognition device 20 involved in this embodiment is described.

[0032] The speech recognition device 20 includes a control unit 21 , a storage unit 22 , a communication unit 23 , an input unit 24 , and an output unit 25 .

[0033] The control unit 21 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or a GPU, or a dedicated processor dedicated to specific processing. "CPU" is the abbreviation of central processing unit. "GPU" is the abbreviation of graphics processing unit. The programmable circuit is, for example, FPGA. "FPGA" is the abbreviation of field-programmable gate array. The dedicated circuit is, for example, ASIC. "ASIC" is the abbreviation of application specific integrated circuit. The control unit 21 controls the various parts of the speech recognition device 20 while performing processing related to the action of the speech recognition device 20.

[0034] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, RAM, ROM, or flash memory. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. RAM is, for example, SRAM or DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. ROM is, for example, EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. Flash memory is, for example, SSD. "SSD" is an abbreviation for solid-state drive. Magnetic storage is, for example, HDD. "HDD" is an abbreviation for hard disk drive. The storage unit 22 functions as, for example, a main storage device, an auxiliary storage device, or a super-high-speed cache memory. The storage unit 22 stores data used in the operation of the speech recognition device 20 and data obtained by the operation of the speech recognition device 20 .

[0035] The communication unit 23 includes at least one communication module. The communication module is, for example, a module corresponding to a mobile communication standard such as LTE, 4G standard, or 5G standard, or a wireless LAN communication standard such as IEEE 802.11. "LTE" is the abbreviation of Long Term Evolution. "4G" is the abbreviation of 4th generation. "5G" is the abbreviation of 5th generation. "IEEE" is the abbreviation of Institute of Electrical and Electronics Engineers. The communication unit 23 communicates with the server device 30. The communication unit 23 receives data used in the operation of the speech recognition device 20, and also sends data obtained by the operation of the speech recognition device 20.

[0036] The input unit 24 includes at least one input device. The input device is, for example, a physical key, an electrostatic capacitance key, a pointing device, a touch screen integrated with a display, a visible light camera, a depth camera, LiDAR, or a microphone. "LiDAR" is the abbreviation of light detection and ranging. The input unit 24 accepts an operation of inputting data used in the operation of the speech recognition device 20. For the input unit 24, instead of being set on the speech recognition device 20, it can also be connected to the speech recognition device 20 as an external input device. As a connection interface, an interface corresponding to a standard such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used. "USB" is the abbreviation of Universal Serial Bus. "HDMI (registered trademark)" is the abbreviation of High-Definition Multimedia Interface.

[0037] The output unit 25 includes at least one output device. The output device is, for example, a display or a speaker. The display is, for example, an LCD or an organic EL display. "LCD" is the abbreviation of liquid crystal display. "EL" is the abbreviation of electro luminescent. The output unit 25 outputs data obtained by the operation of the voice recognition device 20. For the output unit 25, instead of being set on the voice recognition device 20, it can also be connected to the voice recognition device 20 as an external output device such as a display audio. As a connection interface, an interface corresponding to a standard such as USB, HDMI (registered trademark) or Bluetooth (registered trademark) can be used.

[0038] The functions of the speech recognition device 20 are realized by executing the program involved in this embodiment by the processor as the control unit 21. That is, the functions of the speech recognition device 20 are realized by software. The program enables the computer to function as the speech recognition device 20 by causing the computer to execute the actions of the speech recognition device 20. That is, the computer functions as the speech recognition device 20 by executing the actions of the speech recognition device 20 according to the program.

[0039] The program can be pre-stored in a non-temporary computer-readable medium. The non-temporary computer-readable medium is, for example, a flash memory, a magnetic recording device, an optical disc, an optical magneto-recording medium, or a ROM. The circulation of the program is implemented, for example, by selling, transferring or lending a removable medium such as an SD card, DVD or CD-ROM that records the program. "SD" is the abbreviation for Secure Digital. "DVD" is the abbreviation for digital versatile disc. "CD-ROM" is the abbreviation for compact disc read only memory. The program can also be circulated by storing the program in a storage device of a server in advance and transmitting the program from the server to other computers. The program can also be provided as a program product.

[0040] The computer temporarily stores a program stored in a removable medium or a program transmitted from a server in a main storage device, for example. Then, in the computer, the processor reads the program stored in the main storage device, and the processor executes the processing according to the read program. The computer may also read the program directly from the removable medium and execute the processing according to the program. The computer may also sequentially execute the processing according to the received program each time the program is transmitted from the server to the computer. It is also possible not to implement the transmission of the program from the server to the computer, but to execute the processing through a so-called ASP-type service that implements functions only based on execution instructions and result acquisition. "ASP" is the abbreviation of application service provider. The program includes information for processing implemented by an electronic computer and content that is treated as a program. For example, data that is not a direct instruction to the computer but has the nature of regulating the processing of the computer is equivalent to "content treated as a program."

[0041] A part or all of the functions of the speech recognition device 20 may be realized by a programmable circuit or a dedicated circuit as the control unit 21. In other words, a part or all of the functions of the speech recognition device 20 may also be realized by hardware.

[0042] Reference Figure 4 , the operation of the speech recognition device 20 involved in this embodiment is described. The operation described below is equivalent to the control method involved in this embodiment. That is, the control method involved in this embodiment includes Figure 4 Steps S1 to S9 are shown.

[0043] When the user 11 issues a start command such as “Hey, car!” or presses a start button displayed on a screen or physically arranged, step S1 is started.

[0044] In S1 , the control unit 21 receives a voice input from the user 11 . For example, the control unit 21 receives a voice input such as “I want to go to X” or “Turn on the TV” from the user 11 via the microphone as the input unit 24 .

[0045] In S2, the control unit 21 determines whether the voice input from the user 11 can be recognized. If it can be recognized (S2-Yes), the process proceeds to S3. If it cannot be recognized (S2-No), the process proceeds to S9. For example, if the voice input "I want to go to X" can be recognized in S2, the process proceeds to S3. In addition, for example, although the part "I want to go" can be recognized in S2, if the place is not heard clearly, the process proceeds to S9.

[0046] In S3 , the control unit 21 obtains the state of the vehicle 12 . For example, the control unit 21 receives data on the speed of the vehicle 12 from a speedometer mounted on the vehicle 12 via the communication unit 23 , thereby obtaining the state of the vehicle 12 .

[0047] In S4, the control unit 21 refers to Figure 3 Definition data 50 as shown is provided to determine whether the function corresponding to the voice input recognized in S2 is available. If it is available (S4-Yes), the process proceeds to S5. If it is not available (S4-No), the process proceeds to S7. For example, when the voice input "I want to go to X" is recognized in S2, the control unit 21 will determine that the "search destination" function is available regardless of the state of the vehicle 12 obtained in S3, and the process proceeds to S5. On the other hand, when the voice input "turn on the TV" is recognized in S2 and the state of the vehicle 12 obtained in S3 is "driving", the control unit 21 determines that the "turn on the TV" function is not available, and the process proceeds to S7.

[0048] In S5, the control unit 21 controls the function determined to be available in S4 based on the voice input recognized in S2. For example, the control unit 21 controls the function of "searching for a destination" determined to be available in S4 based on the voice input of "I want to go to X" recognized in S2, thereby causing the navigation system mounted on the vehicle 12 to search for X. Next, the control unit 21 causes the navigation system to set the searched X as the destination. After S5, the process proceeds to S6.

[0049] In S6, the control unit 21 outputs a first notification. For example, when the control unit 21 causes the navigation system to set X as a destination in S5, the control unit 21 outputs a voice message "X has been set as a destination" as a first notification via a speaker as the output unit 25. For example, the control unit 21 may cause a display as the output unit 25 to display a message "X has been set as a destination" as a first notification.

[0050] After S6, the end Figure 4 The process shown.

[0051] In S7, the control unit 21 outputs a second notification. For example, based on the voice input of "Turn on the TV" recognized in S2, the control unit 21 notifies the user of the reason for the unavailability defined in the definition data 50 for the function of "Turn on the TV" determined to be unavailable in S4. Specifically, as a second notification, the control unit 21 outputs the voice "Cannot be used while driving" via the speaker as the output unit 25. For example, as a second notification, the control unit 21 may also cause the display as the output unit 25 to display the message "Cannot be used while driving". Thus, the user 11 can know that, although the voice input is recognized, the function corresponding to the voice input cannot be used. After S7, the processing enters S8.

[0052] In S8, the control unit 21 transmits data for identifying the model of the vehicle 12 and data indicating the function determined to be unavailable in S4 to the server device 30 via the communication unit 23. For example, the control unit 21 transmits data indicating the model of the vehicle 12 "AAA" and data indicating the function "turn on the TV" to the server device 30 via the communication unit 23. In addition, the control unit 21 may also transmit data indicating the date of voice input, data indicating the user ID for identifying the user 11, or data indicating the reason for unavailability. "ID" is the abbreviation of identifier.

[0053] An example of data to be stored in the database of the server device 30 is shown in Figure 5In this example, data indicating the date of voice input, user ID, vehicle model, function, and reason for unavailability sent from the control unit 21 is stored in the database of the server device 30. By accumulating the data sent from the control unit 21 in the server device 30, the operator can obtain information such as "users of vehicle model AAA have requested the function of reading weather forecast more often." As a result, the operator can know that the function is unavailable despite voice input, that is, the function is not actually installed despite the user 11's demand, and can obtain important marketing materials for product development.

[0054] After S8, the end Figure 4 The process shown.

[0055] In S9, the control unit 21 outputs a third notification. For example, as the third notification, the control unit 21 outputs a voice message “Unrecognizable. Please say it again” via the speaker as the output unit 25. Therefore, the user 11 can know that the voice input is not recognized.

[0056] After S9, the end Figure 4 The process shown.

[0057] As described above, when the control unit 21 recognizes the voice input from the user 11, it controls the function according to the recognized voice input. The control unit 21 outputs different notifications when the voice input cannot be recognized and when the voice input is recognized but the function is not available.

[0058] According to the present embodiment, when the voice input from the user 11 is not accepted, the user 11 can easily know whether the voice input cannot be recognized in the first place or the function corresponding to the voice input cannot be used.

[0059] The present disclosure is not limited to the above-mentioned embodiments. For example, two or more frames recorded in the block diagram may be merged, or one frame may be divided. Alternatively, instead of executing two or more steps recorded in the flowchart in a time series according to the description, the steps may be executed in parallel or in a different order according to the processing capability of the device executing each step or as needed. In addition, changes can be implemented within the scope of the subject matter of the present disclosure.

[0060] Explanation of symbols

[0061] 10. System;

[0062] 11. User;

[0063] 12. Vehicles;

[0064] 20. Voice recognition device;

[0065] 21. Control department;

[0066] 22. Storage

[0067] 23. Ministry of Communications;

[0068] 24. Input section

[0069] 25. Output unit;

[0070] 30. Server device;

[0071] 40. Network;

[0072] 50. Define data.

Claims

1. A speech recognition device comprising a control unit, wherein the control unit recognizes speech input from a vehicle occupant and controls a function corresponding to the recognized speech input, and wherein the control unit outputs different notifications when the speech input cannot be recognized and when the speech input is recognized but the function is unavailable.

2. The speech recognition device according to claim 1, wherein: further comprising a communication unit for communicating with the server device, When the voice input is recognized and the function is not available, the control unit transmits data for identifying the model of the vehicle and data indicating the function to the server device via the communication unit.

3. The speech recognition device according to claim 1, wherein: When recognizing the voice input, the control unit refers to definition data defining a plurality of functions and availability of each function, thereby determining whether the function is available.

4. The speech recognition device according to claim 3, wherein: The definition data further includes data defining a reason why a function among the plurality of functions cannot be used. The control unit includes, in the notification, a description of a reason defined by the definition data for the function, when the voice input is recognized and the function is unavailable.

5. The speech recognition device according to claim 3 or claim 4, wherein: The definition data is data that defines whether each function is usable or not according to the state of the vehicle.

Images