Voice operation device, voice operation program and voice operation system
The voice operation device improves voice recognition accuracy by using a separate system with specialized terminology, ensuring the operated system functions as intended, and enhances user convenience and privacy.
Patent Information
- Application Number
- JP2023083247
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-19
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing voice operation systems suffer from low accuracy in voice recognition due to common voice recognition being executed for all users, leading to a reduced likelihood that the operated system will operate as intended by the user.
A voice operation device that uses a voice recognition system separate from the operated system, downloads dictionary data indicating specialized terminology from the operated system, and performs voice recognition using this data to improve accuracy.
Enhances the likelihood that the operated system will operate as intended by the user, improving recognition accuracy and reducing the need for repeated utterances, while also protecting user privacy.
Smart Images

Figure 2024166861000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a voice operation device, a voice operation program, and a voice operation system for operating an operated system. [Background technology]
[0002] Conventionally, there is known a voice operation system that includes an operated system and a voice operation device that receives voice input from a user and operates the operated system (see, for example, Patent Document 1). The voice operation device described in Patent Document 1 transmits voice data indicating the received voice to the operated system. The operated system described in Patent Document 1 then performs voice recognition on the voice data transmitted from the voice operation device and operates according to the result of the voice recognition. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2019-109752 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, in the voice operation system described in Patent Document 1, the operated system performs voice recognition, so common voice recognition is performed for all users. This has the problem that the accuracy of voice recognition may be low for some users, and as a result, there is a low possibility that the operated system will operate as intended by the user.
[0005] Therefore, an object of the present invention is to provide a voice operation device, a voice operation program, and a voice operation system that can improve the likelihood that the operated system will operate as intended by the user. [Means for solving the problem]
[0006] The voice operation device of the present invention is characterized in that it accepts voice input from a user, and transmits the result of voice recognition by a voice recognition system on voice data representing the accepted voice to an operated system which operates in accordance with the result.
[0007] With this configuration, the voice operation device of the present invention has a voice recognition system other than the operated system perform voice recognition on voice data indicating voice input by the user, so that a voice recognition system with high voice recognition accuracy for the user's voice can be used, thereby improving the likelihood that the operated system will operate as intended by the user.
[0008] The voice operation device of the present invention may download dictionary data indicating technical terms specific to the operated system from the operated system, and pass the downloaded dictionary data to the voice recognition system which performs voice recognition using the dictionary data.
[0009] With this configuration, the voice operation device of the present invention downloads dictionary data indicating technical terms specific to the operated system from the operated system and passes the downloaded dictionary data to the voice recognition system. Therefore, even if the voice recognition system does not previously store dictionary data indicating technical terms specific to the operated system, the voice recognition system can perform highly accurate voice recognition using dictionary data indicating technical terms specific to the operated system, thereby improving the likelihood that the operated system will operate as intended by the user.
[0010] The voice operation program of the present invention is characterized in that it causes a computer to perform the operations of accepting voice input from a user and transmitting the results of voice recognition by a voice recognition system for voice data representing the accepted voice to an operated system that operates in accordance with the results.
[0011] With this configuration, a computer executing the voice operation program of the present invention has a voice recognition system other than the operated system perform voice recognition on voice data indicating voice input by the user, so that a voice recognition system with high voice recognition accuracy for the user's voice can be used, thereby improving the likelihood that the operated system will operate as intended by the user.
[0012] The voice operation system of the present invention comprises an operated system and a voice operation device that accepts voice input from a user and operates the operated system, wherein the voice operation device transmits to the operated system the result of voice recognition by a voice recognition system for voice data indicating the accepted voice, and the operated system operates according to the result.
[0013] With this configuration, the voice operation system of the present invention has a voice recognition system other than the operated system perform voice recognition on voice data indicating the voice input by the user to the voice operation device, so that a voice recognition system with high voice recognition accuracy for the user's voice can be used, thereby improving the likelihood that the operated system will operate as intended by the user. Effect of the Invention
[0014] The voice operation device, the voice operation program, and the voice operation system of the present invention can improve the likelihood that the operated system will operate as intended by the user. [Brief description of the drawings]
[0015] [Figure 1] 1 is a block diagram of a voice operation system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram of a user terminal shown in FIG. [Diagram 3] FIG. 2 is a block diagram of the voice recognition system shown in FIG. 1 when configured by one computer. [Figure 4]FIG. 2 is a block diagram of the operated system shown in FIG. 1 when it is an MFP. [Diagram 5] 4 is a sequence diagram of the operation of the voice operation system shown in FIG. 1 when a connection is established between a user terminal and an operated system. [Figure 6] 4 is a sequence diagram of the operation of the voice operation system shown in FIG. 1 when the operated system is operated via a user terminal. [Figure 7] 4 is a flowchart of the operation of the user terminal shown in FIG. 1 when receiving text data from the voice recognition system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0016] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0017] First, a configuration of a voice operation system according to an embodiment of the present invention will be described.
[0018] FIG. 1 is a block diagram of a voice operation system 10 according to the present embodiment.
[0019] As shown in Fig. 1, the voice operation system 10 includes a user terminal 20 as a voice operation device that receives voice input from a user and operates an operated system. The user terminal 20 generates voice data representing the received voice. The user terminal 20 is configured by a computer such as a smartphone or a tablet.
[0020] The voice operation system 10 includes a voice recognition system 30 that performs voice recognition on voice data generated by the user terminal 20 to generate text data as a result of the voice recognition. A voice recognition system suitable for the voice of the user of the user terminal 20 is adopted as the voice recognition system 30. For example, a voice recognition system that has been trained with the voice of the user of the user terminal 20 may be adopted as the voice recognition system 30. Therefore, the voice recognition system 30 can perform voice recognition corresponding to the voice quality, accent, and speaking habits of the user of the user terminal 20. The voice recognition system 30 may be configured by one computer or may be configured by multiple computers.
[0021] The voice operation system 10 includes an operated system 40 that operates according to operation contents indicated by text data input from a user terminal 20. The operated system 40 may be, for example, an MFP (Multifunction Peripheral).
[0022] In the voice operation system 10, a user terminal 20 and a voice recognition system 30 are capable of communicating with each other via a network 11 such as a LAN (Local Area Network) or the Internet.
[0023] In the voice operation system 10, a user terminal 20 and an operated system 40 can communicate with each other via a network 12 such as a LAN or the Internet.
[0024] FIG. 2 is a block diagram of user terminal 20.
[0025] As shown in FIG. 2, the user terminal 20 is equipped with an operation unit 21 which is an operation device such as a button through which various operations are input, a display unit 22 which is a display device such as an LCD (Liquid Crystal Display) that displays various information, a microphone 23, a speaker 24, a communication unit 25 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly by wire or wirelessly without using a network, a memory unit 26 which is a non-volatile memory device such as a semiconductor memory or an HDD (Hard Disk Drive) that stores various information, and a control unit 27 which controls the entire user terminal 20.
[0026] The storage unit 26 stores a voice operation program 26a for accepting a voice input from a user and operating an operated system. The voice operation program 26a may be installed in the user terminal 20 during the manufacturing stage of the user terminal 20, or may be additionally installed in the user terminal 20 from an external storage medium such as a USB (Universal Serial Bus) memory, or may be additionally installed in the user terminal 20 from a network.
[0027] The control unit 27 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores programs and various data, and a RAM (Random Access Memory) that serves as a memory used as a working area for the CPU of the control unit 27. The CPU of the control unit 27 executes the programs stored in the storage unit 26 or the ROM of the control unit 27.
[0028] The control unit 27 executes the voice operation program 26a to realize a voice operation unit 27a that receives a voice input from a user and operates the operated system.
[0029] FIG. 3 is a block diagram of a voice recognition system 30 configured by a single computer.
[0030] As shown in FIG. 3, the voice recognition system 30 includes an operation unit 31 which is an operating device such as a keyboard or a mouse through which various operations are input, a display unit 32 which is a display device such as an LCD that displays various information, a communication unit 33 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly by wire or wirelessly without using a network, a memory unit 34 which is a non-volatile memory device such as a semiconductor memory or a HDD that stores various information, and a control unit 35 which controls the entire voice recognition system 30.
[0031] The storage unit 34 stores a voice recognition program 34a for converting voice data generated by the user terminal 20 into text data by voice recognition. The voice recognition program 34a may be installed in the voice recognition system 30 during the manufacturing stage of the voice recognition system 30, or may be additionally installed in the voice recognition system 30 from an external storage medium such as a USB memory, or may be additionally installed in the voice recognition system 30 from a network.
[0032] The storage unit 34 stores a voice recognition model 34b, which is a machine learning model for converting voice data into text data by voice recognition.
[0033] The control unit 35 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 35. The CPU of the control unit 35 executes the programs stored in the storage unit 34 or the ROM of the control unit 35.
[0034] The control unit 35 executes the voice recognition program 34a to realize a voice recognition unit 35a that converts voice data generated by the user terminal 20 into text data by voice recognition.
[0035] FIG. 4 is a block diagram of the operated system 40 when it is an MFP.
[0036] As shown in FIG. 4, the operated system 40 includes an operation unit 41 which is an operating device such as a button through which various operations are input, a display unit 42 which is a display device such as an LCD that displays various information, a speaker 43, a printer 44 which is a printing device that prints images on a recording medium such as paper, a scanner 45 which is a reading device that reads images from a document, a communication unit 46 which is a communication device that communicates with an external device via a network such as a LAN or the Internet, or directly by wire or wirelessly without using a network, a fax communication unit 47 which is a fax device that communicates with an external facsimile machine (not shown) via a communication line such as a public telephone line, a memory unit 48 which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information, and a control unit 49 which controls the entire operated system 40.
[0037] The storage unit 48 stores an operated program 48a for operating in response to the operation content indicated by the text data input from the user terminal 20. The operated program 48a may be installed in the operated system 40 during the manufacturing stage of the operated system 40, or may be additionally installed in the operated system 40 from an external storage medium such as a USB memory, or may be additionally installed in the operated system 40 from a network.
[0038] The storage unit 48 stores dictionary data 48 b that indicates technical terms specific to the operated system 40 .
[0039] The control unit 49 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 49. The CPU of the control unit 49 executes the programs stored in the storage unit 48 or the ROM of the control unit 49.
[0040] By executing the operated program 48a, the control unit 49 realizes a dictionary data transmission unit 49a that transmits dictionary data indicating technical terms specific to the operated system 40 to the user terminal 20, a natural language processing unit 49b that converts text data input from the user terminal 20 into commands for the operated system 40 by natural language processing, and a command execution unit 49c that operates in accordance with the commands generated by the natural language processing unit 49b.
[0041] Next, the operation of the voice operation system 10 will be described.
[0042] First, the operation of the voice operation system 10 when a connection between the user terminal 20 and the operated system 40 is established will be described.
[0043] FIG. 5 is a sequence diagram of the operation of the voice operation system 10 when a connection between the user terminal 20 and the operated system 40 is established.
[0044] The user can instruct the user terminal 20 to establish a connection between the user terminal 20 and the operated system 40 via the operation unit 21 of the user terminal 20 .
[0045] When instructed to establish a connection between the user terminal 20 and the operated system 40, the voice operation unit 27a of the user terminal 20 establishes a connection with the operated system 40 as shown in FIG. 5 (S61).
[0046] When a connection with the user terminal 20 is established in S61, the dictionary data transmission section 49a of the operated system 40 transmits dictionary data that is the same as the dictionary data 48b to the user terminal 20 (S62).
[0047] When the voice operation unit 27a of the user terminal 20 receives the dictionary data transmitted from the operated system 40 in S62, it transmits the received dictionary data to the voice recognition system 30 (S63).
[0048] When the voice recognition unit 35a of the voice recognition system 30 receives the dictionary data transmitted from the user terminal 20 in S63, the voice recognition unit 35a stores the received dictionary data in the memory unit 34 or the RAM of the control unit 35 (S64).
[0049] Next, the operation of the voice operation system 10 when the operated system 40 is operated via the user terminal 20 will be described.
[0050] FIG. 6 is a sequence diagram of the operation of the voice operation system 10 when the operated system 40 is operated via the user terminal 20. As shown in FIG.
[0051] When a connection between the user terminal 20 and the operated system 40 is established, the user can input a voice into the microphone 23 of the user terminal 20 indicating the operation content for the operated system 40, such as "copy it."
[0052] When a voice is input to the microphone 23, the voice operation unit 27a of the user terminal 20 accepts the voice input to the microphone 23, as shown in FIG. 6 (S71).
[0053] When the process of S71 is completed, the voice operation unit 27a transmits voice data indicating the voice received in S71 to the voice recognition system 30 (S72).
[0054] When the voice recognition unit 35a of the voice recognition system 30 receives the voice data transmitted from the user terminal 20 in S72, the voice recognition unit 35a performs voice recognition on the received voice data using the voice recognition model 34b, thereby converting the received voice data into text data (S73). In the voice recognition in S73, the voice recognition unit 35a uses the dictionary data stored in the memory unit 34 or the RAM of the control unit 35 in S64. For example, when the voice data transmitted from the user terminal 20 in S72 is data indicating a voice saying "Copy it," the voice recognition unit 35a may generate text data indicating the text "Copy it" in S73, or may erroneously generate text data indicating the text "Copy it" in S73.
[0055] When the process of S73 ends, the voice recognition unit 35a transmits the text data generated in S73 to the user terminal 20 (S74).
[0056] When the voice operation unit 27a of the user terminal 20 receives the text data transmitted from the voice recognition system 30 in S74, it transmits the received text data to the operated system 40 (S75).
[0057] When the natural language processing unit 49b of the operated system 40 receives the text data transmitted from the user terminal 20 in S75, it attempts to convert the received text data into a command for the operated system 40 by natural language processing (S76).
[0058] When the natural language processing unit 49b of the operated system 40 fails to convert the text data into a command in S76, it notifies the user that the text data could not be converted into a command in S76 (S77). The notification method in S77 may be a notification by at least one of the display unit 42 and the speaker 43 of the operated system 40. When the natural language processing unit 49b executes the notification in S77 by the speaker 43 of the operated system 40, it may output a voice corresponding to the text shown in the text data transmitted from the user terminal 20 in S75 by the speaker 43. For example, when the text shown in the text data transmitted from the user terminal 20 in S75 is the text "Call me", the natural language processing unit 49b may output a voice saying "Call me" by the speaker 43.
[0059] If the command executing unit 49c of the operated system 40 was able to convert the text data into a command in S76, it operates according to the command generated in S76 (S78). For example, if the text data transmitted from the user terminal 20 in S75 is data indicating the text "copy it," the command executing unit 49c reads an image from an original document using the scanner 45, and prints the image read from the original document by the scanner 45 on a recording medium using the printer 44.
[0060] 6, when the voice operation unit 27a of the user terminal 20 receives text data transmitted from the voice recognition system 30, the voice operation unit 27a always transmits the text data received from the voice recognition system 30 to the operated system 40 (S75). However, when the voice operation unit 27a receives text data transmitted from the voice recognition system 30, the voice operation unit 27a may transmit the text data received from the voice recognition system 30 to the operated system 40 only when instructed by the user, as shown in FIG.
[0061] FIG. 7 is a flowchart showing the operation of user terminal 20 when text data is received from voice recognition system 30. As shown in FIG.
[0062] When the voice operation unit 27a of the user terminal 20 receives the text data transmitted from the voice recognition system 30, it executes the operation shown in FIG.
[0063] As shown in FIG. 7, the voice operation unit 27a displays a transmission instruction acceptance screen on the display unit 21 of the user terminal 20 for accepting an instruction on whether or not to transmit the text data received from the voice recognition system 30 to the operated system 40 via the operation unit 21 of the user terminal 20 (S81). The transmission instruction acceptance screen includes the contents of the text data received from the voice recognition system 30. When displaying the transmission instruction acceptance screen on the display unit 21, the voice operation unit 27a may notify the contents of the text data received from the voice recognition system 30 by the speaker 24 of the user terminal 20. When notifying the contents of the text data received from the voice recognition system 30 by the speaker 24, the voice operation unit 27a outputs a voice corresponding to the text shown in the text data received from the voice recognition system 30 by the speaker 24. For example, when the text shown in the text data received from the voice recognition system 30 is the text "Call me", the voice operation unit 27a outputs the voice "Call me" by the speaker 24.
[0064] When the process of S81 ends, the voice operation unit 27a judges whether or not an instruction to transmit the text data received from the voice recognition system 30 to the operated system 40 has been accepted on the transmission instruction acceptance screen (S82).
[0065] When the voice operation unit 27a determines in S82 that the transmission instruction acceptance screen has not accepted the instruction to transmit the text data received from the voice recognition system 30 to the operated system 40, it determines whether the transmission instruction acceptance screen has accepted an instruction not to transmit the text data received from the voice recognition system 30 to the operated system 40 (S83).
[0066] When the voice operation unit 27a determines in S83 that the instruction not to transmit the text data received from the voice recognition system 30 to the operated system 40 has not been accepted on the transmission instruction acceptance screen, the voice operation unit 27a executes the process of S82.
[0067] When the voice operation unit 27a determines in S82 that it has accepted on the transmission instruction acceptance screen that the text data received from the voice recognition system 30 should be transmitted to the operated system 40, it transmits the text data received from the voice recognition system 30 to the operated system 40 (S84) and terminates the operation shown in FIG. 7.
[0068] When the voice operation unit 27a determines in S83 that it has received on the transmission instruction acceptance screen that the text data received from the voice recognition system 30 should not be transmitted to the operated system 40, it terminates the operation shown in FIG. 7 without transmitting the text data received from the voice recognition system 30 to the operated system 40.
[0069] As described above, the user terminal 20 causes a voice recognition system 30 separate from the operated system 40 to perform voice recognition on the voice data indicating the voice input by the user (S73). Therefore, the user can prepare and use a voice recognition system 30 that has high accuracy in voice recognition of the user's voice, thereby improving the likelihood that the operated system 40 will operate as the user intends.
[0070] The user terminal 20 can improve the likelihood that the operated system 40 will operate as the user intends, thereby reducing the need for the user to repeat his / her utterance, thereby improving convenience.
[0071] The user terminal 20 does not transmit the user's voice data to the operated system 40, but transmits text data converted from the voice data to the operated system 40, thereby improving the possibility of protecting the user's privacy.
[0072] The user terminal 20 downloads dictionary data indicating technical terms specific to the operated system 40 from the operated system 40 (S62) and passes the downloaded dictionary data to the voice recognition system 30 (S63). Therefore, even if the voice recognition system 30 does not previously store dictionary data indicating technical terms specific to the operated system 40, it is possible to have the voice recognition system 30 perform highly accurate voice recognition (S73) using the dictionary data indicating technical terms specific to the operated system 40, thereby improving the likelihood that the operated system 40 will operate as the user intended.
[0073] When converting voice data into text data, the voice recognition system 30 does not need to use dictionary data indicating technical terms specific to the operated system 40. If the voice recognition system 30 does not use dictionary data indicating technical terms specific to the operated system 40, the voice operation system 10 does not need to download dictionary data indicating technical terms specific to the operated system 40 to the voice recognition system 30.
[0074] In this embodiment, the voice operation system 10 includes a voice recognition system 30 in addition to the user terminal 20. However, the user terminal 20 may also function as the voice recognition system 30. [Explanation of symbols]
[0075] 10 Voice Operation System 20 User terminals (voice-operated devices, computers) 26a Voice-operated program 30 Voice Recognition System 40 Controlled Systems
Claims
1. Accepts voice input from the user, A voice operation device, comprising: a voice recognition system that performs voice recognition on voice data representing a received voice, and transmits the result of the voice recognition to an operated system that operates in accordance with the result.
2. The voice operation device according to claim 1, characterized in that dictionary data indicating terminology specific to the operated system is downloaded from the operated system, and the downloaded dictionary data is passed to the voice recognition system which performs voice recognition using the dictionary data.
3. An operation of accepting voice input from a user; and transmitting a result of voice recognition by a voice recognition system for voice data indicating the received voice to an operated system that operates in accordance with the result. A voice-operated program that is implemented on a computer.
4. An operated system; a voice operation device that receives a voice input from a user and operates the operated system; Equipped with the voice operation device transmits a result of voice recognition by a voice recognition system to the operated system with respect to voice data representing the received voice; The voice-operated system is characterized in that the operated system operates according to the result.
Citation Information
Patent Citations
Wireless terminal, management server, intention interpretation server, control method thereof, and program
JP2019109752A
