Information processing device
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- PIONEER IP
- Filing Date
- 2021-12-10
- Publication Date
- 2026-08-03
Smart Images
Figure 0007898848000001 
Figure 0007898848000002 
Figure 0007898848000003
Abstract
Description
Technical Field
[0001] The present invention relates to an information processing apparatus.
Background Art
[0002] Voice synthesis technology using deep learning has been developed, making it possible to synthesize more natural human voices (for example, Patent Document ).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] However, it is difficult for individual users to develop such technology. Therefore, many users use services provided by other companies to convert text data into voice data. Such services are often provided on a per-use basis, and in order to suppress costs, it is necessary to reduce the amount of service used.
[0005] As an example of the problem to be solved by the present invention, cost reduction can be cited.
Means for Solving the Problems
[0006] In order to solve the above problems, the invention according to claim 1 includes a text data reception processing unit that receives text data from a terminal device, a voice data transmission processing unit that transmits voice data corresponding to the text data to the terminal device, checks whether voice data corresponding to the text data is stored in a storage device that stores a plurality of voice data, If audio data corresponding to the text data is stored in the storage device, the audio data stored in the storage device is transmitted to the terminal device as audio data corresponding to the text data. If audio data corresponding to the text data is not stored in the storage device, the audio data transmission processing unit transmits the text data to an audio data creation device that creates audio data corresponding to the text data on a pay-per-use basis, receives the audio data corresponding to the text data from the audio data creation device, and transmits the audio data received from the audio data creation device as audio data corresponding to the text data to the terminal device. The system includes a storage processing unit that stores audio data received from the audio data creation device in the storage device.
[0007] The invention described in claim 8 is an information processing method performed by a computer, comprising: a text data receiving processing step of receiving text data from a terminal device; an audio data transmission processing step of transmitting audio data corresponding to the text data to the terminal device, the audio data transmission processing step of checking whether audio data corresponding to the text data is stored in a storage device that stores a plurality of audio data, and if audio data corresponding to the text data is stored in the storage device, transmitting the audio data stored in the storage device as audio data corresponding to the text data to the terminal device, and if audio data corresponding to the text data is not stored in the storage device, transmitting the text data to an audio data creation device that creates audio data corresponding to the text data on a pay-per-use basis, receiving audio data corresponding to the text data from the audio data creation device, and transmitting the audio data received from the audio data creation device as audio data corresponding to the text data to the terminal device, and a storage processing step of storing the audio data received from the audio data creation device in the storage device.
[0008] The invention described in claim 9 is an information processing program that causes a computer to execute the information processing method described in claim 8.
[0009] The invention described in claim 10 stores the information processing program described in claim 9. [Brief explanation of the drawing]
[0010] [Figure 1] This figure shows a voice response system according to an embodiment of the present invention. [Figure 2] This diagram illustrates the processing operations in a voice response system. [Figure 3] This is a diagram showing terminal device 100. [Figure 4] This is a diagram showing the control unit 110 of the terminal device 100. [Figure 5] This figure shows the server device 200. [Figure 6] This figure shows the control unit 210 of the server device 200. [Figure 7] This figure shows an example of the processing operation in the voice response system according to this embodiment. [Modes for carrying out the invention]
[0011] An information processing device according to one embodiment of the present invention includes a text data receiving processing unit that receives text data from a terminal device, and an audio data transmission processing unit that transmits audio data corresponding to the text data to the terminal device, the audio data transmission processing unit that checks whether audio data corresponding to the text data is stored in a storage device that stores a plurality of audio data, and if audio data corresponding to the text data is stored in the storage device, transmits the audio data stored in the storage device to the terminal device as audio data corresponding to the text data, and if audio data corresponding to the text data is not stored in the storage device, transmits the text data to an audio data creation device that creates audio data corresponding to the text data on a pay-per-use basis, receives the audio data corresponding to the text data from the audio data creation device, and transmits the audio data received from the audio data creation device to the terminal device as audio data corresponding to the text data, and a storage processing unit that stores the audio data received from the audio data creation device in the storage device. Thus, in this embodiment, if audio data corresponding to the text data is stored, no request is made to the audio data creation device to create the audio data. Furthermore, in this embodiment, it is possible to increase the number of types of audio data to be stored. Therefore, in this embodiment, it becomes possible to reduce the number of times the audio data creation device is requested to create audio data, and as a result, costs can be reduced.
[0012] The text data may be text data for which it has been confirmed that no corresponding audio data is stored in the terminal device. In this way, if the audio data corresponding to the text data is stored in the terminal device, there is no need to exchange data between the terminal device and the information processing device.
[0013] The text data may be text data corresponding to a response to a user's utterance input into the terminal device. In this way, the terminal device can provide a voice response to the user's utterance.
[0014] The terminal devices may be plural. By doing so, the information processing device will store voice data requested from many terminal devices, and it will be possible to further increase the types of voice data to be stored.
[0015] The storage processing unit compares a first cost including the cost for storing the received voice data in the storage device with a second cost including the cost for creating the received voice data by the voice data creation device, and stores the received voice data in the storage device only when the first cost is lower than the second cost. By doing so, it becomes possible to determine whether or not to use the voice data creation device in consideration of the overall cost, and as a result, it becomes possible to suppress the overall cost.
[0016] The second cost may be determined based on the amount of text data received from the voice data creation device. By doing so, it becomes possible to correspond to a service that determines the fee for creating voice data based on the amount of text data to be converted into voice data (for example, the number of characters in the text data). [[ID=!3]]
[0017] The second cost during a predetermined period may be zero until the amount of text data received from the voice data creation device during the predetermined period reaches a predetermined amount. By doing so, it becomes possible to correspond to a service that makes the fee for creating voice data zero until the amount of text data to be converted into voice data during the predetermined period (for example, one month) reaches a predetermined amount.
[0018] Also, an information processing method according to an embodiment of the present invention is an information processing method executed by a computer, including a text data receiving process of receiving text data from a terminal device, and an audio data transmitting process of transmitting audio data corresponding to the text data to the terminal device. In the audio data transmitting process, it is confirmed whether the audio data corresponding to the text data is stored in a storage device that stores a plurality of audio data. If the audio data corresponding to the text data is stored in the storage device, the audio data stored in the storage device is transmitted to the terminal device as the audio data corresponding to the text data. If the audio data corresponding to the text data is not stored in the storage device, the text data is transmitted to an audio data creation device that creates audio data on a per-use basis, the audio data corresponding to the text data is received from the audio data creation device, and the audio data received from the audio data creation device is transmitted to the terminal device as the audio data corresponding to the text data. It further includes a storage process of storing the audio data received from the audio data creation device in the storage device. Thus, in this embodiment, if the audio data corresponding to the text data is stored, a request for creating audio data is not sent to the audio data creation device. Also, in this example, it is possible to increase the types of audio data to be stored. Therefore, in this embodiment, it is possible to suppress the number of times of requesting the audio data creation device to create audio data, and as a result, it is possible to suppress the cost.
[0019] Also, program information processing according to an embodiment of the present invention causes a computer to execute the above information processing method. Therefore, in this embodiment, it is possible to suppress the number of times of requesting the audio data creation device to create audio data by using a computer, and as a result, it is possible to suppress the cost.
[0020] Furthermore, a computer-readable storage medium according to one embodiment of the present invention stores the above-mentioned information processing program. In this way, the above-mentioned information processing program can be distributed independently, in addition to being incorporated into a device, and version upgrades and the like can be easily performed. [Examples]
[0021] <Voice Response System> Figure 1 shows a voice response system according to one embodiment of the present invention. The voice response system according to this embodiment includes one or more terminal devices 100, a server device 200, and a voice data creation device 300. The server device 200 is an example of an information processing device according to the above embodiment.
[0022] Figure 2 illustrates the processing operation in a voice response system. Terminal device 100 receives speech input from the user and outputs a voice response to the user's speech. If terminal device 100 has stored voice data corresponding to the response, it outputs voice based on this stored voice data. On the other hand, if terminal device 100 does not have stored voice data corresponding to the response, it sends a request for voice data corresponding to the response to server device 200, receives voice data from server device 200, and outputs voice based on this received voice data.
[0023] If the server device 200 has stored voice data corresponding to the response requested by the terminal device 100, it transmits this stored voice data to the terminal device 100. On the other hand, if the server device 200 does not have stored voice data corresponding to the response requested by the terminal device 100, it transmits a request to the voice data creation device 300 to create voice data corresponding to the response, receives voice data from the voice data creation device 300, and transmits this received voice data to the terminal device 100.
[0024] The voice data creation device 300 creates voice data corresponding to text data on a pay-per-use basis. Requests for voice data corresponding to responses sent from the terminal device 100 to the server device 200, and requests for the creation of voice data corresponding to responses sent from the server device 200 to the voice data creation device 300, include text data corresponding to the responses. When the voice data creation device 300 receives a request for the creation of voice data corresponding to a response from the server device 200, it creates, for example, voice data corresponding to this text data and sends this created voice data to the server device 200.
[0025] Thus, in this embodiment, if voice data corresponding to the response is stored, no request is made to the voice data creation device to create voice data. Therefore, in this embodiment, it is possible to reduce the number of times the voice data creation device is requested to create voice data, and as a result, costs can be reduced.
[0026] <Terminal device 100> Figure 3 shows a terminal device 100. The terminal device 100 includes a control unit 110, an audio input unit 120, a communication unit 130, an audio output unit 140, and a storage unit 150. The control unit 110 is configured as a computer. The audio input unit 120 is an audio input device for receiving audio input from a microphone or the like. The communication unit 130 is a communication device for sending and receiving information with other devices. The audio output unit 140 is an audio output device for outputting audio from a speaker or the like. The storage unit 150 is a storage device for storing information, such as a hard disk or memory.
[0027] Figure 4 shows the control unit 110 of the terminal device 100. The control unit 110 includes a response creation unit 111, a response voice output processing unit 112, and a storage processing unit 113.
[0028] The response generation unit 111 recognizes the content of the user's speech input by the voice input unit 120 and creates text data corresponding to the response to the user's speech.
[0029] The response creation unit 111 may have a function to recognize the content of the user's utterance, or it may use another device to recognize the content of the user's utterance by communicating with the communication unit 130. Alternatively, the response creation unit 111 may have a function to create a response to the user's utterance, or it may use another device to create a response to the user's utterance by communicating with the communication unit 130.
[0030] The response voice output processing unit 112 outputs a voice response to the user's utterance via the voice output unit 140. In other words, the voice output unit 140 outputs voice based on voice data corresponding to the text data created by the response creation unit 111 (i.e., voice data corresponding to the response).
[0031] For example, if the user's utterance is a search request (e.g., "Find a convenience store"), the response creation unit 111 recognizes the content of the user's utterance, performs the requested search (e.g., a search for convenience stores near the user) to create a response to the user's utterance, and based on the search results, creates text data corresponding to the response to the user's utterance (e.g., "Store A and Store B were found. Which one would you like to go to?"). Then, the response voice output processing unit 112 outputs voice corresponding to this created text data (e.g., "Store A and Store B were found. Which one would you like to go to?").
[0032] When outputting audio based on audio data corresponding to a response, the response audio output processing unit 112 checks whether or not the audio data corresponding to the response is stored in the storage unit 150. If the audio data corresponding to the response is stored in the storage unit 150, the response audio output processing unit 112 outputs audio based on the audio data stored in the storage unit 150 using the audio output unit 140. On the other hand, if the audio data corresponding to the response is not stored in the storage unit 150, the response audio output processing unit 112 sends a request for the audio data corresponding to the response to the server device 200 using the communication unit 130, receives the audio data from the server device 200 using the communication unit 130, and outputs audio based on this received audio data using the audio output unit 140.
[0033] Thus, in this embodiment, if voice data corresponding to the response is stored, the system does not request voice data from the server device and outputs voice based on the stored voice data. Therefore, in this embodiment, if voice data corresponding to the response is stored in the terminal device, there is no need to exchange data between the terminal device and the server device, and it is possible to shorten the time until a response to the user's utterance is output.
[0034] The memory processing unit 113 stores the audio data received from the server device 200 in the memory unit 150. Therefore, in this embodiment, it is possible to increase the types of audio data stored in the memory unit, and as a result, the need for data exchange between the terminal device and the server device is reduced, and the time until a response to the user's speech is output can be shortened.
[0035] In the above configuration, the response generation unit 111 generates a response to the user's speech input by the voice input unit 120. However, it may also be configured to generate a response to information input by other types of input devices, such as a keyboard.
[0036] <Server device 200> Figure 5 shows a server device 200. The server device 200 includes a control unit 210, a communication unit 220, and a storage unit 230. The control unit 210 is configured as a computer. The communication unit 220 is a communication device for sending and receiving information with other devices. The storage unit 230 is a storage device for storing information, such as a hard disk or memory.
[0037] Figure 6 shows the control unit 210 of the server device 200. The control unit 210 includes a text data receiving processing unit 211, an audio data transmission processing unit 212, and a storage processing unit 213.
[0038] The text data receiving processing unit 211 receives a request for voice data corresponding to the response from the terminal device 100 via the communication unit 220. The request for voice data corresponding to the response includes text data corresponding to the response.
[0039] The voice data transmission processing unit 212 transmits voice data corresponding to the response to the terminal device 100 via the communication unit 220.
[0040] At this time, the voice data transmission processing unit 212 checks whether or not voice data corresponding to the response (i.e., voice data corresponding to the response in the text data corresponding to the response) is stored. The voice data transmission processing unit 212 may check whether or not voice data corresponding to the response is stored in the storage unit 230 of the server device 200, or it may check whether or not voice data corresponding to the response is stored in a storage device separate from the server device 200 (for example, the storage unit of another server device, or the storage unit 150 of a terminal device 100 other than the terminal device 100 that sent the request for voice data corresponding to the response).
[0041] If voice data corresponding to the response is stored, the voice data transmission processing unit 212 transmits this stored voice data. On the other hand, if voice data corresponding to the response is not stored, the voice data transmission processing unit 212 sends a request for the creation of voice data corresponding to the response to the voice data creation device 300 via the communication unit 220, receives the voice data corresponding to the response from the voice data creation device 300 via the communication unit 220, and transmits this received voice data to the terminal device 100 via the communication unit 220. The request for the creation of voice data corresponding to the response includes text data corresponding to the response, and the voice data creation device 300 transmits the voice data corresponding to this text data to the server device 200.
[0042] Thus, in this embodiment, if voice data corresponding to the response is stored, no request is made to the voice data creation device to create voice data. Therefore, in this embodiment, it is possible to reduce the number of times the voice data creation device is requested to create voice data, and as a result, costs can be reduced.
[0043] The memory processing unit 213 stores the audio data received from the audio data creation device 300. At this time, the audio data transmission processing unit 212 may store the audio data received from the audio data creation device 300 in the memory unit 230 of the server device 200, or it may store the audio data received from the audio data creation device 300 in a separate storage device from the server device 200. Therefore, in this embodiment, it is possible to increase the types of audio data to be stored and to further reduce the number of times requests are made to the audio data creation device to create audio data.
[0044] For example, it is possible to assume that there are multiple terminal devices 100. In this way, the server device will store voice data requested from many terminal devices, making it possible to increase the variety of voice data that can be stored.
[0045] The memory processing unit 213 may, upon receiving audio data from the audio data creation device 300, compare a first cost, which includes the cost of storing the received audio data, with a second cost, which includes the cost of creating the received audio data using the audio data creation device 300. The memory processing unit may then store the received audio data only if the first cost is lower than the second cost. In this way, it becomes possible to decide whether or not to use the audio data creation device after considering the overall cost, and as a result, it becomes possible to suppress the overall cost.
[0046] Some audio data creation services determine their fees based on the amount of text data to be converted into audio data (e.g., the number of characters in the text data). Therefore, it would be preferable for the second cost to be determined, for example, by the amount of text data received from the audio data creation device 300 (e.g., the number of characters in the text data).
[0047] Furthermore, some audio data creation services offer a service where the fee for creating audio data over a predetermined period (for example, one month) is zero until the amount of text data converted into audio data during that period reaches a predetermined amount. Therefore, the second cost for the predetermined period should be zero, for example, until the amount of text data corresponding to the audio data received from the audio data creation device 300 during that period reaches a predetermined amount.
[0048] <Processing operations in a voice response system> Figure 7 shows an example of processing operation in the voice response system according to this embodiment. The processing operation in Figure 7 is performed each time the terminal device 100 receives user speech input from the voice input unit 120.
[0049] The response creation unit 111 of the terminal device 100 creates text data corresponding to the response to the user's input (step S701). The response voice output processing unit 112 of the terminal device 100 checks whether or not voice data corresponding to the response is stored in the storage unit 150 of the terminal device 100 (step S702). If voice data corresponding to the response is stored in the storage unit 150 (step S702, YES), the response voice output processing unit 112 of the terminal device 100 outputs voice based on the voice data stored in this storage unit 130 using the voice output unit 140 (step S703). If voice data corresponding to the response is not stored in the storage unit 150 (step S702, NO), the response voice output processing unit 112 of the terminal device 100 sends a request for voice data corresponding to the response to the server device 200 using the communication unit 130 (step S704).
[0050] The text data receiving processing unit 211 of the server device 200 receives a request for voice data corresponding to the response from the terminal device 100 via the communication unit 220 (step 705). The voice data transmission processing unit 212 of the server device 200 checks whether or not voice data corresponding to the response is stored (step S706). If voice data corresponding to the response data is stored (step S706, YES), the voice data transmission processing unit 212 of the server device 200 transmits this stored voice data to the terminal device 100 via the communication unit 220 (step S707). If voice data corresponding to the response is not stored (step S706, NO), the voice data transmission processing unit 212 of the server device 200 sends a request to the voice data creation device 300 to create voice data corresponding to the response (step S708).
[0051] The voice data creation device 300 receives a request from the server device 200 to create voice data corresponding to the response, and sends the voice data corresponding to the response to the server device 200 (step S709).
[0052] The voice data transmission processing unit 212 of the server device 200 receives voice data corresponding to the response from the voice data creation device 300 via the communication unit 220, transmits this received voice data to the terminal device 100 via the communication unit 220, and the storage processing unit 213 stores this received voice data (step 710).
[0053] The response voice output processing unit 112 of the terminal device 100 receives voice data corresponding to the response from the server device 200 via the communication unit 130, outputs voice based on this received voice data via the voice output unit 140, and the storage processing unit 113 stores this received voice data in the storage unit 150 (step S711).
[0054] The present invention has been described above with reference to preferred embodiments. Although the present invention has been described with reference to specific examples, various modifications and changes can be made to these examples without departing from the spirit and scope of the invention as described in the claims. [Explanation of Symbols]
[0055] 100 terminal devices 110 Control Unit 111 Response Creation Section 112 Response voice output processing unit 113 Memory Processing Unit 120 Voice input section 130 Communications Department 140 Audio output section 150 Storage section 200 Server Devices 210 Control Unit 211 Text data receiving processing unit 212 Voice data transmission processing unit 213 Memory Processing Unit 220 Communications Department 230 Storage section 300 Audio data creation device
Claims
1. A system comprising a server device having a control unit, a communication unit for sending and receiving information between a terminal device and an audio data creation device, and a storage unit for storing information, and the terminal device, The aforementioned voice data creation device is a device that creates voice data corresponding to text data on a pay-per-use basis. The aforementioned storage unit stores multiple audio data, The control unit, A text data receiving processing unit that receives text data from the terminal device, A voice data transmission processing unit that transmits voice data corresponding to the text data to the terminal device, The storage unit checks whether or not audio data corresponding to the text data is stored there. If audio data corresponding to the text data is stored in the storage unit, the audio data stored in the storage unit is transmitted to the terminal device as audio data corresponding to the text data. If no audio data corresponding to the text data is stored in the storage unit, the audio data transmission processing unit transmits the text data to the audio data creation device, receives audio data corresponding to the text data from the audio data creation device, and transmits the audio data received from the audio data creation device as audio data corresponding to the text data to the terminal device. The system includes a storage processing unit that stores audio data received from the audio data creation device in the storage unit, The system is characterized in that the text data is text data for which it has been confirmed that no corresponding audio data is stored in the terminal device.
2. The system according to claim 1, wherein the text data is text data corresponding to a response to a user's utterance input into the terminal device.
3. The system according to claim 1 or 2, wherein the terminal device is a plurality of devices.
4. A server device having a control unit, a communication unit for sending and receiving information between a terminal device and an audio data creation device, and a storage unit for storing information, The aforementioned voice data creation device is a device that creates voice data corresponding to text data on a pay-per-use basis. The aforementioned storage unit stores multiple audio data, The control unit, A text data receiving processing unit that receives text data from the terminal device, A voice data transmission processing unit that transmits voice data corresponding to the text data to the terminal device, The storage unit checks whether or not audio data corresponding to the text data is stored there. If audio data corresponding to the text data is stored in the storage unit, the audio data stored in the storage unit is transmitted to the terminal device as audio data corresponding to the text data. If no audio data corresponding to the text data is stored in the storage unit, the audio data transmission processing unit transmits the text data to the audio data creation device, receives audio data corresponding to the text data from the audio data creation device, and transmits the audio data received from the audio data creation device as audio data corresponding to the text data to the terminal device. The system includes a storage processing unit that stores audio data received from the audio data creation device in the storage unit, A server device wherein the storage processing unit compares a first cost, which includes the cost of storing the received audio data in the storage unit, with a second cost, which includes the cost of creating the received audio data using the audio data creation device, and stores the received audio data in the storage unit only when the first cost is lower than the second cost.
5. The server device according to claim 4, wherein the second cost is determined based on the amount of text data received from the voice data creation device.
6. The server device according to claim 5, wherein the second cost during a predetermined period is zero until the amount of text data received from the voice data creation device during that predetermined period reaches a predetermined amount.
7. An information processing method performed by a system comprising a server device having a control unit, a communication unit for sending and receiving information between a terminal device and an audio data creation device, and a storage unit for storing information, and the terminal device, The aforementioned voice data creation device is a device that creates voice data corresponding to text data on a pay-per-use basis. The aforementioned storage unit stores multiple audio data, The aforementioned information processing method is A text data reception process for receiving text data from the terminal device, A voice data transmission process that transmits voice data corresponding to the text data to the terminal device, The storage unit checks whether or not audio data corresponding to the text data is stored there. If audio data corresponding to the text data is stored in the storage unit, the audio data stored in the storage unit is transmitted to the terminal device as audio data corresponding to the text data. If audio data corresponding to the text data is not stored in the storage unit, the audio data transmission process includes transmitting the text data to the audio data creation device, receiving audio data corresponding to the text data from the audio data creation device, and transmitting the audio data received from the audio data creation device as audio data corresponding to the text data to the terminal device. The system includes a storage processing step of storing audio data received from the audio data creation device in the storage unit, An information processing method wherein the text data is text data for which it has been confirmed that no corresponding audio data is stored in the terminal device.
8. An information processing method performed by a server device having a control unit, a communication unit for sending and receiving information between a terminal device and an audio data creation device, and a storage unit for storing information, The aforementioned voice data creation device is a device that creates voice data corresponding to text data on a pay-per-use basis. The aforementioned storage unit stores multiple audio data, The aforementioned information processing method is A text data reception process for receiving text data from the terminal device, A voice data transmission process that transmits voice data corresponding to the text data to the terminal device, The storage unit checks whether or not audio data corresponding to the text data is stored there. If audio data corresponding to the text data is stored in the storage unit, the audio data stored in the storage unit is transmitted to the terminal device as audio data corresponding to the text data. If audio data corresponding to the text data is not stored in the storage unit, the audio data transmission process includes transmitting the text data to the audio data creation device, receiving audio data corresponding to the text data from the audio data creation device, and transmitting the audio data received from the audio data creation device as audio data corresponding to the text data to the terminal device. The system includes a storage processing step of storing audio data received from the audio data creation device in the storage unit, The storage processing step is an information processing method which compares a first cost, which includes the cost of storing the received audio data in the storage unit, with a second cost, which includes the cost of creating the received audio data using the audio data creation device, and stores the received audio data in the storage unit only when the first cost is lower than the second cost.
9. An information processing program that causes the control unit to execute the information processing method described in claim 7 or 8.
10. A computer-readable storage medium storing the information processing program described in claim 9.