Automatic interpretation system and program

Abstract

To provide an automatic interpretation system capable of offering interpretation into multiple languages with high accuracy and at low cost.SOLUTION: A second speech 61 in a second language 131, interpreted by a first interpreter 31, is input into a first terminal device 41. A second speech 62 in a second language 132, interpreted by a second interpreter 32, is input into a second terminal device 42. An automatic interpretation unit 15 of an automatic interpretation system 11 performs processing to interpret a first speech 105 in a first language into third speeches 81-85 in a plurality of mutually different third languages 71-75. A transmission unit 33 associates the first speech, the second speeches 61, 62, and the third speeches 81-85 with each other in a format that allows a terminal device 19 of a recipient 29 to select and output a language, and transmits them as a multilingual speech 99.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an automatic translation system and program for translating a speaker's voice into multiple languages.

Background Art

[0002] For example, in the field of international conferences and the like, there are cases where the voice of a speaker at a venue is translated into multiple languages. Conventionally, multiple interpreters corresponding to each of multiple languages are arranged, and each interpreter translates the speaker's voice into the language they are in charge of, and the audience selects the language to view.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, it is difficult to secure interpreters for minor languages, and there is a problem that securing interpreters corresponding to many languages increases the cost.

[0005] The present invention has been made in view of such circumstances, and its object is to provide an automatic translation system and program that can provide high-precision and low-cost translation into multiple languages.

Means for Solving the Problems

[0006] The present invention relates to an automatic translation system comprising: an input unit for inputting a second voice obtained by a translator translating a first voice in a first language spoken by a speaker into a second language; an automatic translation unit for translating the second voice input by the input unit into third voices in a plurality of different third languages; and a transmission unit for associating the first voice, the second voice, and the plurality of third voices in a format that allows a recipient to select a language and transmitting the associated voices to the recipient.

[0007] Preferably, the input unit inputs a plurality of second voices obtained by translating the first voice into a plurality of different second languages, and the transmission unit associates the first voice, the plurality of second voices, and the plurality of third voices in a format that allows a recipient to select a language and transmits the associated voices to the recipient.

[0008] Preferably, for each of the plurality of second voices, the automatic translation unit translates the second voice into a third voice in the plurality of third languages, generates a fourth voice obtained by back-translating the plurality of third voices into the second language respectively, detects a degree of match between the plurality of fourth voices corresponding to the different second languages and the second voice, and selects, from among the plurality of third voices back-translated into the different second languages, the third voice with a high degree of match and causes the selected third voice to be transmitted to the transmission unit.

[0009] Preferably, for the selected third voice in the plurality of different third languages, the automatic translation unit generates translation accuracy information that allows the recipient to identify the third voice with a high degree of match, and the transmission unit transmits the translation accuracy information to the recipient in association with the third voice.

[0010] The present invention relates to an automatic translation system comprising: an input unit for inputting a second voice obtained by a translator translating a first voice in a first language spoken by a speaker into a second language; an automatic translation unit for translating the first voice input by the input unit into third voices in a plurality of different third languages; and a transmission unit for associating the first voice, the second voice, and the plurality of third voices in a format that allows a recipient to select a language and transmitting the associated voices to the recipient.

[0011] The present invention is a program that causes a computer to execute an input step of inputting a second voice obtained by translating, by an interpreter, a first voice in a first language spoken by a speaker into a second language, an automatic translation step of translating the second voice input in the input step into third voices in a plurality of different third languages, and a transmission step of associating the first voice, the second voice, and the plurality of third voices in a form that can be output by a recipient selecting a language and transmitting the same to the recipient.

[0012] The present invention is a program that causes a computer to execute an input step of inputting a second voice obtained by translating, by an interpreter, a first voice in a first language spoken by a speaker into a second language, an automatic translation step of translating the first voice input in the input step into third voices in a plurality of different third languages, and a transmission step of associating the first voice, the second voice, and the plurality of third voices in a form that can be output by a recipient selecting a language and transmitting the same to the recipient.

Advantages of the Invention

[0013] According to the present invention, it is possible to provide an automatic translation system and program that can provide translation into multiple languages with high accuracy and at low cost.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Best Mode for Carrying Out the Invention

[0015] Hereinafter, a translation business model according to an embodiment of the present invention will be described. <First Embodiment> FIG. 1 is a diagram for explaining a translation business model 1 according to the first embodiment of the present invention. FIG. 2 is a diagram for explaining the system used in the translation business model 1 shown in FIG. 1. As shown in FIG. 1, the translation business model 1 is used by, for example, a speaker 5 such as a lecturer, a first translator 31, a second translator 32, and a recipient 29. The recipient 29 may be singular or plural.

[0016] In the present embodiment, the automatic translation system 11 performs a process of automatically translating the first voice 105 in the first language of the speaker 5 into the third voices 81 to 85 in a plurality of different third languages 71 to 75. The first language is, for example, English. The second language is, for example, Chinese. The third languages 71 to 75 are, for example, Korean, Thai, Vietnamese, Spanish, and Portuguese.

[0017] The speaker 5 transmits the first voice 105 of the speech to the automatic translation system 11 using a microphone or a terminal device. The first translator 31 uses the first terminal device 41. The first terminal device 41 inputs the first voice 105 from the automatic translation system 11 and outputs it to the first translator 31. In addition, the first terminal device 41 transmits the second voice 61 obtained by the first translator 31 translating the first voice 105 into the second language 51 to the automatic translation system 11.

[0018] The second translator 32 uses the second terminal device 42. The second terminal device 42 inputs the first voice 105 from the automatic translation system 11 and outputs it to the second translator 32. Further, the second terminal device 42 transmits the second voice 62, which is the first voice 105 translated into the second language 52 by the second interpreter 32, to the automatic translation system 11.

[0019] The automatic translation system 11 has an automatic translation unit 15 and a transmission unit 33. The automatic translation unit 15 performs a process of translating (interpreting) the first voice 105 in the first language into the third voices 81 to 85 in a plurality of different third languages 71 to 75. The transmission unit 33 transmits the first voice, the second voices 61 and 62, and the plurality of third voices 81 to 85, in a form associated with each other and outputtable by the terminal device 19 of the recipient 29 selecting a language, as a multilingual voice 99.

[0020] The recipient 29 uses the terminal device 19. The terminal device 19 receives the multilingual voice 99 from the automatic translation system 11.

[0021] Figure 3 is a functional block diagram of the automatic translation system 11 shown in Figure 1. As shown in Figure 3, the automatic translation system 11 has, for example, a display 51, an operation unit 53, a communication unit 55, a memory 59, and a processing unit 61.

[0022] The display 51 displays an image based on a signal from the processing unit 61. The operation unit 53 is an operation means such as a touch panel, a keyboard, or a mouse. The communication unit 55 communicates with the terminal device of the speaker 5, the first terminal device 41, the second terminal device 42, the terminal device 19, etc. The input unit 57 is a terminal or the like for inputting data from the outside. The memory 59 stores a program executed by the processing unit 61. The processing unit 61 executes the program PRG1 (the program of the present embodiment) stored in the memory 59 and performs the processing of the automatic translation system 11 defined in the present embodiment. The processing unit 61 realizes the functions of the automatic translation unit 15 and the transmission unit 33.

[0023] FIG. 4 is a flowchart for explaining the processing flow of the interpretation business model 1 shown in FIG. 1. Each step will be described. Step ST11: The first voice 105 of the first language of the speaker 5 is input into the automatic interpretation system 11 via a microphone or a terminal device. The automatic interpretation system 11 outputs the input first voice 105 to the speaker 13.

[0024] Step ST12: The automatic interpretation system 11 transmits the first voice 105 of the speaker 5 to the first terminal device 41 of the first interpreter 31, the second terminal device 42 of the second interpreter 32, and the automatic interpretation unit 31.

[0025] Step ST13: The first terminal device 41 outputs the first voice received from the automatic interpretation system 11 to the first interpreter 31. The second terminal device 42 outputs the first voice received from the automatic interpretation system 11 to the second interpreter 32.

[0026] Step ST14: The second voice 61 of the second language 131 interpreted by the first interpreter 31 is input into the first terminal device 41. The second voice 62 of the second language 132 interpreted by the second interpreter 32 is input into the second terminal device 42. The automatic interpretation unit 15 of the automatic interpretation system 11 performs a process of interpreting the first voice 105 of the first language into the third voices 81 to 85 of a plurality of different third languages 71 to 75.

[0027] Step ST15: The transmission unit 33 of the automatic interpretation system 11 associates the first voice, the second voices 61 and 62, and the plurality of third voices 81 to 85 in a format that can be output by the terminal device 19 of the recipient 29 after selecting a language, and transmits them as the multilingual voice 99.

[0028] Step ST16: The terminal device 19 selects and outputs the voice in the language specified by the recipient 29 from the multilingual voice 99.

[0029] As described above, according to the interpretation business model 1, the first interpreter 31 and the second interpreter 32 can automatically perform interpretations into other languages that they cannot interpret by using the automatic interpretation unit 15. Therefore, an interpretation service corresponding to many languages can be provided. According to the present embodiment, interpretations into multiple languages can be provided with high precision and at low cost.

[0030] <Second Embodiment> FIG. 5 is a diagram for explaining the interpretation business model 1 according to the second embodiment of the present invention. As shown in FIG. 5, the interpretation business model 1 is used by a speaker 5 such as a lecturer, a first interpreter 31, a second interpreter 32, and a recipient 29, similar to the first embodiment.

[0031] Hereinafter, the interpretation business model 1 of the second embodiment will be described centering on the differences from the first embodiment. The automatic interpretation system 11 shown in FIG. 5 is the same as that described in the first embodiment except for the processing of the automatic interpretation unit 15. In the present embodiment, the automatic interpretation unit 15 inputs the second voice 61 interpreted by the first interpreter 31 from the first terminal device 41 instead of the first voice 105 of the speaker 5.

[0032] The automatic interpretation unit 15 performs a process of interpreting the second voice 61 into third voices 81 to 85 in a plurality of different third languages 71 to 75.

[0033] In the present embodiment, when the second voice 61 is a language with high versatility such as English, rich interpretation software from the second voice 61 to the third languages 71 to 75 can be used. Thereby, the interpretation accuracy can also be improved.

[0034] <Third Embodiment> FIG. 6 is a flowchart for explaining the interpretation business model 1 according to the third embodiment of the present invention. Hereinafter, the interpretation business model 1 of the third embodiment will be described centering on the differences from the first embodiment. The automatic translation unit 15 performs a process of translating the second voice 61 of the second language 131 from the first terminal device 41 into the third voices 81 to 85 of a plurality of different third languages 71 to 75. In addition, the automatic translation unit 15 performs a process of translating the second voice 62 of the second language 132 from the second terminal device 42 into the third voices 181 to 185 of the plurality of different third languages 71 to 75 described above.

[0035] The automatic translation unit 15 performs a process of back-translating the third voices 81 to 85 into the fourth multilingual voices 99 to 95 in the second language 131 respectively. The automatic translation unit 15 performs a process of back-translating the third voices 181 to 185 into the fourth voices 191 to 195 in the second language 132 respectively.

[0036] The automatic translation unit 15 generates a degree of match between the second voice 61 and the fourth multilingual voices 99 to 95. The automatic translation unit 15 generates a degree of match between the second voice 62 and the fourth voices 191 to 195. For each of the third languages 71 to 75, the automatic translation unit 15 processes to select and transmit the third voice with the higher degree of match among the two third voices of the third voices 81 to 85 and the third voices 181 to 185.

[0037] Thereby, among the two second languages 131 and 132, the one with higher translation accuracy to the third voices 81 to 85 of the third languages 71 to 75 can be selected, enabling high-precision translation.

[0038] <Fourth Embodiment> In this embodiment, the following functions are further added to the third embodiment. The automatic translation unit 15 generates translation accuracy information that enables the recipient to identify the third voice with a high degree of the above-described degree of match for the selected third voice in a plurality of different third languages 71 to 75. The transmission unit 33 transmits the translation accuracy information to the terminal device 19 in association with the third voice.

[0039] As a result, the recipient 29 can grasp the translation accuracy of a plurality of different third languages 71 to 75, and the recipient 29 who can understand multiple languages can select a highly accurate translated voice.

[0040] The present invention is not limited to the above-described embodiments. That is, those skilled in the art may make various changes, combinations, sub-combinations, and substitutions with respect to the components of the above-described embodiments within the technical scope of the present invention or its equivalent scope. For example, the number of the second and third languages is arbitrary. Also, the number of translators is arbitrary.

Industrial Applicability

[0041] The present invention is applicable to an automatic translation system that translates into multiple languages.

Explanation of Reference Numerals

[0042] 1... Translation business model 11... Automatic translation system 19... Recipient's terminal device 41... First terminal device 42... Second terminal device 61... Second voice 62... Second voice 81 to 85... Third voice 99... Multilingual voice 105... First voice

Claims

1. An input unit that inputs a second voice obtained by a translator translating a first voice in a first language by a speaker into a second language; An automatic translation unit that translates the second voice input by the input unit into third voices in a plurality of different third languages; A transmission unit that associates the first voice, the second voice, and the plurality of third voices in a form that allows a receiving destination to select a language and transmits the associated voices to the receiving destination An automatic translation system having the above components.

2. The input unit inputs a plurality of second voices obtained by translating the first voice into a plurality of different second languages, The transmission unit associates the first voice, the plurality of second voices, and the plurality of third voices in a form that allows a receiving destination to select a language and transmits the associated voices to the receiving destination The automatic translation system according to Claim 1.

3. The automatic translation unit For each of the plurality of second voices, translates the second voice into the third voice in the plurality of third languages, Generates a fourth voice obtained by back-translating each of the plurality of third voices into the second language, Detects the degree of coincidence between the plurality of fourth voices corresponding to the different second languages and the second voice, and selects, from among the plurality of third voices back-translated into the different second languages, the third voice with the highest degree of coincidence and causes the transmission unit to transmit it The automatic translation system according to Claim 2.

4. The automatic translation unit For the selected third voice in the plurality of different third languages, generates translation accuracy information that allows the receiving destination to specify the third voice with the highest degree of coincidence, The transmission unit transmits the translation accuracy information to the receiving destination in association with the third voice The automatic translation system according to Claim 3.

5. An input unit that inputs a second voice obtained by a translator translating a first voice in a first language by a speaker into a second language; An automatic translation unit that translates the first voice input by the input unit into third voices in a plurality of different third languages; A transmission unit that associates the first voice, the second voice, and the plurality of third voices in a form that allows a receiving destination to select a language and transmits the associated voices to the receiving destination An automatic translation system having the above components.

6. An input step of inputting a second voice obtained by a translator translating a first voice in a first language by a speaker into a second language; An automatic translation step of translating the second voice input in the input step into third voices in a plurality of different third languages; A transmitting step of associating the first voice, the second voice, and the plurality of third voices in a format that can be output by a receiving destination selecting a language, and transmitting the associated voices to the receiving destination A program for causing a computer to execute the steps above. **Claim 7** The input step inputs a plurality of second voices obtained by translating the first voice into a plurality of different second languages. The transmitting step associates the first voice, the plurality of second voices, and the plurality of third voices in a format that can be output by a receiving destination selecting a language, and transmits the associated voices to the receiving destination. The program according to claim 6. **Claim 8** The automatic translation step For each of the plurality of second voices, translates the second voice into a third voice in the plurality of third languages. Generates a fourth voice obtained by back-translating each of the plurality of third voices into the second language. Detects the degree of match between the plurality of fourth voices corresponding to the different second languages and the second voice, and selects, from among the plurality of third voices back-translated into the different second languages, the third voice with the highest degree of match and causes it to be transmitted to the transmitting step. The program according to claim 7. **Claim 9** The automatic translation step For the selected third voice in the plurality of different third languages, generates translation accuracy information that enables the receiving destination to identify the third voice with the highest degree of match. The transmitting step transmits the translation accuracy information to the receiving destination in association with the third voice. The program according to claim 8. **Claim 10** An input step of inputting a second voice obtained by a translator translating a first voice in a first language spoken by a speaker into a second language. An automatic translation step of translating the first voice input by the input step into third voices in a plurality of different third languages. A transmitting step of associating the first voice, the second voice, and the plurality of third voices in a format that can be output by a receiving destination selecting a language, and transmitting the associated voices to the receiving destination. A program for causing a computer to execute the steps above.

Images