JP6334589B2 - Fixed phrase creation device and program, and conversation support device and program - Google Patents

Description

  The present invention relates to a fixed phrase creation device and program, and a conversation support device and program.

  For example, when traveling abroad, local conversations are a cause for concern. Therefore, a paper medium called a pointing phrase book (registered trademark) and its application software (hereinafter simply referred to as “app”) are known (for example, non-patented) in order to support communication by conversation between people who speak different languages. Reference 1).

  This app includes a set of fixed phrases that contain a number of basic spoken phrases often spoken in a first language (for example, Japanese) and a second language (for example, English) for each situation that a speaker may encounter. Is prepared. The speaker searches for the conversation phrase in the first language from the fixed phrases displayed on the screen according to the scene encountered and the content to be asked, and speaks the speaker himself or herself in the second language written in the text. By tapping and reproducing and outputting native audio in the second language, it is possible to convey the will to the other party.

Travel pointing application “YUBISASHI” for 22 countries or more (free) [March 28, 2016 search], Internet <URL: http://www.yubisashi.com/ An app that travels with you>

  However, in the above-described conventional application, it may take time to search for a target conversation phrase from among a large number of fixed phrases, which may hinder smooth conversation. In the first place, the target conversation phrase may not be listed or stored in the standard phrase collection. For example, in a situation where a store employee or the like is serving a foreign customer, there may be a specific conversation phrase (such as a description of the store system or a recommended product) that is often spoken in that store. The (completely) standard phrase collection rarely contains such a unique conversation phrase for each store.

  Therefore, the present invention has been made in view of such circumstances, and by creating and registering a unique fixed phrase that is often used by speakers, it is possible to support communication through smooth conversation between speakers. An object of the present invention is to provide a regular phrase creation device, a conversation support device, and a conversation support program.

  In order to solve the above-mentioned problem, a fixed phrase creating device according to an aspect of the present invention includes an input unit for inputting speech in a speaker's first language, and a second language in which the content of the input speech is different from the first language. A translation unit that translates the content of the input language, a reverse translation unit that back-translates the translation result of the second language into the content of the first language based on the instructions of the speaker, and displays the content of the input speech and the translation result of the second language A bilingual display unit for registering, and a registration unit for registering the content of the input speech and the translation result in the second language as a standard phrase based on the instructions of the speaker. More specifically, the display unit may be configured to display a button for inputting a speaker's instruction. The “phrase” includes sentences, clauses, phrases, words, and numbers, and may include images or symbols accompanying them.

  In addition, a template display unit that displays a template of the fixed phrase is further provided, and the translation unit converts the content of the input speech into the content of the second language different from the first language using the template based on the instructions of the speaker. It is also suitable for translation.

  Furthermore, a conversation support apparatus according to an aspect of the present invention includes a fixed phrase creating apparatus according to the present invention, a storage unit that stores a set of fixed phrases including a plurality of fixed phrases, a phrase display unit that displays fixed phrases, and a fixed phrase And an output unit for outputting the translation result in the second language by voice.

  In addition, the fixed phrase creation program according to one aspect of the present invention is an input for inputting a voice in a first language of a speaker (not limited to a single type or a single type, but may be a plurality or a plurality of types; the same applies hereinafter). A translation unit that translates the content of the input speech into a content of a second language different from the first language, and a reverse translation that reversely translates the translation result in the second language into the content of the first language based on the instructions of the speaker A translation unit, a bilingual display unit that displays the content of the input speech and the translation result in the second language, and a registration for registering the set of the content of the input speech and the translation result in the second language as a standard phrase based on the instructions of the speaker It functions as a part.

  In addition, the conversation support program according to an aspect of the present invention includes a computer (not limited to a single type or a single type, but may be a plurality or a plurality of types; the same shall apply hereinafter), and an input unit for inputting speech of the speaker in the first language. And a translation unit that translates the content of the input speech into the content of the second language different from the first language, and the reverse translation that reversely translates the translation result of the second language into the content of the first language based on the instructions of the speaker A bilingual display unit for displaying the content of the input speech and the translation result in the second language, and a registration unit for registering the set of the content of the input speech and the translation result in the second language as a standard phrase based on the instructions of the speaker And a storage unit that holds a collection of fixed phrases including a plurality of fixed phrases, a phrase display unit that displays fixed phrases, and an output unit that outputs a translation result of the fixed phrases in the second language by voice Than is.

  According to the present invention, the content of the conversation phrase in the first language input by speech is translated into the content of the second language by speech translation processing, and further back-translated to the content of the first language as necessary. By displaying, the speaker can determine whether the translation result into the second language is correct. As a result, if the translation result into the second language is valid, a set of the content of the input speech in the first language and the translation result in the second language is created as one fixed phrase, and prior to the actual conversation, It can be registered in advance in the fixed phrase collection. Therefore, it is possible for a speaker to find and use a desired conversation phrase accurately and easily from a set of standard phrases in a conversation scene, thereby supporting communication by smooth conversation between speakers. be able to.

1 is a system block diagram schematically showing a preferred embodiment such as a network configuration related to a conversation support device including a fixed phrase creation device according to the present invention. FIG. It is a flowchart which shows an example of the process flow (part) in suitable one Embodiment of the conversation assistance apparatus containing the fixed phrase creation apparatus by this invention. (A) thru | or (D) are top views which show an example of the transition of the display screen in an information terminal. (A) And (D) is a top view which shows an example of the transition of the display screen in an information terminal.

  Hereinafter, embodiments of the present invention will be described in detail. The following embodiments are examples for explaining the present invention, and are not intended to limit the present invention only to the embodiments. The present invention can be variously modified without departing from the gist thereof. Furthermore, those skilled in the art can employ embodiments in which the elements described below are replaced with equivalent ones, and such embodiments are also included in the scope of the present invention. Furthermore, positional relationships such as up, down, left, and right shown as needed are based on the display shown unless otherwise specified. Furthermore, various dimensional ratios in the drawings are not limited to the illustrated ratios.

(Device configuration)
FIG. 1 is a system block diagram schematically showing a preferred embodiment such as a network configuration related to a conversation support device including a fixed phrase creation device according to the present invention. In this example, the conversation support apparatus 100 includes a server 20 that is electronically connected to the information terminal 10 used by the speaker via the network N (but is not limited to this).

  The information terminal 10 employs a user interface such as a touch panel and a display with high visibility, for example. The information terminal 10 here is a portable tablet terminal device including a mobile phone represented by a smartphone having a communication function with the network N. The information terminal 10 further includes a processor 11, a storage resource 12, a voice input / output device 13, a communication interface 14, an input device 15, a display device 16, and a camera 17. In addition, the information terminal 10 operates by an installed conversation support application (at least a part of the conversation support program according to the embodiment of the present invention), thereby including the conversation support including the fixed phrase creating device according to the embodiment of the present invention. It functions as part or all of the device.

  The processor 11 includes an arithmetic logic unit and various registers (program counter, data register, instruction register, general-purpose register, etc.). Further, the processor 11 interprets and executes a conversation support application that is one of the programs P10 stored in the storage resource 12, and performs various processes. The conversation support application as the program P10 can be distributed from the server 20 through the network N, for example, and may be installed and updated manually or automatically.

  The network N includes, for example, a wired network (a short-range communication network (LAN), a wide-area communication network (WAN), a value-added communication network (VAN), etc.) and a wireless network (mobile communication network, satellite communication network, Bluetooth ( Bluetooth (registered trademark)), WiFi (Wireless Fidelity), HSDPA (High Speed Downlink Packet Access), etc.).

  The storage resource 12 is a logical device provided by a storage area of a physical device (for example, a computer-readable recording medium such as a semiconductor memory), and an operating system (OS) program, a driver program used for processing of the information terminal 10, Stores various data. Examples of the driver program include an input / output device driver program for controlling the audio input / output device 13, an input device driver program for controlling the input device 15, and a display device driver program for controlling the display device 16. Can be mentioned. Furthermore, the voice input / output device 13 is, for example, a general microphone and a sound player capable of reproducing sound data.

  The communication interface 14 provides a connection interface with the server 20, for example, and is configured from a wireless communication interface and / or a wired communication interface. The input device 15 provides an interface for accepting an input operation by a tap operation such as an icon, a button, a virtual keyboard, or a text displayed on the display device 16. Various input devices to be attached can be exemplified.

  The display device 16 provides various information to the speaker as an image display interface, and examples thereof include an organic EL display, a liquid crystal display, and a CRT display. The camera 17 is for capturing still images and moving images of various subjects.

  The server 20 is constituted by, for example, a host computer having high arithmetic processing capability, and expresses a server function when a predetermined server program operates on the host computer. It is composed of a single or a plurality of host computers that function as a recognition server, a translation server, and a speech synthesis server (in the figure, it is indicated by a single, but is not limited to this). Each server 20 includes a processor 21, a communication interface 22, and a storage resource 23.

  The processor 21 is composed of an arithmetic and logic unit for processing arithmetic operations, logical operations, bit operations and the like and various registers (program counter, data register, instruction register, general-purpose register, etc.), and is stored in the storage resource 23. P20 is interpreted and executed, and a predetermined calculation processing result is output. The communication interface 22 is a hardware module for connecting to the information terminal 10 via the network N. For example, the communication interface 22 is a modulation / demodulation device such as an ISDN modem, an ADSL modem, a cable modem, an optical modem, or a soft modem.

  The storage resource 23 is a logical device provided by, for example, a storage area of a physical device (a computer-readable recording medium such as a disk drive or a semiconductor memory), and each includes one or a plurality of programs P20, various modules L20, and various databases. D20 and various models M20 are stored. The storage resource 23 also stores a plurality of fixed phrases prepared in advance, history data of input speech, data for various settings, and the like.

  The program P20 is the above-described server program that is the main program of the server 20. In addition, the various modules L20 perform a series of information processing related to requests and information transmitted from the information terminal 10, so that they are appropriately called and executed during the operation of the program P10 (moduleized subprograms). ). Examples of the module L20 include a speech recognition module, a translation module, and a speech synthesis module.

  The various databases D20 include various corpora necessary for speech translation processing (for example, a speech corpus, a character (vocabulary) corpus for a plurality of languages including at least two languages (first language and second language), Dictionary, bilingual dictionary, bilingual corpus, etc.) database, voice database, management database for managing information about speakers (users of conversation support apps, etc.), text as a set of fixed phrases including a plurality of fixed phrases, and An audio database etc. are mentioned. Examples of the various models M20 include acoustic models and language models used for speech recognition. As described above, the storage resource 23 functions as a “storage unit”.

(First embodiment)
An example of processing operations and operations in the conversation support apparatus 100 configured as described above will be described below. FIG. 2 is a flowchart showing an example of (a part of) the processing flow in the conversation support apparatus 100. 3A to 3D are plan views illustrating an example of display screen transition in the information terminal. Here, a scene where a conversation phrase used when a store clerk who speaks Japanese (first language) (store employee) serves a foreign customer who speaks English (second language) is created as a standard phrase. (However, the language and situation are not limited to this.)

  First, when the store clerk starts the conversation support application (step SU1), the language selection for selecting the customer language on the display device 16 of the information terminal 10 by the processor 21 of the server 20 and the processor 11 of the information terminal 10 is performed. A screen is displayed (FIG. 3A; step SJ1). This language selection screen includes a Japanese text T1 for prompting the store clerk to ask the customer about the language, an English text T2 for asking the customer about the language, and a plurality of typical languages assumed here (here Then, a language button 31 indicating English, Chinese (for example, two types depending on the typeface), and Hangul) is displayed. Further below that, a cancel button B1 for closing the language selection screen and ending the conversation support application is also displayed. This screen assumes a scene in which a store clerk and a customer actually have a conversation through speech translation.

  Here, since the fixed phrase is created in advance before the actual conversation, the store clerk selects English as the customer language. When the customer language is selected, the processor 21 of the server 20 and the processor 11 of the information terminal 10 display Japanese and English voice input standby screens on the display device 16 as home screens (FIG. 3B). Step SJ2). On this voice input standby screen, Japanese text T3 asking which of the store clerk or customer speaks, an input button 32a for inputting Japanese voice, and an English voice input. An input button 32b is displayed.

  Also, on this voice input standby screen, a voice button 33 for selecting a list display of a plurality of preset canned sentences, a language selection button 34 for manually selecting a language of a conversation person, History button 35 for selecting the history display of the voice input contents made so far, a list of fixed phrases including a plurality of fixed phrases prepared in advance are displayed, and a desired fixed phrase is selected from among them and a conversation is performed A suggestion button 36 for executing a suggestion function that allows the user to proceed and a setting button 37 for performing various settings of the conversation support application are also displayed.

  Next, in the voice input standby screen shown in FIG. 3B, when the clerk taps the Japanese input button 32a and selects the Japanese voice input, the voice input screen that accepts the utterance contents in Japanese of the clerk; (FIG. 3C). When this voice input screen is displayed, voice input from the voice input / output device 13 is enabled. Further, on this voice input screen, a text T2 for prompting the store clerk to input voice, a microphone design 38 indicating that the voice input state is set, and an input switching button B2 for switching to text input are displayed. Further, a cancel button B1 is also displayed on this voice input screen, and when this is tapped, the conversation support application is terminated, or the voice input standby screen (FIG. 3B) is returned to perform voice input again. Can do.

  In this state, when the store clerk utters a frequently used conversation phrase (for example, “I ’m sorry. Please wait for a moment because it ’s full.”) A multi-circular pattern 39 schematically and dynamically representing is displayed, and the voice input level is visually fed back to the speaker. Then, when the utterance is finished and the microphone design 38 is tapped, the processor 11 finishes accepting the utterance content. The processor 11 of the information terminal 10 generates an audio signal based on the audio input, and transmits the audio signal to the server 20 through the communication interface 14 and the network N. As described above, the information terminal 10 itself, or the processor 11 and the voice input / output device 13 function as an “input unit”.

  Next, the processor 21 of the server 20 receives the voice signal through the communication interface 22 and performs voice recognition processing. At this time, the processor 21 calls the necessary module L20, database D20, and model M20 (speech recognition module, Japanese speech corpus, acoustic model, language model, etc.) from the storage resource 23, and obtains “sound” of the input speech. Convert to "reading" (character). As described above, the processor 21 or the server 20 functions as a “voice recognition server” as a whole. In addition, the processor 21 stores the recognized content in the storage resource 23 (in an appropriate database as necessary) as voice input history data.

  Subsequently, the processor 21 proceeds to multilingual translation processing for translating the recognized “reading” (characters) of the speech into a plurality of other languages. Here, since English is selected as the partner language, the processor 21 sends the necessary modules L20 and database D20 (translation module, Japanese character corpus, Japanese dictionary, English dictionary, Japanese / English) from the storage resource 23. English bilingual dictionary, Japanese / English bilingual corpus, etc.), and “recognition” (character string) of the input speech that is the recognition result is appropriately sorted and converted into Japanese phrases, clauses, sentences, etc. Extract English corresponding to the results, rearrange them according to English grammar and convert them into natural English phrases, clauses, sentences, etc. As described above, the processor 21 also functions as a “translation unit” that translates the content of the input speech into the content of the second language (English) that is different from the first language (Japanese). It also functions as a “server”. If the input voice is not correctly recognized, the voice can be re-input (not shown). The processor 21 can also store those Japanese and English phrases, clauses, sentences, and the like in the storage resource 23.

  Further, during this translation processing, the processor 21 transmits the recognition result of the input speech (contents of the input speech) to the information terminal 10, and the processor 11 converts the recognition result into the translation processing shown in FIG. Displayed as Japanese text T5 on the middle screen. As the text T5, the recognition result of the input voice may be displayed as it is, or it corresponds to the content of the actual input voice from the Japanese conversation corpus stored in the storage resource 23 in advance. May be displayed. Further, on this translation processing screen, a Japanese text T6 indicating that the translation processing is being performed, and a circular design 40 displayed so that a part of the arc is rotated to indicate that the translation processing is being performed. Is also displayed (step SJ3 so far).

  Next, when the multilingual translation processing is completed, the processor 21 proceeds to speech synthesis processing (step SJ4). At this time, the processor 21 calls the necessary module L20, database D20, and model M20 (speech synthesis module, English speech corpus, acoustic model, language model, etc.) from the storage resource 23, and the English phrase that is the translation result, Convert clauses, sentences, etc. to natural speech. As described above, the processor 21 also functions as a “speech synthesizer”, and the server 20 also functions as a “speech synthesizer” as a whole.

  Next, the processor 21 generates a text signal for text display based on the translation result in English (which may be a corresponding English conversation corpus), and transmits the text signal to the information terminal 10. Upon receiving the text signal, the processor 11 translates the Japanese text T5 displayed on the translation-in-progress screen of FIG. 3D and the text T6 of the translation result (translation) in English into the translation shown in FIG. Display on the result display screen. The translation result display screen also displays a Japanese text T7 for explaining that the content indicated by the text T5 is transmitted to the customer. As described above, the processors 11 and 21 and the display device 16 function as a “translation display unit”.

  Various buttons that can be operated by the speaker are displayed on the translation result display screen. That is, in the screen area between the texts T5 and T6, there is a check button B3 for returning to the home screen in FIG. 3B and the content of the translation result text T6 in English for back-translation into Japanese. A reverse translation button B4 is displayed. Further, on this translation result display screen, a mistranslation notification button B5 for reporting an error in the translation result, a voice output button B6 for reproducing the contents of the parallel translation text T6, and a voice input in FIG. A re-input button B7 for returning to the screen and starting the speech again is displayed (step SJ5 so far).

(Reverse translation)
Here, when the correctness of the translation result in English indicated by the text T6 is unknown, the speaker can reverse-translate the contents into Japanese and determine the validity. That is, when the store clerk taps the reverse translation button B4 (step SU3; speaker's instruction), the processor 21 that receives the selection signal from the processor 11 of the information terminal 10 performs the translation result in English by the multilingual translation process described above. 4 is back-translated into Japanese, and the back-translation result text T8 in Japanese is displayed on the back-translation result display screen shown in FIG. Step SJ6). As described above, the processor 21 also functions as a “reverse translation unit” that back-translates the translation result in the second language (English) into the content of the first language (Japanese).

  In this reverse translation result display screen, the contents of the input speech in Japanese indicated by the text T5 and the English indicated by the text T6 are displayed together with a return button B8 for redisplaying the translation result display screen shown in FIG. A registration button B9 for registering a set of translation results by is registered as a standard phrase. That is, the store clerk is synonymous with the content of the input speech in Japanese indicated by the text T5 and the result of reverse translation in Japanese indicated by the text T8 including a slight difference in expression ("little" and "for a while"). Therefore, it is judged that the translation result in English indicated by the text T6 is appropriate (translation accuracy or suitability is high), and by tapping the registration button B9, these Japanese and English contents are used as standard phrases. You can register.

(Regular phrase registration)
Thus, when the store clerk taps the registration button B9 (step SU4; speaker's instruction), the processor 21 that has received the selection signal from the processor 11 of the information terminal 10 accesses a set of fixed phrases that is one of the databases D20. The set of the input speech content in Japanese indicated by the text T5 and the translation result (conversation phrase) in English indicated by the text T6 is registered (stored) in the standard phrase collection. As described above, the processor 21 also functions as a “registration unit”. Further, the processor 21 transmits a display signal of a list of fixed phrases including the registered fixed phrases to the information terminal 10, and the processor 11 that has received the signal displays the collection of fixed phrases, for example, in FIG. It is displayed on the standard phrase book list screen (step SJ7). As described above, the processors 11 and 21 also function as “phrase display units”.

  This fixed phrase list screen is the same as that displayed when the suggest button 36 shown in FIG. 3B is tapped (however, it may of course be different). The configuration of the standard phrase book is not particularly limited, and the standard phrase book list screen includes, for example, a plurality of appropriate heading tabs R1 to R4, etc. A plurality of fixed phrase texts T40 to T46 are displayed separately for each of “greeting”, “order”, “recommendation”, and the like. In each of these fixed phrases, the contents of Japanese and English (for example, texts T5 and T6) are written together. The fixed phrases stored in the heading tabs R1 to R4 are switched (turned) by, for example, tapping the desired heading tabs R1 to R4 or wiping the screen of the display device 16 by the speaker. Can browse. Furthermore, although illustration is abbreviate | omitted, each fixed phrase can also be selected by operation, such as long press, and can be deleted, or it can also be moved suitably between heading tabs R1-R4.

  In addition, by tapping a desired phrase, for example, the previously synthesized English voice can be reproduced and output. In this case, the processor 21 generates a voice signal for voice output based on the synthesized voice, and transmits the voice signal to the information terminal 10. The processor 11 that has received the sound signal outputs (reads out) the sound of the content of the text T5 using the sound input / output device 13 (output unit). After these operations, the store clerk can return to the home screen of FIG. 3B by tapping the check button B3, or can appropriately terminate the application (step SU5).

  The outline of the process when another button displayed on the translation result display screen shown in FIG. 4A is selected and tapped is as follows.

(Notice of mistranslation)
A clerk who confirms the reverse translation result in Japanese and determines that the accuracy of the English translation result is insufficient or mistranslation can notify the server 20 by tapping the mistranslation notification button B5. . In this case, the processor 21 stores that the English translation result is incorrect in association with the contents of the input speech previously stored in the storage resource 23.

(Audio output)
In addition, the clerk confirming the reverse translation result in Japanese and judging that the English translation result is correct or appropriate, taps the voice output button B6, thereby performing the same process as the voice output described above, and in English. The contents of the translation result text T5 can be reproduced.

(Re-enter)
Further, the clerk can return to the voice input screen of FIG. 3C and repeat the utterance without confirming the reverse translation result or after confirming, by tapping the re-input button B7.

(Second Embodiment)
In the processing in the second embodiment, after the voice input screen shown in FIG. 3B is displayed (step SJ2) and before the utterance (step SU1), the speaker presses the suggest button 36 shown in FIG. 3B. The process is the same as the process in the first embodiment, except that a set of fixed phrases is displayed once by tapping and a desired pattern is selected from the patterns of fixed phrases included therein.

In other words, there is a set of standard phrases (for example, in the customer service situation, “I ’m sorry. Please please.” “Today ’s recommended menu is ~.”, “~ Business hours are ~.”) and template phrases) are provided such that they are displayed on the stationery phrasebook list screen example shown in FIG. 4 (D). The configuration of the template phrase collection is not particularly limited, and the template phrase collection list screen includes, for example, appropriate plural heading tabs H1 to H4 (for example, “recently used phrases”, “customer initial movement”, “ A plurality of template phrase texts H40 to H46 are displayed separately for each “greeting”, “order”, “recommendation”, and the like. As described above, the processors 11 and 21 and the display device 16 also function as a “model display unit”.

  When the store clerk selects a desired model phrase by tapping or the like before the utterance (step SU2), the clerk returns to the home screen of FIG. 3B (may return after tapping the check button B3), When the content corresponding to the selected template phrase is uttered, the processor 21 performs translation processing using various corpora along the template phrase (steps SJ3 to SJ5).

  According to the conversation support device 100 including the fixed phrase creation device configured as described above, and the fixed phrase creation program and the conversation support program, the content of the conversation phrase in Japanese (first language) input by voice is spoken. The content is translated into English (second language) content by translation processing, and further back-translated into Japanese content as necessary. Thereby, the store clerk (speaker) can determine whether or not the translation result into English is correct.

  As a result, if the translation result into English is valid, a pair of the input speech content in Japanese and the translation result in English (for example, texts T5 and T6) is created as one fixed phrase and prior to the actual conversation. And can be registered in advance in the standard phrase collection. Therefore, it is possible for a speaker to find and use a desired conversation phrase accurately and easily from a set of standard phrases in a conversation scene, thereby supporting communication by smooth conversation between speakers. be able to. In addition, there is an advantage that by selecting a template phrase before the input speech translation process, the accuracy of translation can be improved, and a standard phrase can be created more easily and efficiently.

  Note that, as described above, each of the above embodiments is an example for explaining the present invention, and is not intended to limit the present invention to the embodiment. The present invention can be variously modified without departing from the gist thereof. For example, those skilled in the art can replace the resources (hardware resources or software resources) described in the embodiments with equivalents, and such replacements are also included in the scope of the present invention.

  Further, for example, when the content of the spoken input speech is as short as a word, reverse translation may not be necessary, so the registration button B9 is also displayed on the translation result display screen shown in FIG. You may do it. Further, in step SJ3 of the flow shown in FIG. 2, for example, when the reverse translation process of step SJ6 is performed in advance and the reverse translation button B4 is tapped, only the reverse translation result may be displayed in step SJ6. That is, in this case, the reverse translation process may be performed in advance, and the reverse translation result may be displayed only when the speaker gives an instruction. Furthermore, the speech synthesis process may be performed when the speech output button B6 is tapped in step SU3 without performing the speech synthesis process (step SJ4) between steps SJ3 and SJ5 of the flow shown in FIG.

  Moreover, although the example which performs each process, such as speech recognition, translation, speech synthesis, by server 20, was described, you may comprise so that these processes may be performed in the information terminal 10. FIG. In this case, the module L20 used for these processes may be stored in the storage resource 12 of the information terminal 10. Furthermore, a database D20 that is a voice database and / or a model M20 such as an acoustic model may also be stored in the storage resource 12 of the information terminal 10. As described above, the fixed phrase creation device may not include the network N and the server 20. Of course, a gateway server for converting a communication protocol between the information terminal 10 and the network N may be interposed. The information terminal 10 is not limited to a portable device, and may be a desktop personal computer, a notebook personal computer, a tablet personal computer, a laptop personal computer, or the like.

  According to the present invention, since communication through smooth conversation between speakers can be supported, the present invention provides, for example, a program, a device, and a device in the field of providing services related to conversation between people who cannot understand each other's language. It can be widely used for activities such as designing, manufacturing, providing and selling systems and methods.

10 Information terminal 11 Processor 12 Storage resource 13 Voice input / output device 14 Communication interface 15 Input device 16 Display device 17 Camera 20 Server 21 Processor 22 Communication interface 23 Storage resource 31 Language buttons 32a, 32b Input button 33 Voice button 34 Language selection Button 35 History button 36 Suggest button 37 Setting button 38 Microphone design 39 Multiple circular design 40 Circular design 100 Conversation support device B1 Cancel button B2 Input switching button B3 Check button B4 Reverse translation button B5 Mistranslation notification button B6 Audio output button B7 Re-input button B8 Back button B9 Registration button D20 Database H1-H4 Heading tabs H40-H46 Template phrase text L20 Module M20 Model N Network P 0, P20 program R1~R4 heading tab T1~T8 text of text T40~T46 boilerplate phrases

Claims (6)

An input unit for inputting the voice of the speaker in the first language;
A translation unit that translates the content of the input speech into the content of a second language different from the first language;
A back translation unit that back translates the translation result of the second language into the content of the first language based on a reverse translation instruction by the speaker;
Displaying the content of the input speech and the translation result in the second language on the same screen so that the speaker can visually recognize the content of the input speech and the translation result in the second language, and the speaker A bilingual display unit for displaying the content of the input speech and the reverse translation result in the second language on the same screen so that the content of the input speech and the reverse translation result in the second language are visible.
Based on the registration instruction by the speaker who determined that the translation result is appropriate from the content of the input speech and the reverse translation result, a set of phrases of the content of the input speech and the translation result in the second language A registration unit to register as,
A template display for displaying a template of the fixed phrase;
With
The translation unit selects a specific model phrase from which a part of the word is omitted from the template of the standard phrase by the speaker, and omits the phrase in the specific model by the speaker. When a speech having a content supplemented with a part of the written word is input, the speech content is changed from the first language by using a corpus along the selected specific template phrase. Translate into two languages,
Fixed phrase creation device. The display unit displays a button for inputting a reverse translation instruction by the speaker, and a button for inputting a registration instruction by the speaker.
The fixed phrase creation device according to claim 1. The display unit displays a template phrase list screen including a plurality of template phrases, and the template phrase list screen displays text of a plurality of template phrases for each of a plurality of appropriate headings. Displayed,
The fixed phrase creation device according to claim 1 or 2. The fixed phrase creation device according to any one of claims 1 to 3,
A storage unit that holds a collection of fixed phrases including a plurality of fixed phrases;
A phrase display section for displaying the fixed phrase;
An output unit for outputting the translation result of the second language in the fixed phrase by voice;
A conversation support device. Computer
An input unit for inputting the voice of the speaker in the first language;
A translation unit for translating the content of the input speech into the content of a second language different from the first language;
A reverse translation unit that back-translates the translation result of the second language into the content of the first language based on a reverse translation instruction by the speaker;
Displaying the content of the input speech and the translation result in the second language on the same screen so that the speaker can visually recognize the content of the input speech and the translation result in the second language, and the speaker A bilingual display unit that displays the content of the input speech and the result of reverse translation in the second language on the same screen so that the content of the input speech and the result of reverse translation in the second language are visible.
Based on the registration instruction by the speaker who determined that the translation result is appropriate from the content of the input speech and the reverse translation result, a set of phrases of the content of the input speech and the translation result in the second language Function as a registration unit for registering as a template display unit for displaying a template of the fixed phrase,
The translation unit selects a specific model phrase from which a part of the word is omitted from the template of the standard phrase by the speaker, and omits the phrase in the specific model by the speaker. When a speech having a content supplemented with a part of the written word is input, the speech content is changed from the first language by using a corpus along the selected specific template phrase. Translate into two languages,
Fixed phrase creation program. Computer
An input unit for inputting the voice of the speaker in the first language;
A translation unit for translating the content of the input speech into the content of a second language different from the first language;
A reverse translation unit that back-translates the translation result of the second language into the content of the first language based on a reverse translation instruction by the speaker;
Displaying the content of the input speech and the translation result in the second language on the same screen so that the speaker can visually recognize the content of the input speech and the translation result in the second language, and the speaker A bilingual display unit that displays the content of the input speech and the result of reverse translation in the second language on the same screen so that the content of the input speech and the result of reverse translation in the second language are visible.
Based on the registration instruction by the speaker who determined that the translation result is appropriate from the content of the input speech and the reverse translation result, a set of phrases of the content of the input speech and the translation result in the second language As a registration department,
A template display for displaying a template of the fixed phrase;
A storage unit for holding a collection of fixed phrases including a plurality of fixed phrases;
A phrase display unit that displays the fixed phrase; and an output unit that outputs a translation result of the fixed phrase in the second language by voice;
Function as
The translation unit selects a specific model phrase from which a part of the word is omitted from the template of the standard phrase by the speaker, and omits the phrase in the specific model by the speaker. When a speech having a content supplemented with a part of the written word is input, the speech content is changed from the first language by using a corpus along the selected specific template phrase. Translate into two languages,
Conversation support program.