JP2005107595A - Automatic translation device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an automatic translation device that clarifies each speaker, and produces a translation output adapted to a situation even when a conversation is conducted among three or more persons. <P>SOLUTION: The device uses an automatic translation device 1 equipped with an automatic translation part 2, a communication part 7, and a display part 6. The automatic translation part 2 translates a first language into a second language, and outputs it as a first translation data. The communication part 7 transmits the first translation data and a first identification data that identifies the automatic translation device 1, to a conversational partner's automatic translation device. The display part 6 associates the first language data with the first identification data and displays them. The communication part 7 receives a second translation data and a second identification data that identifies the partner's automatic translation device, from the partner's automatic translation device. The automatic translation part 2 translates the second translation data into the first language if the second translation data is not the first language, and outputs it anew as the second translation data. The display part 6 associates the second translation data with the second identification data, and displays them. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an automatic translation apparatus, and more particularly to an automatic translation apparatus with an improved user interface.

  An automatic translation device that automatically translates a language into a different language is known. Such a device is designed for use on a one-to-one basis by two users who speak different languages. In that case, a method of alternately using one automatic translation device or a method of using each device having a terminal and communicating with two devices is adopted.

As such a technique, Japanese Patent Application Laid-Open No. 2000-112939 discloses a technique of a multilingual translation apparatus. This technique is to provide a device that has a simple configuration, can easily handle a plurality of languages, and allows users of three or more languages to talk at the same time.
The multilingual translation device of this technology interprets between a plurality of callers having different languages. An input unit, a language processing unit, a common encoding unit, a transmission unit, a reception unit, a common decoding unit, a language processing unit, and an output unit are provided. The input means inputs the caller's input language and converts it into digital data. The language processing means shapes the output of the input means. The common encoding means converts the output of the language processing means into a common code. The transmission means transmits the common code converted by the common encoding means. The receiving means receives a signal from the transmission side. The common decoding means converts the common code output from the receiving means into the language data of the caller. The language processing means shapes the language data combined by the common compounding means. The output means notifies the caller of the digital data output from the language processing means.

  Here, when a user interface similar to that for two people is used, when a conversation is performed between three or more people, it is conceivable that there is a situation where it is not possible to know which statement is who. In addition, there may be situations where it is difficult to talk to only some of the people. Furthermore, there may be a situation in which it is desired to confirm whether or not his / her speech is properly communicated to the other device.

  An automatic translation device that can clarify a speaker even when a conversation is performed between three or more people is desired. An automatic translation apparatus capable of performing translation output suitable for the conversation situation is desired. There is a need for an automatic translation device that can talk only to some of a plurality of people. There is a need for an automatic translation device that can confirm whether or not his / her speech is properly communicated to the other device.

JP 2000-1112939 A

  Accordingly, an object of the present invention is to provide an automatic translation apparatus capable of clarifying a speaker even when a conversation is performed between three or more people.

  Another object of the present invention is to provide an automatic translation apparatus capable of outputting a translation suitable for a conversation situation even when a conversation is performed between three or more people.

  Still another object of the present invention is to provide an automatic translation apparatus capable of having a conversation with only a part of them even when a conversation is performed between three or more people.

  Another object of the present invention is to provide an automatic translation apparatus capable of confirming whether or not his / her speech is properly communicated to a partner apparatus even when a conversation is performed between three or more people. is there.

  Hereinafter, means for solving the problem will be described using the numbers and symbols used in the best mode for carrying out the invention. These numbers and symbols are added in parentheses in order to clarify the correspondence between the description of the claims and the best mode for carrying out the invention. However, these numbers and symbols should not be used for interpreting the technical scope of the invention described in the claims.

Therefore, in order to solve the above problem, the automatic translation apparatus of the present invention is an automatic translation apparatus (1 / 1a) that uses a person who speaks a different language as a partner. And an automatic translation part (2), a communication part (7), and a display part (6) are comprised. The automatic translation unit (2) translates the first original language data (Japanese) indicating the first language (Japanese) into the second language (English) and outputs the first translation data (English). The communication unit (7) uses the first translation data (English) and the first identification data for identifying the automatic translation device (1) as at least one of the plurality of other automatic translation devices (1b / 1c / 1d). To the other party's automatic translation apparatus (1c). The display unit (6) displays the first language data (Japanese) and the first distinction data (you) based on the first identification data in association with each other. The communication unit (7) receives the second identification data for identifying the partner automatic translation device (1c) and the second translation data (English) from the partner automatic translation device (1c). If the second translation data (English) is not in the first language (Japanese), the automatic translation unit (2) translates the second translation data into the first language (Japanese) and re-enters the second translation data (Japanese). Output. The display unit (6) displays the second translation data (Japanese) and the second distinction data (Pierre) based on the second identification data in association with each other.
Here, the distinction data (including the first distinction data and the second distinction data) is such that each of a plurality of other automatic translation apparatuses (or their users) can be visually recognized at a glance (can be distinguished from each other). Indicates the symbol or name set in. The distinction data is exemplified by the user's name, nickname, ID number, figure, and color.

  In the above automatic translation apparatus, the communication unit (7) further transmits the first original language data (Japanese) to the counterpart automatic translation apparatus (1c). On the other hand, the second original data (French) indicating the third language (French) before translation of the second translation data (English) is received from the counterpart automatic translation apparatus (1c). The display unit (6) further displays the second original language data (French) and the second distinction data (Pierre) in association with each other.

  In the automatic translation apparatus, the display unit (6) displays the second original data (French) and the second distinction data (Pierre), and then displays the second translation data (Japanese) and the second distinction data (Pierre). ) And.

  In the automatic translation apparatus, the first original language data (Japanese) is voice recognition data obtained by voice recognition of a human voice.

  The automatic translation apparatus further includes a lamp (19) that is provided at a position that can be visually recognized from the outside and that is lit in a different color based on the first identification data and the second identification data.

  In the above automatic translation apparatus, the communication unit (7) identifies the plurality of translation data (English) transmitted from the other plurality of automatic translation apparatuses (1b / 1c / 1d) and the other plurality of automatic translation apparatuses. A plurality of identification data to be received. The automatic translation unit (2) translates and outputs a plurality of translation data (English) into the first language (Japanese). The display unit (6) includes a plurality of pieces of translation data translated into the first language (Japanese) and a plurality of pieces of discrimination data (John / Pierre / Zenyu) generated based on the plurality of pieces of identification data. The corresponding one of is displayed.

  In the above automatic translation apparatus, the display unit (6) associates each of the plurality of translated translation data with a corresponding one of the plurality of distinction data (John / Pierre / Zenyu), Display in the order received in (7).

  In the above automatic translation apparatus, the display unit (6) may display other parts of the plurality of translation data when the display screen (16a) is filled with a part of the plurality of translation data and a predetermined condition is satisfied. indicate. The predetermined condition is the input of a signal from the outside instructing the display of a predetermined time or the display of other parts of the plurality of translation data.

  In the automatic translation apparatus, the display unit (6) sets a display frame (51-1 / 51-2 / 51-3) corresponding to each of the plurality of identification data, and the plurality of translated data translated. Are associated with a corresponding one of a plurality of distinction data (John / Pierre / Zenyu) and displayed in a corresponding display frame (51-1, 51-2 / 51-3).

  In the automatic translation device, each of the plurality of pieces of distinction data (John / Pierre / Zenyu) includes an identification figure (59-1 / 59-3 / 59-4).

  In the automatic translation apparatus, the display unit (6) divides the plurality of identification data into a plurality of groups, and displays display frames (54-1 / 54-2, 56-1 / corresponding to each of the plurality of groups. 56-2) is set. Then, each of the plurality of translated data and the corresponding one of the plurality of discriminating data (John / Pierre / Zenyu) are associated with each other, and the corresponding display frames (54-1 / 54-2, 56 -1 / 56-2).

  In the automatic translation device, the display unit (6) displays an identification graphic (59-1 / 59-2 / 59-3 / 59-4) corresponding to each of the plurality of identification data. When translation data is received from one of the plurality of identification data, the display state of the corresponding identification graphic (59-3 / 59-4) is changed. When the identification figure (59-4) is selected, the translation data (58-3) and the corresponding one of the plurality of distinction data (Zenyu) are displayed in association with each other.

In the above automatic translation device,
The display unit (6) displays an identification graphic (59-1 / 59-3 / 59-4) corresponding to each of the plurality of identification data, and based on the input of an external signal, the identification graphic (59-1 / 59-3 / 59-4), when the translation data is received from one of the plurality of identification data, the corresponding identification graphic (59-1) and the translation data (51-1) '') And a corresponding one (John) of the plurality of pieces of distinction data are displayed in association with each other.

  In the above automatic translation apparatus, the display unit (6) sets at least one of a character font and a character color corresponding to each of the plurality of identification data. Then, each of the plurality of translated data translated and the corresponding one of the plurality of distinction data are associated with each other and displayed at least one of the corresponding character font and character color.

  In order to solve the above problems, an automatic translation method using the automatic translation apparatus of the present invention includes steps (a) to (d). (A) The step includes: first original language data (Japanese) indicating a first language (Japanese); first identification data (you) based on first identification data for identifying an automatic translation device (1 / 1a); Are related and displayed on the display screen (16 / 16a). (B) The step includes converting the first translation data (English) translated into the second language (English) and the first identification data into at least one of the plurality of other automatic translation devices (1b / 1c / 1d). To the other party automatic translation apparatus (1c). In the step (c), second identification data for identifying the partner automatic translation apparatus (1c) and second translation data (English) are received from the partner automatic translation apparatus (1c). In the step (d), if the second translation data (English) is not the first language (Japanese), the second translation data (Japanese) is translated into the first language (Japanese) to be the second translation data (Japanese). In addition, it is displayed on the display screen (16a) in association with the second distinction data (Pierre) based on the second identification data.

  In the above automatic translation method, (c) step includes (c1) a plurality of translation data transmitted from a plurality of other automatic translation devices (1b / 1c / 1d), and a plurality of other automatic translation devices (1b / Receiving a plurality of identification data identifying 1c / 1d). (D) The step includes (d1) a plurality of pieces of translation data (Japanese) translated into the first language (Japanese) and a plurality of pieces of discrimination data (John / And displaying on the display screen (16a) in association with a corresponding one of (Pierre / Zenyu).

  In the automatic translation method, (d1) step associates each of a plurality of translated data (d11) with a corresponding one of a plurality of distinction data (John / Pierre / Zenyu), (C1) A step of displaying on the display screen (16a) in the order received in the step is provided.

  In the automatic translation method described above, the step (d11) includes a step (d111) where the display screen (16a) is filled with a part of a plurality of pieces of translation data, and when the predetermined condition is satisfied, A step of displaying the portion on the display screen (16a). The predetermined condition is the input of a signal from the outside instructing the display of a predetermined time or the display of other parts of the plurality of translation data.

  In the automatic translation method described above, the step (d1) includes (d12) associating each of a plurality of translated translation data with a corresponding one of a plurality of distinction data (John / Pierre / Zenyu), A step of displaying on a corresponding one of the display frames (51-1 / 51-2 / 51-3) set in advance corresponding to each of the plurality of identification data on the display screen (16a).

  In the automatic translation method, each of the plurality of pieces of discrimination data includes an identification figure (59-1 / 59-3 / 59-4).

  In the automatic translation method described above, the step (d1) includes (d13) associating each of the translated plural translation data with a corresponding one of the plural discriminating data (John / Pierre / Zenyu), A step of displaying on the corresponding display frame (54-1 / 54-2, 56-1 / 56-2) of the display screen (16a). Here, the display frames (54-1 / 54-2, 56-1 / 56-2) divide a plurality of identification data into a plurality of groups, and are set in advance corresponding to each of the plurality of groups.

  In the automatic translation method, the (d1) step includes (d14) displaying an identification figure (59-1 / 59-2 / 59-3 / 59-4) corresponding to each of the plurality of identification data on a display screen (16a (D15) a step of changing the display state of the corresponding identification graphic (59-3 / 59-4) when translation data is received from one of the plurality of identification data; d16) When the identification figure (59-4) is selected, the translation data (58-3) and the corresponding one of the plurality of discrimination data (Zenyu) are related to the display screen (16a). Displaying.

  In the automatic translation method, the (d1) step displays (d17) the identification graphic (59-1 / 59-3 / 59-4) corresponding to each of the plurality of identification data on the display screen (16a). And (d18) a step of changing the display position of the identification graphic (59-1 / 59-3 / 59-4) based on the input of the external signal and displaying it on the display screen (16a), and (d19) The identification figure (59-1), the translation data (51-1 ″), and a corresponding one (John) of the plurality of pieces of discrimination data are displayed in association with each other.

  In the automatic translation method described above, the data displayed in the step (d1) is preset with at least one of a character font and a character color corresponding to each of the plurality of identification data. At least one is displayed on the display screen (16a).

  In order to solve the above problems, a program for causing a computer to execute an automatic translation method using the automatic translation apparatus of the present invention includes steps (a) to (d). (A) The step includes: first original language data (Japanese) indicating a first language (Japanese); first identification data (you) based on first identification data for identifying an automatic translation device (1 / 1a); Are related and displayed on the display screen (16 / 16a). (B) The step includes converting the first translation data (English) translated into the second language (English) and the first identification data into at least one of the plurality of other automatic translation devices (1b / 1c / 1d). To the other party automatic translation apparatus (1c). In the step (c), second identification data for identifying the partner automatic translation apparatus (1c) and second translation data (English) are received from the partner automatic translation apparatus (1c). In the step (d), if the second translation data (English) is not the first language (Japanese), the second translation data (Japanese) is translated into the first language (Japanese) to be the second translation data (Japanese). In addition, it is displayed on the display screen (16a) in association with the second distinction data (Pierre) based on the second identification data.

  In the above program, (c) step includes (c1) a plurality of translation data transmitted from a plurality of other automatic translation apparatuses (1b / 1c / 1d), and a plurality of other automatic translation apparatuses (1b / 1c / Receiving a plurality of identification data identifying 1d). (D) The step includes (d1) a plurality of pieces of translation data (Japanese) translated into the first language (Japanese) and a plurality of pieces of discrimination data (John / And displaying on the display screen (16a) in association with a corresponding one of (Pierre / Zenyu).

  In the above program, the (d1) step associates (d11) each of the plurality of translated data with a corresponding one of the plurality of discriminating data (John / Pierre / Zenyu), ) The step of displaying on the display screen (16a) in the order received in the step is provided.

  In the above program, in the step (d11), (d111) When the display screen (16a) is filled with a part of a plurality of translation data, when a predetermined condition is satisfied, the other part of the plurality of translation data is The step of displaying on a display screen (16a) is provided. The predetermined condition is the input of a signal from the outside instructing the display of a predetermined time or the display of other parts of the plurality of translation data.

  In the above program, the step (d1) includes the step (d12) of associating each of the plurality of translated data with a corresponding one of the plurality of discriminating data (John / Pierre / Zenyu), (16a) including a step of displaying on a corresponding one of the display frames (51-1 / 51-2 / 51-3) set in advance corresponding to each of the plurality of identification data.

  In the above program, each of the plurality of distinction data includes an identification figure (59-1 / 59-3 / 59-4).

  In the above program, the step (d1) includes (d13) associating each of a plurality of translated data with a corresponding one of a plurality of distinction data (John / Pierre / Zenyu), (16a) including a step of displaying in the corresponding display frame (54-1 / 54-2, 56-1 / 56-2). Here, the display frames (54-1 / 54-2, 56-1 / 56-2) divide a plurality of identification data into a plurality of groups, and are set in advance corresponding to each of the plurality of groups.

  In the above program, in the step (d1), (d14) the identification graphic (59-1 / 59-2 / 59-3 / 59-4) corresponding to each of the plurality of identification data is displayed on the display screen (16a). (D15) a step of changing the display state of the corresponding identification graphic (59-3 / 59-4) when translation data is received from one of the plurality of identification data, and (d16) identification When the graphic (59-4) is selected, the translation data (58-3) and the corresponding one of the plurality of distinction data (Zenyu) are displayed on the display screen (16a) in association with each other. With

  In the above program, the step (d1) includes a step (d17) of displaying an identification figure (59-1 / 59-3 / 59-4) corresponding to each of the plurality of identification data on the display screen (16a). (D18) The step of changing the display position of the identification figure (59-1 / 59-3 / 59-4) based on the input of the external signal and displaying it on the display screen (16a), and (d19) the corresponding identification A step of displaying the graphic (59-1), the translation data (51-1 ″), and a corresponding one (John) of the plurality of pieces of distinction data in association with each other.

  In the above program, at least one of a character font and a character color is preset for the data displayed in step (d1) corresponding to each of the plurality of identification data, and at least one of the corresponding character font and character color is set. Is displayed on the display screen (16a).

  Even when a conversation between a plurality of three or more people is performed by the automatic translation apparatus and the automatic translation method of the present invention, each person's speaker can be clarified, and in addition, a translation output suitable for the situation can be provided. It can be carried out.

  Hereinafter, embodiments of an automatic translation apparatus according to the present invention will be described with reference to the accompanying drawings.

(First embodiment)
A first embodiment of an automatic translation apparatus according to the present invention will be described with reference to the accompanying drawings. First, the configuration of the first embodiment of the automatic translation apparatus of the present invention will be described.
FIG. 1 is a block diagram showing the configuration of the first embodiment of the automatic translation apparatus of the present invention. The automatic translation apparatus 1 includes an automatic translation unit 2 as software, a control unit 3, a voice input unit 4, a voice output unit 5, a display unit 6, and a communication unit 7.

  The automatic translation unit 2 automatically translates the input data and outputs it. The automatic translation unit 2 includes a speech recognition unit 21, a translation unit 22, and a speech synthesis unit 23.

  The voice recognition unit 21 performs voice recognition on the voice input data supplied from the voice input unit 4. Then, speech recognition data (example: text data) as a speech recognition result is output to the control unit 3 and the translation unit 22. When the speech data is in the native language (original language: not English), the native language speech recognition unit 31 corresponds. When the voice data is English, the English voice recognition unit 32 corresponds. The control unit 3 outputs the voice recognition data to the display unit 6 and the communication unit 7.

  The translation unit 22 translates the speech recognition data supplied from the speech recognition unit 21. Then, the translation data as the translation result is output to the control unit 3 and the speech synthesis unit 23. Alternatively, the communication input data supplied from the communication unit 7 via the control unit 3 is translated. Then, the communication input data and the translation data are output to the control unit 3 and the speech synthesis unit 23. When the speech recognition data is in the native language (original language: not English), the native language / English translator 33 corresponds. When the speech recognition data is English, the English / native language translation unit 34 corresponds. The control unit 3 outputs the communication input data and the translation data to the display unit 6 and the communication unit 7.

  The speech synthesis unit 23 performs speech synthesis on the translation data supplied from the translation unit 22. Then, the voice output data as the voice synthesis result is output to the voice output unit 5. When the translation data is in English, the English speech synthesizer 35 corresponds. When the translation data is in the native language (original language: not English), the native language speech synthesizer 36 corresponds.

The voice input unit 4 performs analog-digital conversion on a voice input supplied from a sound collecting device such as a microphone. Then, the voice input data as the conversion result is output to the automatic translation unit 2.
The audio output unit 5 performs digital-analog conversion on the audio output data supplied from the audio synthesis unit 23. Then, the audio output as the conversion result is output to a sounding device such as a speaker.

  The display unit 6 displays the voice recognition data, translation data, and communication input data from the control unit 3 on a display device such as a display. At that time, each of the data is displayed based on a format selected from a plurality of formats.

The communication unit 7 outputs communication output data obtained by combining the translation data from the control unit 3 and its own identification data to another automatic translation apparatus. And the communication input data from another automatic translation apparatus are received, and it outputs to the control part 3. FIG. The communication unit 7 includes an identification unit 24.
The identification unit 24 stores identification data of the automatic translation apparatus 1 itself. Then, own identification data is added to each data (communication output data) output from the communication unit 7. In addition, the identification data of other automatic translation apparatuses in the communication range are automatically detected. Further, the identification data of the automatic translation apparatus of the transmission source included in the communication input data is confirmed. The identification data is exemplified by a combination of the owner's name (name) and the serial number of the device. It is also possible to use an image or a symbol indicating the owner.

  The control unit 3 mediates or controls each of the processes and units according to the state of the switch.

FIG. 2 is a diagram showing a hardware configuration of the automatic translation apparatus according to the first embodiment of the present invention. The automatic translation apparatus 1 is an information processing apparatus exemplified by a PDA (Personal Digital Assistant). In particular, it is more preferable that the size is portable (portable terminal). This is because it is desirable that the automatic translation apparatus 1 be carried and used at any time.
The automatic translator includes a memory 12, a CPU (Central Processing Unit) 13, a microphone 14, a speaker 15, a display 16, a communication device 17, a switch 18, and a lamp 19 connected to a bus.
For example, the automatic translation unit 2, the control unit 3, the voice input unit 4, the voice output unit 5, the display unit 6, and the communication unit 7 as software are stored in an HD (Hard Disk) as one of the memories 12. Has been. Then, when the automatic translation apparatus 1 is activated, it is expanded in a RAM (Random Access Memory) as one of the memories 12. Alternatively, the software is stored in a ROM (Read Only Memory) or RAM, or a removable memory such as a memory card. Then, it is expanded in the RAM as necessary at the time of startup, or is executed on the stored memory. Then, the CPU 13 operates the automatic translation apparatus 1 using software in the RAM or ROM. At that time, the microphone 14 is controlled by the voice input unit 4, the speaker 15 is controlled by the voice output unit 5, the display 16 is controlled by the display unit 6, and the communication device 17 is controlled by the communication unit 7. The control unit 3 controls each process and each unit according to the state of the switch 18. The lamp 19 is controlled by the identification unit 24.
The lamp 19 includes a plurality of LEDs having different emission colors. The lamp 19 is installed in a shape protruding from the top of the automatic translation apparatus 1 so that it can be seen not only by the owner of the automatic translation apparatus 1 but also by the conversation partner.

Next, the operation of the first embodiment of the automatic translation apparatus of the present invention will be described.
FIG. 3 is a flowchart showing the operation of the automatic translation apparatus according to the first embodiment of the present invention. In this figure, the operation | movement in the case of performing voice input with respect to the automatic translation apparatus 1 is shown.

(1) Step S01: Voice input (speaking) is started by the operation of the owner turning on the microphone 14.
(2) Step S02: The voice recognition unit 21 generates a unique ID (Identification) for each connected voice input (one message) to the microphone 14. The unique ID is always included in each data (example: voice recognition data, translation data, communication output data) generated with this voice input (speech). Then, with the progress of voice input, voice recognition is performed and generation of voice recognition data is started. Then, an intermediate result of voice recognition (a part of the voice recognition data) starts to be output to the control unit 3.
(3) Step S03: The control unit 3 determines whether or not the voice recognition intermediate result (part of the voice recognition data) has been acquired from the voice recognition unit 21. If Step S03 is Yes, go to Step S04. If No, go to Step S05.
(4) Step S04: When Step S03 is Yes, the control unit 3 outputs the intermediate result (part of the voice recognition data) to the display unit 6 and displays it on the display 16. At the same time, the intermediate result (a part of the speech recognition data) is output to the communication unit 7 and transmitted as communication output data to another automatic translation apparatus.
(5) Step S05: When Step S03 is No, the control unit 3 determines whether or not the voice recognition is finished by the operation of the owner turning off the microphone 14. If Step S05 is Yes, go to Step S06. If No, go to Step S03.
(6) Step S06: When Step S05 is Yes, the continuous speech recognition data indicated by one ID is output from the speech recognition unit 21 and acquired by the translation unit 22 simultaneously with the control unit 3.
(7) Step S07: The control unit 3 outputs the voice recognition data to the display unit 6 and displays it on the display 16. At the same time, the speech recognition data is output to the communication unit 7 and transmitted to another automatic translation apparatus.
(8) Step S08: The control unit 3 determines whether or not the speech recognition data needs to be translated by its own automatic translation apparatus 1. For example, if the speech recognition data is English, it is not translated, and if the speech recognition data is a language other than English, it is translated into English. If Step S08 is Yes, go to Step S09; if No, go to Step S10.
(9) Step S09: The translation unit 22 performs translation on the acquired speech recognition data. Then, the translation data is output to the speech synthesis unit 23 or the control unit 3.
(10) Step S10: The control unit 3 outputs the translation data to the communication unit 7 and transmits it to other automatic translation devices as communication output data. Alternatively, the voice synthesizer 23 generates voice output data and causes a speaker to generate sound.

  In the above operation, the control unit 3 determines the utterance in the automatic translation apparatus 1 and the content of the utterance transmitted from another automatic translation apparatus, the identification data of the utterance automatic translation apparatus, and the utterance time (reception time). They are stored in the memory 12 as a table so that they can be retrieved at any time in association with each other.

  By such an operation, automatic translation can be executed by the automatic translation apparatus.

FIG. 4 is a flowchart showing the operation of the first embodiment of the automatic translation apparatus of the present invention. This figure shows the operation when the automatic translation apparatus 1 receives translation input data from another automatic translation apparatus.
(1) Step S11: It is determined whether or not communication output data output from another automatic translation apparatus has been received as communication input data. If Step S11 is Yes, go to Step S12. If No, go to Step S11.
(2) Step S12: The control unit 3 checks whether or not the ID related to the speech included in the communication input data is the same as the ID related to the speech received previously. If Step S12 is Yes, go to Step S13, and if No, go to Step S14.
(3) Step S13: The control unit 3 outputs the communication input data to the display unit 6. The display unit 6 newly displays a message having the current ID on the display list on the display 16 based on the communication input data.
(4) Step S14: The control unit 3 outputs the communication input data to the display unit 6. Based on the communication input data, the display unit 6 overwrites the previous message displayed in the display list on the display 16 with the current message having the same ID.
(5) Step S15: The control unit 3 determines whether or not the communication input data needs to be translated. For example, if the communication input data is an intermediate result output in the above step S04, it is determined not to be translated. In the case of a piece of communication input data, if the communication input data is in English and not in the native language, it is determined to translate from English to the native language. If Step S15 is Yes, go to Step S16. If No, go to Step S18.
(6) Step S16: When Step S15 is Yes, the control unit 3 outputs the communication input data to the translation unit 22. The translation unit 22 translates the acquired communication input data. Then, the translation data is output to the speech synthesis unit 23 or the control unit 3.
(7) Step S17: The control unit 3 outputs the translation data to the display unit 6. Based on the translation data, the display unit 6 overwrites the pre-translation utterance displayed in the display list on the display 16 with the translation data having the same ID this time.
(8) Step S18: The control unit 3 determines whether or not to pronounce the translation data. For example, if the mode is such that data from another automatic translation apparatus is not sounded, it is determined that sound is not sounded. If step S18 is Yes, step S19, and if No, this operation is terminated.
(9) Step S19: The speech synthesizer 23 generates speech output data based on the translation data and causes the speaker to produce a sound.

  By such an operation, communication using another automatic translation apparatus can be performed with another automatic translation apparatus.

  FIG. 5 is a diagram illustrating an example of transition of display on each display when a conversation is performed using two automatic translation apparatuses. Here, the three displays 16a on the left side of the figure are automatic translation devices used by Japanese. The three displays 16b on the right side of the figure are automatic translation devices used by Americans. And time shall transition from the top to the bottom of the figure.

  In the Japanese device on the right side of the upper row, when the Japanese turns on the microphone 14 and utters “The nearest station is”, a part of the speech recognition data “Ichiban” “Near station” is displayed (steps S02 to S05). On the other hand, communication input data is received from the Japanese device in the upper left device for Americans, and the nearest station is displayed in Japanese (steps S11 to S13).

  Next, in the device for the Japanese on the right side of the middle row, when the Japanese speaks “Where is” and turns off the microphone button, the voice recognition is completed and the voice recognition data “The nearest station is Where is? "Is displayed as a voice recognition result (steps S05 to S07). On the other hand, in the middle left US device, the communication input data is received from the Japanese device, and “where is the nearest station” is displayed in Japanese (steps S11 to S14).

  Subsequently, “Where is the nearest station” is translated in the Japanese device on the right side of the lower row and transmitted to the device for Americans (steps S08 to S10). On the other hand, in the lower left US device, the communication input data is received from the Japanese device, and the translated “Where is the nearest station?” Is displayed (steps S11 to S14).

  FIG. 6 is a diagram illustrating an example of transition of display on each display when a conversation is performed using two automatic translation apparatuses. Here, the display 16a on the left side of the figure is an automatic translation device used by Japanese. The display 16b on the right side of the figure is an automatic translation device used by Americans. And time shall transition from the top to the bottom of each display. On the Japanese device (display 16a), "you" is displayed for yourself and "American" is displayed for Americans. In the device for the American (display 16b), “You” is displayed for the user and “Japan” is displayed for the Japanese. These are displayed based on identification data added to each data output from the automatic translation apparatus.

  As the Japanese and Americans repeat the process of FIG. 5 with each other, conversations are displayed one after the other below (or even above) each display. In this case, when the display list 40a (40b) of the display 16a (16b) cannot fit in the display 16a (16b), the scroll bar 41a (41b) is used.

  Each remark is displayed in an easily distinguishable manner such as “you”, “American”, “You”, and “Japane”, so that even if a new remark is transmitted, it can be read in order. Further, if this is stored as it is in a memory such as an HD, it can be saved as a conversation record. Minutes can also be created easily.

  FIG. 7 is a diagram showing the operation of the automatic translation apparatus used in a conversation between people who speak three kinds of languages. The Japanese uses a portable automatic translation device 1a for Japanese, the American uses a portable automatic translation device 1b for an American, and the French uses a portable automatic translation device 1c for a French. In this case, if a Japanese has an automatic translation device for Japanese-English translation and a French for French-English translation, three people can have a conversation via English translation data. Similarly, even if there are more kinds of languages and the speakers gather to have a conversation, if there is only one automatic translation device for native language-English translation, it will be much more than English translation data. You can talk with other people.

  According to the present invention, since the transmitted utterances are displayed in a list form, even when a plurality of utterers speak in a short time, all the results can be displayed. As a result, even if he / she misses a statement, he / she can be surely informed.

  According to the present invention, when a speaker utters, the result of speech recognition, the result of speech recognition, and the result of translation are sequentially displayed according to the utterance, so the correspondence between the utterance displayed on the screen and the actual utterance can be understood. It can be made easier.

(Second Embodiment)
A second embodiment of the automatic translation apparatus of the present invention will be described with reference to the accompanying drawings. In this embodiment, when using an automatic translation device to talk to a plurality of three or more other parties, it is possible to limit the parties to whom the spoken content is sent, and to instantly check whether the spoken content has been received by the partner. This is different from the first embodiment.

  First, the configuration of the second embodiment of the automatic translation apparatus of the present invention is as shown in FIGS. These are the same as those in the first embodiment.

  Next, the operation of the second embodiment of the automatic translation apparatus of the present invention will be described. Basic communication (dialogue) between automatic translation apparatuses is as in the first embodiment.

  FIG. 8 is a diagram illustrating a situation of the automatic translation apparatus according to the second embodiment of the automatic translation apparatus of the present invention. In this figure, as an example, Japanese (with automatic translation device 1a), American (with automatic translation device 1b), French (with automatic translation device 1c) and Korean (with automatic translation device 1d) Shows the situation where each automatic translation apparatus is within the communication range.

As shown in the figure, the automatic translation apparatus 1a has identification data 50a as name (name of owner, input at the time of acquisition): Ichirou ID (ID of automatic translation apparatus 1a, input at the time of manufacture): 81A0001
have. Similarly, the automatic translation apparatus 1b has name: John and ID: 93C4009 as identification data 50b, the automatic translation apparatus 1c has name: Pierre, ID: 01B5340, and the automatic translation apparatus 1d has identification data 50d as name: Zenyu. , ID: 88Q3902, respectively.

  In this figure, the automatic translation apparatus 1a exchanges identification data with each other by communication with an automatic translation apparatus in the communication range. Then, the automatic translation apparatus capable of dialogue is automatically recognized and displayed as the dialogue partner data 52 on the display 16a. The method will be described later. Although not shown, a list of identification data is similarly displayed in the other automatic translation apparatuses 1b to 1c.

  Before participating in the conversation, the speaker selects a partner who wants to transmit the uttered content from the interactive partner data 52 corresponding to the identification data. For example, in this figure, the Japanese Ichirou selects the partner who wants to transmit the spoken content by checking the John and Pierre check boxes in the dialogue partner data 52. In this way, only John and Pierre can interact with the automatic translation apparatus. Selection can change the transmission partner for each utterance by changing the selection before the utterance.

FIG. 9 is a diagram illustrating another situation of the automatic translation apparatus according to the second embodiment of the automatic translation apparatus of the present invention.
In this figure, for example, red is assigned to the Japanese automatic translation device 1a, blue is assigned to the American automatic translation device 1b, yellow is assigned to the French automatic translation device 1c, and white is assigned to the Korean automatic translation device 1d. Shows the situation. The allocation method will be described later.

  In other words, each automatic translation apparatus is equipped with a lamp capable of emitting light in a plurality of colors at a position where it can be seen from anywhere in normal use. When transmitting the content of the speaker's speech as communication output data together with his / her identification data, the automatic translation apparatus turns on the lamp in the color assigned to the speaker. Then, the other automatic translation apparatus that has received the data turns on the lamp in the color of the speaker to indicate that the data has been received.

  In this figure, when the automatic translation apparatus 1c transmits communication output data indicating the content of a French utterance and its own identification data, its own lamp 19b is lit in yellow of the color assigned to itself. Then, each of the automatic translation apparatuses 1a, 1b, and 1d that has received the data from the automatic translation apparatus 1c turns on the lamps 19a, 19b, and 19d in yellow assigned to the automatic translation apparatus 1c.

FIG. 10 is a flowchart showing the operation of the second embodiment of the automatic translation apparatus of the present invention. This figure shows the assignment of colors to each automatic translation apparatus and the display of identification data on each automatic translation apparatus.
(0) Step S20: The automatic translation apparatus is turned on.
(1) Step S21: The communication unit 7 of the automatic translation device searches for other automatic translation devices in the vicinity.
(2) Step S22: The communication unit 7 determines whether there is another automatic translation apparatus in the vicinity. The determination is made based on whether or not the communication unit 7 responds to a preset call. If Step S22 is Yes, go to Step S24. If No, go to Step S23.
(3) Step S23: Since no other automatic translation apparatus is found in the vicinity, the communication unit 7 provisionally determines its color as red. Proceed to step S25.
(4) Step S24: Since there are other automatic translation devices in the vicinity, the communication unit 7 provisionally determines its own color based on the number of devices found. For example, blue is found when one is found, yellow is found when two are found, and so on. The color assignment method is the same for the fully automatic translation apparatus. In this way, different colors are assigned in the order in which the power is turned on.
(5) Step S25: The communication unit 7 transmits its color and identification data provisionally determined to other automatic translation apparatuses in the surrounding communication area. At the same time, identification data of another automatic translation apparatus is requested.
(6) Step S26: The other automatic translation apparatus returns identification data. At this time, if the tentatively determined colors overlap, a control signal indicating that is returned together.
(7) Step S27: It is determined whether or not the temporarily determined colors overlap. This determination is made based on whether or not there is a control signal indicating that the temporarily determined colors overlap from other automatic translation apparatuses. If Step S27 is Yes, go to Step S28, and if No, go to Step S29.
(8) Step S28: The communication unit 7 changes its own color based on the received colors assigned to the other automatic translation apparatuses so as not to overlap them. Then, the user's tentatively determined color and identification data are transmitted again to other automatic translation apparatuses in the surrounding communication area. After this process, the identification data includes the assigned color.
(9) Step S29: The communication unit 7 outputs the identification data of the other automatic translation apparatus and the assigned color to the control unit 3. The control unit 3 outputs the data to the display unit 6 and displays the data on the display 16. The state of display is, for example, like the automatic translation apparatus 1a in FIG. At this time, each character is displayed in a color assigned to each automatic translation apparatus. Thereby, it becomes easy to understand the color of the lamp 19 of each automatic translation apparatus.

  Thereafter, as shown in FIG. 8 and the description thereof, a partner who wants to transmit the uttered content is selected from the dialogue partner data 52 and the dialogue is performed. When transmitting the communication output data including the contents of the message, the identification data of the selected partner is also transmitted. The automatic translation device on the receiving side does not perform display or translation when its identification data is not included in the transmitted communication output data.

  FIG. 11 is a diagram illustrating an example of the dialogue in the situation of FIG. In this figure, the left side shows an automatic translation device 1a for Japanese, the middle shows an automatic translation device 1b for Americans, and the right side shows an automatic translation device 1c for French people. It shows that time has passed from the top to the bottom of the figure.

  First, John makes a statement 62-1 using the automatic translation apparatus 1b. At this time, the lamp 19b of the automatic translation apparatus 1b is blue (the color of the automatic translation apparatus 1b). The statement 62-1 is translated by the automatic translation apparatus 1a to become a translation 61-1. The lamp 19a of the automatic translation apparatus 1a turns blue. Similarly, the statement 62-1 is translated by the automatic translation apparatus 1c to become a translation 63-1. The lamp 19c of the automatic translation apparatus 1c turns blue.

  Next, Ichirou first selects only John from the partner data 52a that can be interacted with. Subsequently, the utterance 61-2 is performed using the automatic translation apparatus 1a. At this time, the lamp 19a of the automatic translation apparatus 1a turns red (the color of the automatic translation apparatus 1a). The utterance 61-2 is translated by the automatic translation apparatus 1a and then transmitted to the automatic translation apparatus 1b to become the translation 62-2. The lamp 19b of the automatic translation apparatus 1b is red. However, the utterance 61-2 is neither translated nor displayed in the automatic translation apparatus 1c.

  Subsequently, John makes a statement 62-3 using the automatic translation apparatus 1b. At this time, the lamp 19b of the automatic translation apparatus 1b turns blue. The statement 62-3 is translated into the translation 61-3 by the automatic translation apparatus 1a. The lamp 19a of the automatic translation apparatus 1a turns blue. Similarly, the statement 62-3 is translated by the automatic translation apparatus 1c into a translation 63-3. The lamp 19c of the automatic translation apparatus 1c turns blue.

  According to the present invention, when the automatic translation apparatus is used to talk to a plurality of three or more partners, the partners to whom the spoken content is sent can be limited. On the contrary, since the unnecessary message content is not displayed on the side that receives the communication output data including the message content, the display screen can be used effectively.

  According to the present invention, since the plurality of lamps that have sent the spoken content react, it is possible to instantly check whether the spoken content has been received by the other party.

(Third embodiment)
A third embodiment of the automatic translation apparatus of the present invention will be described with reference to the accompanying drawings. In this embodiment, when an automatic translation apparatus is used to talk to a plurality of three or more other parties, a communication (dialog) result display method that is optimal for them is executed according to various conversation situations (modes). Is different from the first and second embodiments.

  First, the configuration of the third embodiment of the automatic translation apparatus of the present invention is as shown in FIGS. These are the same as those in the first embodiment. The mode is selected by operating the switch 18 by the owner of the automatic translation apparatus 1. Based on this, the display unit 6 changes the display method.

  Next, the operation of the third embodiment of the automatic translation apparatus of the present invention will be described. Basic communication (dialogue) between automatic translation apparatuses is as in the first and second embodiments.

  FIG. 12 is a diagram showing a display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 12 shows the display of the display list 40a-1 when a plurality of three or more persons speak (speak) freely. Here, there are the following features.
(A) Each statement (translated) is displayed for each speaker, such as “you” and “John”.
(B) The translation results are arranged and displayed in the order of statements, and are automatically scrolled as necessary. The amount that cannot be displayed on the display 16a can be displayed by operating the scroll bar 41a-1.
(C) According to the storage capacity, it is possible to confirm a statement retroactively.

  In this case, old utterances with low importance disappear from the display 16a, and the most important latest utterances can always be confirmed. In addition, by storing the contents of the remarks, conversation records and minutes can be easily created.

  FIG. 13 is a diagram showing an application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 13 shows the display of the display list 40a-1 ′ when a plurality of three or more people freely speak (speak) as in the case of FIG. Here, there are the following features.
(A) Each remark is displayed for each speaker such as “John”, “Pierre”, and “Zenyu”.
(B) The translation results are arranged and displayed in the order of statements, but when a plurality of statements are received at once (within a predetermined time), they are not automatically scrolled. Scroll after a certain time or by user operation. The part that cannot be displayed on the display 16a can be displayed by operating the scroll bar 41a-1 ′. At this time, the feed button 60 indicates that there is a next message (a beautiful message displayed on the screen).
(C) According to the storage capacity, it is possible to confirm a statement retroactively.

  When a plurality of utterances are received at once, for example, within one second, it takes time to confirm the contents of each utterance on the display screen 40a-1 '. In this case, the screen is scrolled (display screen 40a-1 ″) when the user presses the feed button 60 for a certain time (example: 5 seconds) considered necessary for content confirmation. . As a result, even when a large amount of speech is received at once, or when participating in a conversation from the middle, the speech does not flow before reading, and the content of the conversation can be confirmed at your own pace. In addition, by storing the contents of the remarks, conversation records and minutes can be easily created.

  FIG. 14 is a diagram showing another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 14 shows the display of the display list 40a-2 when one person individually answers questions from a plurality of people. Here, there are the following features.
(A) Each comment (translated) is displayed for each speaker such as “you”, “John”, and “Pierre”.
(B) A display frame is provided for each speaker, and the same person's speech is displayed in the frame. For example, “John” is the display frame 51-1, “You” is the display frame 51-2, and “Pierre” is the display frame 51-3.
(C) When displaying the content of a person who is currently speaking, the display frame of the person is automatically expanded and the display frame of another person is automatically reduced. For example, in the display 16a on the left side of the drawing, the display frame 51-2 is wider than the other display frames for the speech of “you”. In the display 16a on the right side of the drawing, the display frame 51-1 ′ is expanded compared to other display frames for the statement “John”.
(D) When displaying the content of a person who is currently speaking, the name of the speaker is displayed with a mark. For example, in the display 16a on the left side of the figure, “▼” (black inverted triangle) is added in front of the speaker “you”. In the display 16a on the right side of the figure, “▼” (black inverted triangle) is added in front of the speaker “John”.

FIG. 15 is a flowchart showing the operation of the display unit for performing the display of FIG.
(1) Step S31: The content of the speech and the identification data of the speaker are acquired.
(2) Step S32: It is confirmed whether or not a display frame corresponding to the identification data is set. If Step S32 is Yes, go to Step S34, and if No, go to Step S33.
(3) Step S33: A display frame corresponding to the identification data is set.
(4) Step S34: The display frame corresponding to the identification data is expanded.
(5) Step S35: The contents of the statement are displayed together with the identification data (here, the name of the speaker) with a mark in the display frame corresponding to the identification data.
(6) Step S36: It is confirmed whether or not this mode is finished. This operation | movement is complete | finished when step S36 is Yes, and when it is No, it goes to step S31.

  In this case, who can speak can be confirmed at a glance. In addition, the most important latest remarks can be most easily seen. Furthermore, since the display position for each speaker is relatively determined, it is possible to easily focus on the content of a specific speaker.

  FIG. 16 is a diagram showing a modification of another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 16 shows a display on the display 16a when a plurality of people speak each other. Here, there are the following features.
(A) A character is provided for each speaker. For example, John 59-1, Pierre 59-3, and Zenyu 59-4. They can be freely set at an appropriate location on the display screen 16a by an operation such as drag and drop (the right diagram in FIG. 16).
(B) Each utterance (translated) is displayed as a balloon from the character set for each speaker. At that time, it is displayed at a predetermined position for each speaker so that it automatically fits in a space that does not cover the character indicating the speaker. For example, the statement of John 59-1 is a balloon 51-1 ″. “You” is a balloon 51-2 ″ from the front although there is no character.
(C) A conversation slider 64 and a conversation slider bar 63 that are advanced as the conversation progresses are displayed at the bottom of the display 16a. When the conversation slider 64 is moved, the conversation contents are displayed from the present to the past. In the conversation slider bar 63, the right end indicates the current time and the left end indicates the start of the conversation.

  The operation of the display unit related to FIG. 16 is the same as the flow of FIG. 15 except that the setting of the display frame in FIG. 15 is changed to the setting and arrangement of characters and balloons.

From the relationship between the character and the balloon, you can see at a glance who is speaking right now. In addition, the most important latest remarks can be most easily seen. Since the display position is relatively determined for each speaker, it is possible to easily focus on the content of a specific speaker.
In addition, when the user matches the position of the character on the display 16a with the position of the actual speaker, the translation result of each comment is displayed in a balloon from the corresponding character, making it easier to understand the correspondence with the reality. That is, even though the conversation is through the automatic translation device, it can be brought closer to the feeling of direct conversation. Further, by moving the conversation slider 64, past conversation contents can be confirmed in time order.

  FIG. 17 is a diagram showing still another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 17 shows the display of the display list 40a-3 when there is a moderator. Here, there are the following features.
(A) The content of the remarks of the designated person (moderator) is always displayed in a separate display frame 54-1 at the top or bottom of the display list.
(B) The contents of other people's utterances are collectively displayed in one display frame 54-2 in the order of utterances, and the translation results are automatically scrolled as necessary. The part that cannot be displayed in the display frame 54-2 can be displayed by operating the scroll bar.
For example, on the left side of the figure, another display frame 54-1 for the moderator (John) is always displayed at the top of the display list 40a-3. On the right side of the figure, another display frame 54-1 'for the moderator (John) is left as it is, and other people's remarks are displayed in the display frame 54-2' for other people. A scroll bar 41a-3 is displayed as necessary.

FIG. 18 is a flowchart showing the operation of the display unit for performing the display of FIG.
(1) Step S41: A designated person is set from the interactive partner data 52.
(2) Step S42: The content of the speech and the identification data of the speaker are acquired.
(3) Step S43: It is confirmed whether or not the designated person speaks. If Step S42 is Yes, go to Step S44, and if No, go to Step S45.
(4) Step S44: The content of the statement is displayed on the display frame 54-1 for the designated person.
(5) Step S45: The content of the statement is displayed on the display frame 54-2 for other people.
(6) Step S46: It is confirmed whether or not this mode is finished. This operation | movement is complete | finished when step S46 is Yes, and it goes to step S42, when No.

  In this case, since the question of the chairman (proceeder) can always be confirmed, even after many people speak, the question can be answered correctly and the opinion can be expressed correctly. In addition, it is possible to distinguish between a moderator's speech and another person's speech at a glance.

  FIG. 19 is a diagram showing another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 19 shows the display of the display list 40a-4 when a plurality of people are divided into groups. Here, there are the following features.
(A) It can be set in advance to which group each speaker belongs.
(B) A display frame is provided for each group, and the content of messages in the same group are displayed together in the same display frame in the order of statements. Scroll automatically as needed. The part that cannot be displayed in the display frame can be displayed by operating the scroll bar.
For example, on the left side of the figure, the display frame 56-1 and the display frame 56-2 are displayed in the display list 40a-4 corresponding to the two groups. On the right side of the figure, the speech contents of the speakers belonging to the respective groups are displayed in display frames 56-1 ′ and 56-2 ′, respectively. Scroll bars 41a-4 (1) and 41a-4 (2) are displayed as necessary. The other person's remarks are displayed in the display frame 54-2 'for the other person.

FIG. 20 is a flowchart showing the operation of the display unit for performing the display of FIG.
(1) Step S51: A group is set from the partner data 52 that can be interacted with.
(2) Step S52: The content of the speech and the identification data of the speaker are acquired.
(3) Step S53: The content of the statement is displayed in the display frame of the group to which the speaker belongs.
(4) Step S54: It is confirmed whether or not this mode is finished. If Step S54 is Yes, this operation is terminated. If No, the process proceeds to Step S52.

  In this case, since the utterances are divided for each group, it is possible to identify which group's utterance belongs to at a glance.

  FIG. 21 is a diagram showing still another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 21 shows the display of the display list 40a-6 when talking with many people and requesting opinions. Here, there are the following features.
(A) Participants in the conversation are displayed in characters in the display frame 58-4, for example, John 59-1, Pierre 59-3, Zenyu 59-4, you 59-2, and the speaker changes color Displayed. For example, in the right diagram of FIG. 21, Pierre 59-3 and Zenyu 59-4 in the display frame 58-4 are lit, indicating that both have made a statement (a message has been received).
(B) By selecting a character corresponding to the speaker, the user displays the speech (translated) of the speaker in the speech frame (58-1, 58-2, 58-3). For example, if Zenyu 59-4 is selected, Zenyu's remark is displayed in the remark frame 58-3.

FIG. 22 is a flowchart showing the operation of the display unit for performing the display of FIG.
(1) Step S71: It is confirmed whether a new message has been acquired. If Step S71 is Yes, go to Step S72. If No, go to Step S76.
(2) Step S72: The content of the speech and the identification data of the speaker are acquired.
(3) Step S73: It is confirmed whether or not a character corresponding to the identification data is set. If Step S73 is Yes, go to Step S75. If No, go to Step S74.
(4) Step S74: A character corresponding to the identification data is set in the display frame 58-4.
(5) Step S75: In the display frame 58-4, the character corresponding to the identification data is turned on (color change).
(6) Step S76: It is confirmed whether or not the user has selected a character. If Step S76 is Yes, go to Step S77, and if Step S76 is No, go to Step S78.
(7) Step S77: In the message frame (58-1, 58-2, 58-3) by the user's selection, together with the identification data (herein, the name of the speaker) of the selected speaker, the content of the statement Is displayed. Also, the corresponding character is turned off (color change).
(8) Step S78: It is confirmed whether or not this mode is finished. This operation | movement is complete | finished when step S78 is Yes, and goes to step S71, when No.

  In this case, even when a plurality of utterances are received in a short time, the utterances of each utterer can be read carefully without being sent to the pace of receiving the utterances. Also, you can see at a glance who spoke.

  FIG. 23 is a diagram showing still another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. In this figure, the display 16a (display screen) of the automatic translation apparatus 1a for Japanese is shown as an example.

FIG. 23 is a display list in the case where the font and display color of the character for displaying the translation result are changed for each speaker, for each group of speakers, or for each designated person and other speakers. The display of 40a-5 is shown. This application example can also be applied to the examples shown in FIGS. 12, 13, 14, 16, 17, 19, and 21. Here, there are the following features.
(A) The difference between speakers can be specified at a glance, and the speaker can be specified. The part that cannot be displayed in the display frame can be displayed by operating the scroll bar 41a-5.

FIG. 24 is a flowchart showing the operation of the display unit for performing the display of FIG.
(1) Step S61: The content of the speech and the identification data of the speaker are acquired.
(2) Step S62: It is confirmed whether or not a font (display color) corresponding to the identification data is set. If Step S62 is Yes, go to Step S64. If No, go to Step S63.
(3) Step S63: A font (display color) corresponding to the identification data is set.
(4) Step S64: The content of the statement is displayed in a font (display color) corresponding to the identification data.
(5) Step S65: It is confirmed whether or not this mode is finished. If Step S65 is Yes, the operation is terminated. If No, the process proceeds to Step S61.

  In this case, since the display method is different for each speaker, each group of speakers, or each designated person and other speakers, the difference between the speakers can be determined at a glance.

FIG. 1 is a block diagram showing the configuration of the first embodiment of the automatic translation apparatus of the present invention. FIG. 2 is a diagram showing a hardware configuration of the automatic translation apparatus according to the first embodiment of the present invention. FIG. 3 is a flowchart showing the operation of the automatic translation apparatus according to the first embodiment of the present invention. FIG. 4 is a flowchart showing the operation of the first embodiment of the automatic translation apparatus of the present invention. FIG. 5 is a diagram showing transition of display on each display when a conversation is performed using two automatic translation apparatuses. FIG. 6 is a diagram showing transition of display on each display when a conversation is performed using two automatic translation apparatuses. FIG. 7 is a diagram showing the operation of the automatic translation apparatus used in a conversation between people who speak three kinds of languages. FIG. 8 is a diagram illustrating a situation of the automatic translation apparatus according to the second embodiment of the automatic translation apparatus of the present invention. FIG. 9 is a diagram illustrating another situation of the automatic translation apparatus according to the second embodiment of the automatic translation apparatus of the present invention. FIG. 10 is a flowchart showing the operation of the second embodiment of the automatic translation apparatus of the present invention. FIG. 11 is a diagram illustrating an example of the dialogue in the situation of FIG. FIG. 12 is a diagram showing a display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 13 is a diagram showing an application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 14 is a diagram showing another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 15 is a flowchart showing the operation of the display unit for performing the display of FIG. FIG. 16 is a diagram showing a modification of another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 17 is a diagram showing still another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 18 is a flowchart showing the operation of the display unit for performing the display of FIG. FIG. 19 is a diagram showing another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 20 is a flowchart showing the operation of the display unit for performing the display of FIG. FIG. 21 is a diagram showing still another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 22 is a flowchart showing the operation of the display unit for performing the display of FIG. FIG. 23 is a diagram showing still another application example of the display method of the automatic translation apparatus in the third embodiment of the automatic translation apparatus of the present invention. FIG. 24 is a flowchart showing the operation of the display unit for performing the display of FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1, 1a, 1b, 1c, 1d Automatic translation apparatus 2 Automatic translation part 3 Control part 4 Voice input part 5 Voice output part 6 Display part 7 Communication part 12 Memory 13 CPU
14 Microphone 15 Speaker 16, 16a, 16b, Display 17 Communication device 18 Switch 19, 19a, 19b, 19c, 19d Lamp 21 Speech recognition unit 22 Translation unit 23 Speech synthesis unit 24 Identification unit 31 Native language speech recognition unit 32 English speech recognition Part 33 Native language / English translation part 34 English / Native language translation part 35 English speech synthesis part 36 Native language speech synthesis part 40a, 40b,
40a-1 (') (''), 40a-2 ('), 40a-3 ('), 40a-4 ('), 40a-5 Display list 41a, 41b,
41a-1 ('), 41a-2, 41a-3, 41a-4 (1,2), 41a-5 Scroll bar 50a, 50b, 50c, 50d Identification data 52, 52a Interactive partner data 51-1 (' ), 51-2 ('), 51-3 ('),
54-1 ('), 54-2 ('), 56-1 ('), 56-2 (') Display frame 51-1 ", 51-2" Balloon 59, 59-1, 59-2 , 59-3, 59-4 Character 60 Feed button 61-2, 62-1, 62-3 Comment 61-1, 61-3, 62-2, 63-1, 63-3 Translation 63 Conversation slider bar 64 Conversation Slider

Claims (34)

An automatic translation device that uses people who speak different languages
An automatic translation unit that translates the first source language data indicating the first language into the second language and outputs the first language data;
A communication unit that transmits the first translation data and first identification data for identifying the automatic translation device to a partner automatic translation device that is at least one of a plurality of other automatic translation devices;
A display unit that associates and displays the first original language data and the first distinction data based on the first identification data;
The communication unit receives second identification data for identifying the partner automatic translation device and second translation data from the partner automatic translation device,
When the second translation data is not in the first language, the automatic translation unit translates the second translation data into the first language and outputs it as second translation data again.
The automatic translation apparatus, wherein the display unit displays the second translation data in association with second distinction data based on the second identification data. The automatic translation device according to claim 1,
The communication unit further transmits the first source language data to the partner automatic translation device, and receives second source language data indicating a third language before translation of the second translation data from the partner automatic translation device. And
The display unit further displays the second original language data and the second distinction data in association with each other. The automatic translation apparatus according to claim 2,
The automatic translation apparatus, wherein the display unit displays the second translation data and the second distinction data after displaying the second original language data and the second distinction data. The automatic translation device according to claim 1,
The automatic translation apparatus, wherein the first original language data is voice recognition data obtained by voice recognition of a human voice. In the automatic translation apparatus according to any one of claims 1 to 4,
An automatic translation apparatus further comprising a lamp that is provided at a position that is visible from the outside and that is lit in a different color based on the first identification data and the second identification data. In the automatic translation apparatus according to any one of claims 1 to 5,
The communication unit receives a plurality of translation data transmitted from the other plurality of automatic translation devices, and a plurality of identification data for identifying the other plurality of automatic translation devices,
The automatic translation unit translates and outputs the plurality of translation data into the first language,
The display unit displays each of the plurality of pieces of translation data translated into the first language and a corresponding one of a plurality of pieces of discrimination data generated based on the plurality of pieces of identification data. Automatic translation device. The automatic translation apparatus according to claim 6,
The automatic translation apparatus, wherein the display unit associates each translated plurality of translation data with a corresponding one of the plurality of pieces of distinction data and displays them in the order received by the communication unit. The automatic translation apparatus according to claim 7,
When the display screen is filled with a part of the plurality of translation data, when the predetermined condition is satisfied, the display unit displays another part of the plurality of translation data,
The automatic translation apparatus, wherein the predetermined condition is an input of an external signal instructing the passage of a preset time or display of another part of the plurality of translation data. The automatic translation apparatus according to claim 6,
The display unit sets a display frame corresponding to each of the plurality of identification data, associates each of the plurality of translated data translated with a corresponding one of the plurality of distinction data, An automatic translation device that displays the corresponding display frame. The automatic translation apparatus according to claim 6,
Each of the plurality of distinction data includes an identification figure.
Automatic translation device. The automatic translation apparatus according to claim 6,
The display section divides the plurality of identification data into a plurality of groups, sets a display frame corresponding to each of the plurality of groups, and translates each of the plurality of translated data and the plurality of discrimination data. An automatic translation device that associates a corresponding one of the images with the corresponding one of the display frames. The automatic translation apparatus according to claim 6,
The display unit displays an identification graphic corresponding to each of the plurality of identification data, and when translation data is received from one of the plurality of identification data, changes a display state of the corresponding identification graphic. An automatic translation apparatus that displays the translation data and the corresponding one of the plurality of discrimination data in association with each other when the identification graphic is selected. The automatic translation apparatus according to claim 6,
The display unit displays an identification graphic corresponding to each of the plurality of identification data, changes a display position of the identification graphic based on an input of an external signal, and translates from one of the plurality of identification data An automatic translation apparatus that displays, when data is received, the corresponding identification graphic, the translation data, and the corresponding one of the plurality of distinction data in association with each other. The automatic translation apparatus according to any one of claims 6 to 13,
The display unit sets at least one of a character font and a character color corresponding to each of the plurality of identification data, and each of the plurality of translated data translated and a corresponding one of the plurality of discrimination data An automatic translation apparatus that displays at least one of the corresponding character font and the character color. An automatic translation method using an automatic translation device,
(A) displaying the first original language data indicating the first language on the display screen in association with the first distinction data based on the first identification data for identifying the automatic translation device;
(B) transmitting the first translation data obtained by translating the first source language data into a second language and the first identification data to a partner automatic translation device that is at least one of a plurality of other automatic translation devices. And steps to
(C) receiving second identification data for identifying the counterpart automatic translation device and second translation data from the counterpart automatic translation device;
(D) When the second translation data is not in the first language, the second translation data is translated into the first language, and again as second translation data, second discrimination data based on the second identification data And displaying it on the display screen in association with the automatic translation method. The automatic translation method according to claim 15, wherein
The step (c) includes:
(C1) receiving a plurality of translation data transmitted from the other plurality of automatic translation apparatuses and a plurality of identification data for identifying the other plurality of automatic translation apparatuses;
The step (d) includes:
(D1) The display screen is associated with each of the plurality of translation data translated into the first language and a corresponding one of a plurality of pieces of discrimination data generated based on the plurality of identification data. An automatic translation method comprising a step of displaying. The automatic translation method according to claim 16, wherein
The step (d1) includes
(D11) including a step of associating each of the plurality of translated data translated with a corresponding one of the plurality of distinction data and displaying the translated data on the display screen in the order received in the step (c1). Automatic translation method. The automatic translation method according to claim 17,
The step (d11) includes
(D111) when the display screen is filled with a part of the plurality of translation data, when a predetermined condition is satisfied, the display screen includes a step of displaying another part of the plurality of translation data on the display screen;
The automatic translation method, wherein the predetermined condition is an elapse of a preset time or an input of an external signal instructing display of another part of the plurality of translation data. The automatic translation method according to claim 16, wherein
The step (d1) includes
(D12) Preliminarily set corresponding to each of the plurality of identification data on the display screen by associating each of the plurality of translated data translated with a corresponding one of the plurality of discrimination data An automatic translation method comprising a step of displaying on a corresponding one of display frames. The automatic translation method according to claim 16, wherein
Each of the plurality of distinction data includes an identification figure.
Automatic translation method. The automatic translation method according to claim 16, wherein
The step (d1) includes
(D13) comprising a step of associating each of the plurality of translated data translated with a corresponding one of the plurality of pieces of distinction data and displaying them in a corresponding display frame of the display screen, An automatic translation method in which the plurality of identification data is divided into a plurality of groups and set in advance corresponding to each of the plurality of groups. The automatic translation method according to claim 16, wherein
The step (d1) includes
(D14) displaying an identification graphic corresponding to each of the plurality of identification data on the display screen;
(D15) when translation data is received from one of the plurality of identification data, the display state of the corresponding identification graphic is changed;
(D16) An automatic translation method comprising: when the identification graphic is selected, displaying the translation data and the corresponding one of the plurality of pieces of discrimination data on the display screen in association with each other. The automatic translation method according to claim 16, wherein
The step (d1) includes
(D17) displaying an identification graphic corresponding to each of the plurality of identification data on the display screen;
(D18) changing the display position of the identification graphic based on the input of an external signal and displaying it on the display screen;
(D19) An automatic translation method comprising: displaying the corresponding identification graphic, the translation data, and the corresponding one of the plurality of pieces of distinction data in association with each other. The automatic translation method according to any one of claims 16 to 23,
In the data displayed in the step (d1), at least one of a character font and a character color is set in advance corresponding to each of the plurality of identification data, and at least one of the corresponding character font and the character color Automatic translation method displayed on the display screen. A program for causing a computer to execute an automatic translation method using an automatic translation device,
(A) displaying the first original language data indicating the first language on the display screen in association with the first distinction data based on the first identification data for identifying the automatic translation device;
(B) transmitting the first translation data obtained by translating the first source language data into a second language and the first identification data to a partner automatic translation device that is at least one of a plurality of other automatic translation devices. And steps to
(C) receiving second identification data for identifying the partner automatic translation device and second translation data from the partner automatic translation device from the partner automatic translation device;
(D) When the second translation data is not in the first language, the second translation data is translated into the first language, and again as second translation data, second discrimination data based on the second identification data And displaying the program on the display screen in association with the program. The program according to claim 25,
The step (c) includes:
(C1) receiving a plurality of translation data transmitted from the other plurality of automatic translation apparatuses and a plurality of identification data for identifying the other plurality of automatic translation apparatuses;
The step (d) includes:
(D1) The display screen is associated with each of the plurality of translation data translated into the first language and a corresponding one of a plurality of pieces of discrimination data generated based on the plurality of identification data. A program with steps to display. The program according to claim 26, wherein
The step (d1) includes
(D11) including a step of associating each of the plurality of translated data translated with a corresponding one of the plurality of distinction data and displaying the translated data on the display screen in the order received in the step (c1). program. The program according to claim 27,
The step (d11) includes
(D111) when the display screen is filled with a part of the plurality of translation data, and when a predetermined condition is satisfied, the display screen includes a step of displaying another part of the plurality of translation data.
The predetermined condition is an input of an external signal instructing display of a predetermined time or display of another part of the plurality of translation data. The program according to claim 26, wherein
The step (d1) includes
(D12) Preliminarily set corresponding to each of the plurality of identification data on the display screen by associating each of the plurality of translated data translated with a corresponding one of the plurality of discrimination data A program comprising a step of displaying on a corresponding one of the display frames. The program according to claim 26, wherein
Each of the plurality of discriminating data includes a program for identifying. The program according to claim 26, wherein
The step (d1) includes
(D13) comprising a step of associating each of the plurality of translated data translated with a corresponding one of the plurality of pieces of distinction data and displaying them in a corresponding display frame of the display screen, A program that divides the plurality of identification data into a plurality of groups and is set in advance corresponding to each of the plurality of groups. The program according to claim 26, wherein
The step (d1) includes
(D14) displaying an identification graphic corresponding to each of the plurality of identification data on the display screen;
(D15) when translation data is received from one of the plurality of identification data, the display state of the corresponding identification graphic is changed;
(D16) A program comprising: when the identification graphic is selected, displaying the translation data and a corresponding one of the plurality of distinction data on the display screen in association with each other. The program according to claim 26, wherein
The step (d1) includes
(D17) displaying an identification graphic corresponding to each of the plurality of identification data on the display screen;
(D18) changing the display position of the identification graphic based on the input of an external signal and displaying it on the display screen;
(D19) A program comprising the step of displaying the corresponding identification graphic, the translation data, and the corresponding one of the plurality of distinction data in association with each other. The program according to any one of claims 26 to 33,
In the data displayed in the step (d1), at least one of a character font and a character color is set in advance corresponding to each of the plurality of identification data, and at least one of the corresponding character font and the character color Program displayed on the display screen.

Images