JP2000194700A - Information processing device and method and information providing medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily change the contents of interpretation. SOLUTION: Terminals 11 and 12 are connected to a network 3 via devices having the telephone functions respectively, and the users A and B can talk with each other via the terminals 11 and 12. Both users A and B interpret their speech contents via one of interpretation service providing devices 13-1 to 13-3. The device 13-1 functions as a server which has a speech recognition function, a machine translation function and a voice synthesizing function in addition to a history information storage function. Thus, the device 13-1 stores the contents of hitherto conversations, executes the interpretation based on the stored conversation contents and supplies the conversation history information to other devices 13-2 and 13-3 as necessary.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing apparatus and method, and a providing medium, and more particularly, to an information processing apparatus and method capable of easily changing the contents of speech recognition and machine translation, and Regarding the providing medium.

[0002]

2. Description of the Related Art FIG. 10 shows a configuration example of a conventional interpreting service system. Each of the terminal 1 and the terminal 2 is, for example, a telephone, and is connected to a network 3 including a telephone line. The user A and the user B can talk (talk) via the terminal 1 and the terminal 2. it can.

The language used by user A (for example,
If the language (eg, English) used by user B is different from user B, user A and user B
Three interpreting service providing devices 4-1 to 4-3 (hereinafter referred to as
When it is not necessary to distinguish the interpreting service providing apparatuses 4-1 to 4-3 individually, the interpreting service providing apparatuses 4 are simply described. The same applies to other devices), and the content of the conversation can be interpreted there.

The interpreting service providing apparatus 4-1 is a server having a speech recognition function, a machine translation function, and a speech synthesizing function, and executes an interpreting process on a supplied speech signal. By the interpreting process in the interpreting service providing device 4-1, for example, a voice signal from the terminal 1 supplied via the network 3 is recognized by speech, converted into a language used by the user B (machine translation), and The signal is converted to a signal and transmitted to the terminal 2. Similarly, the voice signal from the terminal 2 supplied via the network 3 is also voice-recognized, translated into the language of the user A, converted into a voice signal, and transmitted to the terminal 1.

The interpreting service providing apparatus 4-2 is a server having a speech recognition function, a machine translating function, and a speech synthesizing function similarly to the interpreting service providing apparatus 4-1, and executes an interpreting process. The providing device 4-2 includes:
Since more language data for speech recognition, language data for machine translation, and language data for speech synthesis are stored, the interpreter of the interpreting service providing apparatus 4-2 interprets the interpreting service. It will be more accurate than the interpretation by the interpreting process.

The interpreting service providing apparatus 4-3 is, for example, a telephone which can be connected to two lines simultaneously. The interpreting process here is performed by an operator (human) performing the interpreting (interpreting process) instead of the voice recognition and the machine translation by the device. For example, the operator listens to the voice (words) of the user A supplied from the terminal 1 from a receiving unit (not shown) of the interpreting service providing apparatus 4-3, translates it into the language of the user B by himself, and Is pronounced and input to a transmitting section (not shown) of the interpreting service providing apparatus 4-3.
The operator also hears the voice (words) of the user B supplied from the terminal 2 from the receiving unit, translates it into the language of the user A, pronounces it, and inputs it to the transmitting unit. I do. The voice of the operator input from the transmitter is
It is transmitted to terminal 2 or terminal 1.

[0007] The interpretation by the operator is more accurate than the interpretation by the interpretation processing of the translation service providing devices 4-1 and 4-2.

Next, the operation will be described. Terminal 1
And a communication link with the terminal 2 is established on the network 3 so that the user A and the user B can talk via the terminal 1 and the terminal 2. Therefore, for example, when the user A wants to talk with the user B via the interpreter of the interpreter service providing apparatus 4-1, the user A performs a predetermined operation on the terminal 1, and
-1 and inputs information (hereinafter referred to as necessary information) required for the interpreting process, such as the address (telephone number) of the terminal 2 and the type of language to be interpreted. Thereby, the user A can talk to the user B via the interpreter of the interpreter service providing apparatus 4-1.

[0009]

When language data (language data for speech recognition and language data for machine translation) of words used in a conversation is not stored in the interpreting service providing apparatus 4-1. Interpretation processing (speech recognition and machine translation) is not performed properly. For such a reason, when the conversation with the user B is not properly interpreted, the user A replaces the interpreting service providing apparatus 4-1 with an interpreting service providing apparatus that executes an interpreting process based on more language data. 4-2, or an interpreting service providing device 4-3 in which an interpreting process is executed by an operator can be used.

[0010] However, in this case, the user A temporarily suspends the call with the user B, performs a predetermined operation on the terminal 1 again, and sends a message to the interpreting service providing apparatus 4-2 or the interpreting service providing apparatus 4-3. Access and necessary information must be input (notified to the operator) from the beginning, and there is a problem that it is troublesome.

Further, since the contents of past conversations are not stored in the interpreting service providing apparatus 4 for newly executing the interpreting process, for example, a pronoun or the like estimated from the contents of past conversations in a conversation is used. When used, there was a problem that the content was not translated properly.

The present invention has been made in view of such a situation, and it is an object of the present invention to easily change the contents of an interpreter so that the contents of a call can be appropriately interpreted.

[0013]

According to a first aspect of the present invention, there is provided an information processing apparatus for executing a predetermined interpreting process selected from a plurality of interpreting processes by selecting a predetermined interpreting process. Transmitting means for transmitting an audio signal addressed to another information processing apparatus to the server; and other information on which the predetermined interpreting processing has been executed, which has been transmitted from the server which executes the predetermined interpreting processing selected by the selecting means. It is characterized by comprising a receiving means for receiving an audio signal from the processing device, and a switching signal transmitting means for transmitting a switching signal to a server for executing a predetermined interpreting process selected by the selecting means.

According to a second aspect of the present invention, there is provided an information processing method comprising: a selecting step of selecting a predetermined interpreting process from a plurality of interpreting processes; and a server for executing the predetermined interpreting process selected in the selecting step. A transmitting step of transmitting a voice signal addressed to the processing device, and a voice signal from another information processing device, which has been subjected to the predetermined interpreting process and transmitted from the server that executes the predetermined interpreting process selected in the selecting step And a switching signal transmitting step of transmitting a switching signal to a server that executes a predetermined interpreting process selected in the selecting step.

[0015] According to a third aspect of the present invention, the providing medium includes a selecting step of selecting a predetermined interpreting process from the plurality of interpreting processes;
A transmitting step of transmitting an audio signal addressed to another information processing device to a server that executes the predetermined interpreting process selected in the selecting step, and a server that executes the predetermined interpreting process selected in the selecting step. A switching step of transmitting a switching signal to a server that executes a predetermined interpreting process selected in the receiving step of receiving a voice signal from another information processing device on which the predetermined interpreting process has been executed and the selecting step And a computer-readable program for executing a process including steps.

[0016] The information processing apparatus according to claim 1 and claim 2.
In the information processing method described in the above, and the providing medium described in the claim 3, a predetermined interpreting process is selected from the plurality of interpreting processes, and a server that executes the selected predetermined interpreting process is provided with another information processing method. An audio signal addressed to the device is transmitted and transmitted from a server that executes a selected predetermined interpreting process.
A voice signal from another information processing apparatus on which the predetermined interpreting process has been executed is received, and a switching signal is transmitted to the selected server that executes the predetermined interpreting process.

According to a fourth aspect of the present invention, there is provided an information processing apparatus for receiving and storing history information transmitted from another information processing apparatus, and executing an interpreting process on an audio signal transmitted from a terminal. Executing means, updating means for updating the history information stored in the storage means based on the interpretation result of the interpretation processing, and history information stored in the storage means,
And transmitting means for transmitting the information to another information processing device designated by the predetermined information transmitted from the terminal.

According to a fifth aspect of the present invention, there is provided an information processing method comprising the steps of: receiving and storing history information transmitted from another information processing apparatus; and performing an interpreting process on a voice signal transmitted from a terminal. An execution step of performing, an update step of updating the history information stored in the storage step based on the interpretation result of the interpretation process, and specifying the history information stored in the storage step as predetermined information transmitted from the terminal. And transmitting to another information processing apparatus.

According to a sixth aspect of the present invention, a providing medium receives and stores history information transmitted from another information processing apparatus, and executes a translation process on a voice signal transmitted from a terminal. An execution step, an update step of updating the history information stored in the storage step based on the interpretation result of the interpretation process, and the history information stored in the storage step is designated as predetermined information transmitted from the terminal. And a computer-readable program for executing a process including a transmission step of transmitting the information to another information processing apparatus.

[0020] The information processing apparatus according to claim 4, and claim 5.
In the information processing method according to the item (1) and the providing medium according to the item (6), history information transmitted from another information processing device is received, stored, and interpreted for an audio signal transmitted from the terminal. Is executed, the stored history information is updated based on the interpretation result of the interpretation process, and the stored history information is transmitted to another information processing device designated as predetermined information transmitted from the terminal. Sent.

[0021]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of the present invention will be described below. In order to clarify the correspondence between each means of the invention described in the claims and the following embodiments, each means is described. When the features of the present invention are described by adding the corresponding embodiment (however, an example) in parentheses after the parentheses, the result is as follows. However, of course, this description does not mean that each means is limited to those described.

According to the first aspect of the present invention, there is provided an information processing apparatus comprising: a selection means (for example, an interpretation service switching button 24 in FIG. 2) for selecting a predetermined interpretation processing from a plurality of interpretation processings; Transmitting means (for example, the transmitting section 32 in FIG. 3) for transmitting a voice signal addressed to another information processing apparatus to a server executing the interpreting process, and a server executing a predetermined interpreting process selected by the selecting means Receiving means for receiving a voice signal from another information processing apparatus, for example, receiving the voice signal transmitted from the other information processing apparatus, and the predetermined interpreting process selected by the selecting means Is provided with a switching signal transmitting unit (for example, the communication control unit 36 in FIG. 3) for transmitting a switching signal.

The information processing apparatus according to a fourth aspect of the present invention receives the history information transmitted from another information processing apparatus and stores the received information, for example, step S23 in FIG. Execution means (for example, step S26 in FIG. 8) for executing an interpreting process on the audio signal, and updating means (for example, FIG. 8) for updating the history information stored in the storage unit based on the interpretation result of the interpreting process. Step S of 9
44) and transmission means for transmitting the history information stored in the storage means to another information processing apparatus designated by the predetermined information transmitted from the terminal (for example, step S in FIG. 8).
27).

FIG. 1 shows a configuration example of an interpreting service system to which the present invention is applied. Terminal 11 and terminal 12
Are, for example, devices having a telephone function,
It is connected to the network 3. The user A and the user B can talk (talk) via the terminal 11 and the terminal 12.

When the language (for example, Japanese) used by the user A and the language (for example, English) used by the user B are different, the user A and the user B communicate with each other through the three interpreting service providing apparatuses 13-. Through any one of 1 to 13-3, the content of the conversation can be interpreted there.

The interpreting service providing apparatus 13-1 is a server having a history information storage function in addition to a speech recognition function, a machine translation function, and a speech synthesis function. The interpreting service providing apparatus 13-1 stores the speech recognition result and the machine translation result, that is, the contents of the conversation as it is (hereinafter referred to as conversation history information) stored by the history information storage function, and based on it. And execute the interpreting process.

The interpreting service providing apparatus 13-2 is a server having a speech recognition function, a machine translating function, a speech synthesizing function, and a history information storing function, like the interpreting service providing apparatus 13-1. Since more speech recognition language data and machine translation language data are stored in the device 13-2, the interpretation by the interpreting process of the interpreting service providing device 13-2 is performed by the interpreting service providing device 13-1. In comparison, it is considered accurate.

The interpreting service providing apparatus 13-3 is an apparatus having a telephone function capable of connecting to two lines simultaneously and a history information storage function. The operator (human) managing the interpreting service providing apparatus 13-3 translates the conversation between the user A and the user B with reference to the conversation history information stored by the history information storage function.

The interpretation by the operator in the interpreting service providing apparatus 13-3 is performed by the interpreting service providing apparatus 1.
It is more accurate than the interpretation by the translation process of 3-1 and 13-2. In this example, the fee for receiving the interpreting service (hereinafter referred to as the interpreting service fee) is proportional to the accuracy of the interpreting, and the interpreting service fee of the interpreting service providing apparatus 13-3 is the highest. Next, the interpreting service providing apparatus 13-2 and the interpreting service providing apparatus 13-3 are performed in this order.

FIG. 2 shows an example of the configuration outside the terminal 11. On the left side of the main body of the terminal 11, a microphone (not shown) for the user A to input a voice and a speaker (not shown) for outputting the voice of the user B of the other party or the translated voice. A receiver 21 is provided. On its right side, there is provided a display unit 22 on which information to be presented to the user A is displayed, and below it, a keyboard 23 operated when inputting a telephone number and the like; There are provided three interpretation service switching buttons 24-1 to 24-3 that are operated when switching (contents of interpretation).

FIG. 3 shows an example of the internal configuration of the terminal 11. The control unit 31 controls each unit. The transmitting unit 32
The input from the microphone of the handset 21 is controlled.
The button input control unit 33 controls input from the keyboard 23 or the interpreter service switching button 24. Receiver 3
4 controls output of the handset 21 to the speaker, and the display control unit 35 controls display of information on the display unit 22.
The communication control unit 36 controls communication processing for the network 3.

The external appearance and internal configuration of the terminal 12 are basically the same as those of the terminal 11, so that illustration and description thereof are omitted.

FIG. 4 shows an example of the internal configuration of the interpreting service providing apparatus 13-1. The control unit 41 controls each unit. The voice recognition unit 42 has a voice recognition function, refers to the language data for voice recognition stored in the language data storage unit 43, performs voice recognition of a voice signal supplied from the terminal 11 or the terminal 12, and Generate and output text data.

The machine translation unit 44 has a machine translation function,
The text data generated by the voice recognition unit 42 is analyzed, and machine translation is performed by referring to the language data for machine translation stored in the language data storage unit 43 and the conversation history information stored in the history information storage unit 45. Execute the process. For example,
The machine translation unit 44 analyzes the text data (for example, Japanese text data) generated based on the voice signal from the terminal 11 and outputs the text data of the language used by the user B (for example, English text data). Convert to
On the other hand, the machine translation unit 44 analyzes the text data (English text data) generated based on the voice signal from the terminal 12 and converts the text data into text data (Japanese text data) in the language used by the user A. I do.

The speech synthesizer 46 has a speech synthesis function.
The text data translated by the machine translation unit 44 is converted into a speech signal with reference to the speech synthesis language data stored in the language data storage unit 43.

The language data storage unit 43 stores speech recognition language data, machine translation language data, and speech synthesis language data.

The history information storage section 45 has a history information storage function, and has conversation history information (speech recognition result in the speech recognition section 42 and machine translation result in the machine translation section 44).
And service history information such as billing information. In the following, in the case where it is not necessary to distinguish between them, the conversation history information and the service history information are collectively referred to as history information.

The communication control unit 47 controls communication processing for the network 3. For example, the communication control unit 47 receives a voice signal transmitted from the terminal 11 or the terminal 12 via the network 3 and supplies the voice signal to the voice recognition unit 42 or a voice signal of a machine translation result in the machine translation unit 44. To the terminal 12 or the terminal 1 via the network 3.
Send to 1.

FIG. 5 shows an example of the configuration of the interpreting service providing apparatus 13-2.
Since the configuration is basically the same as that described above, a detailed description is omitted. The language data storage unit 53 of the translation service providing apparatus 13-2 has more language recognition language data, machine translation language data, and speech synthesis than the language data storage unit 43 of the translation service providing apparatus 13-1. Language data is stored.

FIG. 6 shows a configuration example of the interpreting service providing apparatus 13-3. The control unit 61 to the communication control unit 66 of the translation service providing apparatus 13-3 have the same functions as those of the control unit 31 to the communication control unit 36 of the terminal 11 in FIG. . The history information storage unit 67 stores conversation history information such as the voice of the user A supplied from the terminal 11, the voice of the user B supplied from the terminal 12, and the voice (interpretation) of the operator, and service history information.

Next, the procedure of the interpreting call process of the terminal 11 will be described with reference to the flowchart of FIG. A communication link between the terminal 11 and the terminal 12 has already been established on the network 3, and the user A and the user B
In a state where the user 1 and the terminal 12 can talk (talk) with each other, the user A operates any one of the interpretation service switching buttons 24-1 to 24-3 of the terminal 11 in step S1. Then, by operating the keyboard 23, for example, the terminal 1 owned by the user B who is the call partner
Necessary information required in the interpreting process of the interpreting service providing apparatus 13 is input, such as the address (for example, telephone number) of No. 2 and the language to be interpreted (for example, Japanese or English).

Next, in step S2, the control unit 31
Is the interpreter service switching button 2 operated in step S1
4 is selected.

In this example, the interpreting service switching button 24-1 corresponds to the interpreting service providing apparatus 13-1, and the interpreting service switching button 24-2 corresponds to the interpreting service providing apparatus 13-2. The interpreter service switching button 24-3 has the interpreter service provider 13
-3 is supported. That is, for example, step S
When the interpreter service switching button 24-1 is operated in step 1, the interpreter service providing apparatus 13-1 is selected in step S2.

In step S3, the control section 31 controls the communication control section 36 to establish a communication link with the translation service providing apparatus 13 selected in step S2. Next, in step S4, the control unit 31 further controls the communication control unit 36, and inputs the interpretation signal to the translation service providing apparatus 13 with which the communication link has been established in step S2 together with a control signal for requesting interpretation in step S1. Required information is transmitted.

Thus, the interpreting service providing apparatus 13-1 selected in step S2 receives the control signal and the necessary information transmitted in step S4, and starts the interpreting process.

In step S5, the control section 31 controls the transmission section 32, the reception section 34, and the communication control section 36 to start the call processing. Thereby, the transmitting unit 32
Converts the voice of the user A input from the microphone of the handset 21 into a voice signal and supplies the voice signal to the communication control unit 36. The communication control unit 36 transmits the audio signal supplied from the transmission unit 32 to the translation service providing apparatus 13 selected in step S2. Further, the communication control unit 36 receives the audio signal transmitted from the interpreting service providing apparatus 13 and supplies it to the receiving unit 34. The receiver 34 converts the audio signal supplied via the communication controller 36 into the handset 2
Output from the first speaker. Thereby, the user A
It is possible to communicate with the user B via an interpreter by the interpreter service providing apparatus 13.

Next, in step S6, the controller 31
Determines whether or not the interpreter service switching button 24 has been operated, and if it has been determined that the
Go to 7. In step S7, the control unit 31 determines whether the communication link between the terminal 11 and the terminal 12 has been disconnected, that is, whether the call between the user A and the user B has ended, and the call has not ended. When the determination is made, the process returns to step S6. In the terminal 11 and the terminal 12, the call is terminated when the handset 21 is returned to a predetermined place, as in a normal telephone.

In step S6, if the control unit 31 determines that the interpretation service switching button 24 has been operated, the process proceeds to step S8, and the control unit 31 switches the interpretation service providing apparatus 13 corresponding to the interpretation service switching button 24 operated in step S6. select.

Next, in step S9, the control unit 31
Controls the communication control unit 36 to transmit an interpretation service switching signal including the address of the translation service providing apparatus 13 newly selected in step S8 to the interpreting service providing apparatus 13 that is currently performing the interpreting process, Step S10
, The communication link with the translation service providing apparatus 13 is disconnected. Thereafter, returning to step S3, the control section 31 controls the communication control section 36 to establish a communication link with the translation service providing apparatus 13 newly selected in step S8, and executes the subsequent processing. That is, this allows the newly selected interpreter service providing device 13
, The call between the user A and the user B is interpreted.

If it is determined in step S7 that the call has ended, the process proceeds to step S11, where the control unit 31
Controls the communication control unit 36 to transmit a control signal for notifying the interpreting service stop to the interpreting service providing apparatus 13 that is executing the interpreting process at that time.
, The service history information transmitted from the interpreting service providing apparatus 13 is received.

In step S13, the control unit 31
The display control unit 35 controls the display control unit 35 to display the service history information received in step S12 on the display unit 22.

Next, in step S14, the control unit 3
1 controls the communication control unit 36 to disconnect the communication link with the translation service providing apparatus 13. Thus, the process is completed.

As described above, the call between the user A and the user B is interpreted by the interpreting process of the interpreting service providing apparatus 13.

The interpreting call processing at the terminal 12 is as follows.
Since this is the same as the case of the terminal 11, the description is omitted.

Next, the procedure of the interpreting process of the interpreting service providing apparatus 13-1 will be described with reference to the flowchart of FIG. In step S21, the control unit 41
The interpreting service providing device 13-1 is controlled by the communication control unit 47.
It waits until the control signal and the required information of the translation request addressed to the address are received, and when the control signal and the required information are received, the process proceeds to step S22.

In step S22, the control unit 41
The communication control unit 47 is controlled to establish a communication link with the device specified in the necessary information. In the case of this example, the necessary information received in step S21 is transmitted from the terminal 11, and it is assumed that the address of the terminal 12 is specified. In step S22, a communication link with the terminal 12 is established. Shall be.

Next, in step S23, the control unit 4
1 determines whether the communication control unit 47 has received history information (conversation history information and service history information) from another translation service providing apparatus 13, and if it is determined that it has been received, proceeds to step S24. Then, the received history information is stored in the history information storage unit 45, and step S25 is performed.
Proceed to. On the other hand, when it is determined in step S23 that the history information has not been received, the process in step S24 is skipped, and the process proceeds to step S25.

In step S25, the control section 41
The communication control unit 47 waits until an audio signal from the terminal 11 or the terminal 12 is received. When the audio signal is received, the process proceeds to step S26, where the speech recognition unit 42, the machine translation unit 44, the speech synthesis unit 46 , And history information storage unit 4
5 to execute a translation process on the audio signal received in step S25. Details of the translation process in step S26 are shown in the flowchart of FIG.

That is, in step S 41, the speech recognition section 42 refers to the speech recognition language data stored in the language data storage section 43 and performs speech recognition on the speech signal received by the communication control section 47. Generate text data in the corresponding language.

In step S42, the machine translation unit 44
Is stored in the history information storage unit 4 together with machine translation language data such as grammar rules stored in the language data storage unit 43.
With reference to the conversation history information stored in No. 5, the text data generated by the voice recognition unit 42 is analyzed and converted (translated) into text data in another language.

In step S43, the speech synthesizer 46
Converts the text data generated by the machine translation unit 44 into an audio signal.

Next, in step S44, the history information storage unit 45 stores the speech recognition result in step S41,
The conversation history information in the history information storage unit 45 is updated based on the machine translation result in step S42. At this time, the history information storage unit 45 also stores service history information such as charging information updated by the control unit 41, for example. As a result, the translation process ends, and the process proceeds to step S27 in FIG.

In step S27, the control section 41
The communication control unit 47 is controlled to cause the terminal 11 or the terminal 12 to transmit the translation result (voice signal) obtained by the processing in step S26. Naturally, the translation result based on the audio signal from the terminal 11 is transmitted to the terminal 12,
The translation result based on the audio signal from is transmitted to the terminal 11.

Next, at step S28, the control unit 4
1 determines whether or not the interpretation service switching signal has been received by the communication control unit 47, and if it is determined that the interpretation service switching signal has been received, the process proceeds to step S29, where the communication control unit 47 is controlled to receive the interpretation service switching signal. A communication link with the designated interpreting service providing apparatus 13 is established.

In step S30, the control unit 41
The history information (conversation history information and service history information) is read from the history information storage unit 45, and in step S31, the communication control unit 47 is controlled and transmitted to the translation service providing apparatus 13 with the communication link established in step S29. .

Next, at step S32, the control unit 4
1 controls the communication control unit 47, and the terminals 11, 12,
Then, the communication link with the interpreting service providing apparatus 13 is disconnected, and thereafter, the process returns to step S21 and waits until the next control signal and necessary information are received.

In step S28, the communication control unit 47
When it is determined that the interpretation service switching signal has not been received, the process proceeds to step S33, and the control unit 41
The communication control unit 47 determines whether a control signal for notifying the end of the interpreting process has been received. If it is determined that the control signal has not been received, the process returns to step S25.
Execute the subsequent processing.

On the other hand, if it is determined in step S33 that the communication control unit 47 has received the control signal for notifying the end of the interpreting process, the process proceeds to step S34. The service history information is read, and in step S35, the communication control unit 4
7 is transmitted to the terminal 11.

Next, in step S36, the control unit 4
1 controls the communication control unit 47, and controls the terminal 11 and the terminal 1
2 is disconnected, and thereafter, in step S21
And wait until the next control signal and necessary information are received.

Next, the operation procedure of the terminal 11 of the user A will be described.
A description will be given corresponding to a specific situation. When the conversation with the user B is, for example, a chat, and does not require an accurate interpreter, the user A can use the interpreter service switch button 24-
Operate 1 Thereby, the conversation between the user A and the user B is interpreted by the interpreting process of the interpreting service providing apparatus 13-1. In this case, the conversation between the user A and the user B is not so accurately interpreted, but the interpreter service fee is lower than in the interpreter service providing devices 13-2 and 13-3, so that the user A Call costs can be kept low. That is, user A
The interpreter service switching button 24 to be operated can be selected in consideration of the cost for the interpreter.

However, when a more accurate interpretation is required, for example, when a chat is over and a business conversation is to be started, the user A operates the interpretation service switching button 24-2. Thereby, the conversation between the user A and the user B is performed by the interpreting service providing apparatus 13-.
Interpretation is performed by the second interpreting process, and the interpretation is more accurately performed as compared with the above-described interpretation by the interpretation service providing apparatus 13-1.

When the conversation with the user B becomes more specialized and the interpreting process of the interpreting service providing apparatus 13-2 stops accurate interpretation, the user A
This time, the interpreter service switching button 24-3 is operated. Thereby, the conversation between the user A and the user B is interpreted by the operator who manages the interpreting service providing apparatus 13-3, and in this example, the interpretation is most accurate.

As described above, the user A can change the required accuracy of the interpreter (contents of the interpreter) only by operating the interpreter service switching button 24 without interrupting the communication with the user B. Can be.

Next, the above-described operation of the user A on the terminal 11, that is, the interpretation service switching button 24-1,
The main operations of the translation service providing apparatuses 13-1 to 13-3 when the translation service switching button 24-2 and the translation service switching button 24-3 are operated in this order will be described.

When a call between the user A and the user B is interpreted by the call processing in the interpreting service providing apparatus 13-1, when the interpreting service switching button 24-2 of the terminal 11 is operated by the user A, In the interpreting service providing apparatus 13-1, the interpreting service switching signal transmitted from the terminal 11 is received by the communication control unit 47 (step S28). This establishes a communication link with the translation service providing apparatus 13-2 specified in the translation service switching signal (step S29).

Next, the contents of the conversation (conversation history information) between the user A and the user B so far and the service history information such as billing information are read from the history information storage section 45 of the interpreting service providing apparatus 13-1. (Step S30) and transmitted to the interpreting service providing apparatus 13-2 (step S3).
1). Thereafter, the communication link between the terminal 11 and the terminal 12 is disconnected (step S32).

In the interpreting service providing apparatus 13-2 corresponding to the interpreting service switching button 24-2, the same processing as in steps S21 and S22 in FIG. The transmitted history information is received by the communication control unit 57 (process similar to step S23), and stored in the history information storage unit 55 (process similar to step S24).

When an audio signal is received from terminal 11 or terminal 12 (the same processing as in step S25), a translation process is performed on the received audio signal (step S25).
26). In this case, the terminal 11 or the terminal 1
2 is subjected to speech recognition by the speech recognition unit 52 of the translation service providing apparatus 13-2 based on the speech recognition language data in the language data storage unit 53 (step S4).
1), the machine translation unit 54 refers to the conversation history information in the history information storage unit 55 together with the machine translation language data in the language data storage unit 53, and performs machine translation (process similar to step S42). ).

For example, when a pronoun such as “that”, “that”, “he” or “her” is used in a conversation, a proper noun corresponding to the pronoun is transmitted from the interpreting service providing apparatus 13-1. The determination is made based on the transmitted conversation history information. Further, when a predetermined expression is omitted in the conversation, the meaning of the expression is similarly determined based on the conversation history information. In this manner, the conversation between the user A and the user B is performed by referring to the conversation history information stored in the history information storage unit 55 and performing machine translation.
In the interpreting service providing apparatus 13-2, interpreting is performed more accurately.

The conversation history information stored in the history information storage unit 55 is updated based on the speech recognition result in the speech recognition unit 52 and the machine translation result in the machine translation unit 54. (Process similar to step S44).

The translation result in the machine translation section 54 is converted into a speech signal by the speech synthesis section 56 (step S43).
Is transmitted to the terminal 11 or the terminal 12 (processing similar to step S27).

Thus, the interpreting service providing apparatus 1
The interpreting process in 3-2 is executed. When the interpreter service switching button 24-3 of the terminal 11 is operated by the user A, the interpreter service transmitted from the terminal 11 is transmitted to the interpreter service providing apparatus 13-2. The switching signal is received (the same processing as in step S28). This allows
A communication link is established between the translation service providing apparatus 13-2 and the translation service providing apparatus 13-3 selected corresponding to the translation service switching button 24-3 (step S2).
9).

Thereafter, the history information is read from the history information storage unit 55 of the interpretation service providing apparatus 13-2 (the same processing as in step S30), and the interpretation service providing apparatus 1
It is transmitted to 3-3 (the same processing as step S31).
Then, the communication links with the terminals 11, 12 and the interpreting service providing apparatus 13-3 are disconnected (the same processing as in step S32).

Next, an interpreting process is performed in the interpreting service providing apparatus 13-3. At this time, the operator directly listens to the conversation between the user A and the user B and translates the conversation. In this case, the operator refers to the conversation history information (the contents of the past conversation) displayed on the display unit (not shown) of the interpreting service providing apparatus 13-3, and consults the conversation between the user A and the user B. Translator.

The audio signal from the terminal 11 and the audio signal from the terminal 12 supplied to the interpretation service providing apparatus 13-3,
And the voice (translation) of the operator are stored in the history information storage unit 6.
7 is stored. The history information stored in the history information storage unit 67 corresponds to the operation of the interpreter service switching button 24 of the terminal 11 and corresponds to the interpreter service providing devices 13-1 and 13-1.
-2.

In this way, the interpreting service providing apparatus 1
3-1 to 13-3 store the content of the conversation as conversation history information and transmit it to the translation service providing apparatus 13 corresponding to the translation service switching button 24. Calls are interpreted correctly.

In the above, for simplicity, the user A
Operates the interpretation service switching button 24 of the terminal 11 as an example.
By operating the interpreter service switching button, the accuracy of the interpreter can be easily switched.

In the above description, the case where three levels of translation accuracy are selected by the three translation service switching buttons 24-1 to 24-3 has been described as an example. , A particular field can be selected.

Further, the contents of interpretation in the interpreting service providing apparatus 13 are displayed on the display unit 22 of the terminal 11, and it can be easily determined whether or not the interpreting in the interpreting service providing apparatus 13 is properly performed. You can do so.

In this specification, the term “system” refers to an entire device including a plurality of devices, means, and the like.

Further, as a providing medium for providing a user with a computer program for performing the processing as described above,
In addition to recording media such as magnetic disks, CD-ROMs, and solid-state memories, communication media such as networks and satellites can be used.

[0092]

According to the information processing apparatus according to the first aspect, the information processing method according to the second aspect, and the providing medium according to the third aspect, a predetermined switching signal is transmitted. Servers can be easily switched.

The information processing apparatus according to claim 4, and claim 5
According to the information processing method described in (1) and the providing medium described in (6), the interpretation is performed more accurately because the history information is received and the interpreting process is executed based on the history information.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a configuration example of an interpreting service system to which the present invention has been applied.

FIG. 2 is a diagram illustrating a configuration example of an appearance of a terminal 11 in FIG.

FIG. 3 is a diagram illustrating an example of an internal configuration of a terminal 11 in FIG.

FIG. 4 is a diagram illustrating a configuration example of an interpreting service providing apparatus 13-1 in FIG. 1;

FIG. 5 is a diagram illustrating a configuration example of an interpreting service providing apparatus 13-2 in FIG. 1;

FIG. 6 is a diagram illustrating a configuration example of an interpreting service providing apparatus 13-3 in FIG. 1;

FIG. 7 is a flowchart illustrating a procedure of an interpreting call process.

FIG. 8 is a flowchart illustrating a procedure of an interpreting process.

FIG. 9 is a flowchart illustrating a procedure of a translation process.

FIG. 10 is a diagram showing a conventional interpreting service system.

[Explanation of symbols]

1 terminal, 2 terminals, 3 networks, 4 interpreting service providing device, 11 terminals, 12 terminals, 1
3 Interpretation service providing device, 21 Handset, 22
Display unit, 23 keyboard, 24 interpreter service switching button, 31 control unit, 32 transmission unit, 33
Button input control unit, 34 reception unit, 35 display control unit, 36 communication control unit, 41 control unit, 42 voice recognition unit, 43 language data storage unit, 44 machine translation unit, 45 history information storage unit, 46 voice synthesis unit,
47 communication control unit, 51 control unit, 52 speech recognition unit, 53 language data storage unit, 54 machine translation unit, 55 history information storage unit, 56 speech synthesis unit,
57 communication control unit, 61 control unit, 62 transmission unit,
63 button input control unit, 64 earpiece unit, 65
Display control unit, 66 communication control unit, 67 history information storage unit

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Masato Shimakawa 6-7-35 Kita-Shinagawa, Shinagawa-ku, Tokyo Inside Sony Corporation (72) Inventor Osamu Hamada 6-35-35 Kita-Shinagawa, Shinagawa-ku, Tokyo Sony Corporation F term (reference)

Claims (6)

[Claims] 1. An information processing apparatus connected via a network to a server that executes a plurality of interpreting processes and another information processing apparatus, comprising: a selecting unit that selects a predetermined interpreting process from the plurality of interpreting processes; Transmitting means for transmitting an audio signal addressed to the other information processing device to a server for executing the predetermined interpreting processing selected by the selecting means; and executing the predetermined interpreting processing selected by the selecting means Receiving means for receiving a voice signal transmitted from the server, from which the predetermined interpreting processing has been executed, from the another information processing apparatus, and executing the predetermined interpreting processing selected by the selecting means; An information processing apparatus comprising: a server; and a switching signal transmitting unit that transmits a switching signal. 2. An information processing method for an information processing device connected via a network to a server that executes a plurality of interpreting processes and another information processing device, wherein a predetermined interpreting process is selected from the plurality of interpreting processes. A selecting step, a transmitting step of transmitting an audio signal addressed to the other information processing device to a server that executes the predetermined interpreting process selected in the selecting step, and the predetermined interpreter selected in the selecting step A receiving step of receiving a voice signal from the other information processing apparatus, from which the predetermined interpreting process has been executed, transmitted from the server performing the process, and the predetermined interpreting process selected in the selecting step Transmitting a switching signal to the server executing the server. A selecting step of selecting a predetermined interpreting process from the plurality of interpreting processes, to an information processing device connected via a network to a server executing the plurality of interpreting processes and another information processing device; A transmitting step of transmitting an audio signal addressed to the other information processing device to a server that executes the predetermined interpreting process selected in the selecting step; and executing the predetermined interpreting process selected in the selecting step. A receiving step of receiving an audio signal transmitted from the other information processing apparatus, wherein the predetermined interpreting process has been executed and transmitted from the server; and the executing the predetermined interpreting process selected in the selecting step. A computer-readable program for causing a server to execute a process including a switching signal transmitting step of transmitting a switching signal is provided. Providing medium to be. 4. An information processing apparatus connected via a network to a plurality of terminals capable of talking and another information processing apparatus, receiving and storing history information transmitted from the other information processing apparatus. A storage unit, an execution unit that executes an interpreting process on an audio signal transmitted from the terminal, and an update that updates the history information stored in the storing unit based on an interpretation result of the interpreting process. And information transmitting means for transmitting the history information stored in the storage means to another information processing apparatus designated by predetermined information transmitted from the terminal. apparatus. 5. An information processing method for an information processing apparatus connected to a plurality of terminals capable of talking and another information processing apparatus via a network, wherein history information transmitted from the other information processing apparatus is received. And a storage step of storing; an execution step of executing an interpreting process on a voice signal transmitted from the terminal; and, based on an interpretation result of the interpreting process, the history information stored in the storing step. An update step of updating, and a transmission step of transmitting the history information stored in the storage step to another information processing apparatus designated by predetermined information transmitted from the terminal. Information processing method. 6. An information processing apparatus connected to a plurality of terminals capable of talking and another information processing apparatus via a network receives and stores history information transmitted from the other information processing apparatus. A storage step; an execution step of executing an interpreting process on a voice signal transmitted from the terminal; and an updating step of updating the history information stored in the storing step based on an interpretation result of the interpreting process. And a transmission step of transmitting the history information stored in the storage step to another information processing device designated by the predetermined information transmitted from the terminal. A providing medium characterized by providing a program.