JP2017201737A - Information processing apparatus, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable easy-to-understand display according to an occurrence of an event in a display of a result of textualization of a speech.SOLUTION: A distribution apparatus 100 acquires data based on a speech that is a speech of a person and is converted into text for display and determines that a predetermined event corresponding to an action of a person who makes a speech to be converted into a text has occurred. Then, the distribution apparatus 100 switches an output of the acquired data based on the speech to be converted into a text on the basis of the determination result of the event occurrence.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a technique for outputting data based on an utterance that is converted into text.

  2. Description of the Related Art Conventionally, in order to enable a conference between remote sites, there is a multipoint conference system that distributes video and audio of conference participants at each site to other sites. In addition, there is a conference system that makes it possible to visually recognize the content of the conference by converting the speech of the conference participant into text and displaying it on a display or the like. Patent Document 1 describes that a statement file in a meeting is made into text, and a minutes file is created in which the text is associated with information indicating a comment time and a speaker of each comment.

JP 2007-180828 A

  However, with the method of Patent Document 1, it is possible that the result of texting a statement cannot be displayed according to the occurrence of an event, and the display becomes difficult for the user to understand. For example, consider a case where there are a plurality of participants at each of a plurality of bases in a conference by a multipoint conference system. In this case, if the statements made for all participants at different locations and the statements made only for participants in the same location are made into a text without being distinguished, the user can make a conference based on the textual results. May be difficult to understand. In addition, not only in a multipoint conference system but also in a case where a conference is held between two bases, there is a similar problem. There is a similar problem when texts of conferences held in one site are converted into texts.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to provide a technique for enabling easy-to-understand display according to the occurrence of an event in the display of a result obtained by converting a statement into text.

  In order to solve the above problems, an information processing apparatus according to the present invention has, for example, the following configuration. That is, it is determined that an acquisition unit that acquires data based on a person's utterance that is converted into text for display, and that a predetermined event corresponding to the action of the person who performs the textized utterance has occurred Discriminating means for switching, and switching means for switching the output of data based on the utterance made into text acquired by the acquiring means based on the determination result by the discriminating means.

  According to the present invention, an easy-to-understand display according to the occurrence of an event can be performed in the display of the result of converting a comment into text.

1 is a diagram illustrating an overall configuration of a multipoint conference system 10 according to an embodiment. It is a block diagram which shows the function structure of the delivery apparatus 100 which concerns on embodiment. 2 is a block diagram illustrating a hardware configuration of a distribution apparatus 100. FIG. 5 is a flowchart for explaining the operation of the distribution apparatus 100. 6 is a diagram illustrating an example of display contents of the display device 104. FIG.

  Embodiments of the present invention will be described below with reference to the drawings. Note that not all configurations described in the following embodiments are essential to the present invention.

[System configuration]
The overall configuration of the multipoint conference system 10 according to the present embodiment will be described with reference to FIG. The multipoint conference system 10 includes a distribution device 100, a communication device 101, a microphone 102, a camera 103, and a display device 104 installed in each of the base A, the base B, and the base C. The microphone 102, camera 103, and display device 104 are each connected to the communication device 101 at the same location. Further, each communication device 101 installed at each base is connected to the distribution device 100 via a network. By using the multipoint conference system 10, the user can share video, audio, data, etc. in real time between bases. In addition, the multipoint conference system 10 converts the speech of a person existing at each base into text so that it can be displayed.

  In the present embodiment, the multipoint conference system 10 in the case where the distribution apparatus 100 controls communication between the three bases A, B, and C will be mainly described. However, the present invention is not limited to this, and the distribution apparatus 100 may be connected to the communication apparatuses 101 installed at four or more bases to control communication between those bases, or control communication between the two bases. Also good. Further, at least one of the communication devices 101 installed at each base may have the function of the distribution device 100, and the communication devices 101 may be directly connected to perform communication. In addition, at least one of the microphone 102, the camera 103, and the display device 104 may be configured integrally with the communication device 101. In this case, the microphone 102 functions as a sound collection unit of the communication device 101, the camera 103 functions as an imaging unit, and the display device 104 functions as a display unit. Further, at least one of the communication device 101, the microphone 102, the camera 103, and the display device 104 may be installed in the same base, or at least one of the microphone 102, the camera 103, and the display device 104 does not exist. There may be a base.

  Next, functions of each device included in the multipoint conference system 10 will be described. The microphone 102 collects the voice in the base such as a speech of a conference participant and outputs it to the communication device 101. For example, the camera 103 captures a predetermined area in the base such as a conference room where conference participants exist, and outputs the captured image to the communication apparatus 101. In the present embodiment, the captured image output by the camera 103 is a moving image, but the camera 103 may output a still image. The display device 104 displays the image data input from the communication device 101. The image data input from the communication apparatus 101 includes, for example, a captured image captured at another site, characters that are texts of statements made during a meeting, and the like. FIG. 5 shows an example of the contents displayed on the display device 104. In the present embodiment, the display device 104 includes a speaker and outputs sound based on audio data input from the communication device 101. Specific examples of the display device 104 include a liquid crystal display and a projector. Note that the speaker may be provided separately from the display device 104.

  The communication device 101 generates audio data based on the voice input from the microphone 102 and transmits the audio data to the distribution device 100. In addition, the communication apparatus 101 transmits the captured image input from the camera 103 to the distribution apparatus 100. Then, the communication device 101 receives audio data based on the sound collected at each site from the distribution device 100 and outputs it to the display device 104 having a speaker. Further, the communication device 101 receives text data obtained by converting the voice collected at each site into text and a captured image captured at each site from the distribution device 100, and includes image data including the remark content and the captured image at each site. Is generated and output to the display device 104.

  As illustrated in FIG. 2, the distribution apparatus 100 includes a conversion unit 300 and a session management unit 301. The conversion unit 300 performs speech recognition processing on the audio data received by the session management unit 301 from the communication device 101 at each site, thereby converting the speech included in the audio data into text and generating character data. Specifically, the conversion unit 300 calculates a feature amount from the audio data and compares it with a database of feature amounts stored in the distribution device 100, thereby converting the speech included in the audio data into characters. Note that the speech recognition method is not limited to this and may be another method. The session management unit 301 receives audio data and captured images from the communication device 101 at each site. The session management unit 301 transmits the received audio data and captured image to the communication device 101 at each site together with the character data generated by the conversion unit 300 based on the audio data. Here, the session management unit 301 controls a session used for data transmission according to the event occurrence state at each site. Details of this session control will be described later. Note that the session in the present embodiment is a unit of a series of identifiable communication such as an HTTP session managed using a session ID in HTTP (Hypertext Transfer Protocol), for example. The distribution apparatus 100 transmits / receives data to / from different communication apparatuses 101 using different sessions. In addition, when the distribution apparatus 100 transmits data to the same communication apparatus 101 using a plurality of sessions, the communication apparatus 101 can process the received data by distinguishing each session.

[Hardware configuration]
FIG. 3 is a block diagram illustrating a hardware configuration of the distribution apparatus 100 according to the present embodiment. Note that the communication device 101 has the same configuration as the distribution device 100. The distribution device 100 includes a CPU 201, a ROM 202, a RAM 203, an auxiliary storage device 204, an operation unit 205, a communication unit 206, and a bus 207.

  The CPU 201 controls the entire distribution apparatus 100 using computer programs and data stored in the ROM 202 and the RAM 203. The ROM 202 stores programs and parameters that do not need to be changed. The RAM 203 temporarily stores programs and data supplied from the auxiliary storage device 204 and data supplied from the outside via the communication unit 206. The auxiliary storage device 204 is constituted by a hard disk drive, for example, and stores content data such as image data and audio data.

  The operation unit 205 includes, for example, a keyboard and a mouse, and inputs various instructions to the CPU 201 in response to user operations. The communication unit 206 communicates with an external device such as the communication device 101. For example, when the distribution device 100 is connected to an external device by wire, a LAN cable or the like is connected to the communication unit 206. Note that when the distribution device 100 has a function of performing wireless communication with an external device, the communication unit 206 includes an antenna. A bus 207 connects the units of the distribution apparatus 100 to transmit information.

  In this embodiment, the CPU 201 executes a program to control communication between the distribution apparatus 100 and an external apparatus via the communication unit 206. However, at least a part of communication between the distribution apparatus 100 and the external apparatus is controlled. The communication unit 206 may be controlled by hardware processing. In this embodiment, the operation unit 205 exists inside the distribution apparatus 100, but the operation unit 205 may exist outside the distribution apparatus 100 as another apparatus. In this case, the CPU 201 operates as an operation control unit that controls the operation unit 205. When the distribution device 100 is connected to an external display device, the CPU 201 operates as a display control unit that controls the display device.

[Operation flow]
Next, an operation flow of the distribution apparatus 100 that controls a conference between a plurality of bases will be described with reference to FIG. The process shown in FIG. 4 is started when the distribution apparatus 100 receives a conference start request from the communication apparatus 101 at any base. However, the start timing of the process shown in FIG. 4 is not limited to the above timing. The processing shown in FIG. 4 is realized by the CPU 201 developing the program stored in the ROM 202 on the RAM 203 and executing it. Note that at least part of the processing illustrated in FIG. 4 may be realized by dedicated hardware different from the CPU 201.

  In step S <b> 401, the session management unit 301 issues a session setting instruction for starting a multipoint conference to the communication device 101 at each site. Upon receiving the instruction, each communication device 101 sets a session for performing communication with the distribution device 100 and responds. Note that the configuration of the present embodiment is effective even when a conference is held between two sites, and also effective when a conference is held within one site. An application example when a conference is held within one site will be described later. In S402, the session management unit 301 determines whether a predetermined event has occurred at any of the bases. If it is determined that a predetermined event has not occurred, the process proceeds to S404. On the other hand, if it is determined that a predetermined event has occurred, the process proceeds to S403, and the session management unit 301 performs session control based on the determination result. Details of the predetermined event and details of session control will be described later.

  In step S404, the session management unit 301 receives audio data transmitted from a plurality of communication devices 101 (communication devices 101 at bases A, B, and C). This audio data is generated from the sound collected by the microphone 102 by the communication device 101 of the transmission source, and includes speech that is converted into text in the conference. In S <b> 405, the conversion unit 300 generates and acquires character data representing characters such as a person's remarks in the conference by converting into text based on the audio data acquired by the session management unit 301 in S <b> 404.

  In S406, the session management unit 301 transmits the audio data received in S404 and the character data acquired by the conversion unit 300 in S405 to the communication device 101 at each site. When session control is performed in S403, data transmission is performed in a session corresponding to the session control. The communication device 101 at each site outputs to the display device 104 based on the received data. Specifically, the communication device 101 outputs audio data to the display device 104, thereby causing the display device 104 to output sound collected at another site. In addition, the communication device 101 outputs image data based on the received character data to the display device 104, thereby displaying the result of converting the voice collected at the local site or the other site into text, that is, the content of the speech in the conference. It is displayed on the device 104.

  In S407, the session management unit 301 determines whether to end the multipoint conference. If it is determined not to end the conference, the distribution apparatus 100 executes the processing from S402 again. On the other hand, when it is determined that the conference is to be ended, the session management unit 301 instructs the communication device 101 at each site to end the session used for communication, and ends the processing illustrated in FIG. The case where it is determined that the conference is to be ended is, for example, a case where the distribution device 100 receives a conference end request from the communication device 101.

  This is the end of the description of the operation flow of the distribution apparatus 100. In the above description, the description has focused on the transmission of audio data and character data from the distribution apparatus 100 to the communication apparatus 101. However, in addition to this, the distribution apparatus 100 according to the present embodiment receives a captured image from the communication apparatus 101 at each site and starts the communication apparatus 101 at another site from the start of the conference in S401 to the end in S407. Send to. The communication device 101 that has received the captured image from the distribution device 100 outputs image data based on the captured image to the display device 104, thereby causing the display device 104 to display images of conference participants at other locations. The distribution apparatus 100 may not transmit the captured image. Further, the distribution apparatus 100 may receive the contents of the input by the digitizer and other data from the communication apparatus 101 at any base and transfer them to the communication apparatus 101 at each base.

[Session control method]
Next, details of the event occurrence determination in S402 and the session control in S403 will be described. In step S <b> 402, the session management unit 301 first acquires a captured image transmitted from the communication apparatus 101. And the session management part 301 discriminate | determines that the predetermined | prescribed event according to the operation | movement of the person who performs the utterance made into text generate | occur | produces by analyzing the acquired captured image. In the present embodiment, the predetermined event is, for example, that a person who makes a statement made into text (a person in the captured image) faces a predetermined direction, or a person making a statement made into a text is in a predetermined area. Such as touching. However, the contents of the event determined by the session management unit 301 are not limited to these, and may include, for example, a user operating a predetermined switch. In step S <b> 403, the session management unit 301 switches the session used for data output (transmission) to the communication apparatus 101 in step S <b> 406 based on the determination result of the event occurrence. For example, the session management unit 301 sets a new session with the communication apparatus 101 according to the determination result, and uses the newly set session for data output. Further, for example, the session management unit 301 ends any one of a plurality of sessions set with the communication apparatus 101 according to the determination result, and outputs data using the remaining sessions that have not ended.

  Hereinafter, a specific example of session switching according to the occurrence of an event will be described. The microphone 102 at the site A collects the speech of the conference participant at the site A, and the communication apparatus 101 transmits audio data including the collected voice to the distribution apparatus 100. The camera 103 at the site A captures an area including the conference participant at the site A and the display screen of the display device 104, and the communication device 101 transmits the captured image to the distribution device 100.

  FIG. 5 is a diagram illustrating an example of display contents of the display device 104 at the site A. In the display area 500, a thread 501 indicating the result of texting the speech in the conference, a thread 504 indicating the result of texting the conversation in the site B, and the result of texting the conversation in the site C are shown. A thread 505 is displayed. In addition to this, in the display area 500, a captured image 502 in which a conference participant at the base B is copied and a captured image 503 in which the conference participant at the base C is copied are displayed.

  The conference participant at the site A speaks while viewing the display device 104 when speaking to the conference participants at the site B and the site C. On the other hand, the conference participants at the site A may have a conversation that is unrelated to the content of the conference with another site between the conference participants in the site A. When performing a conversation in such a base, a conference participant at the base A speaks in a direction different from the display device 104 (for example, a direction in which another conference participant in the same base is present).

  When the session management unit 301 analyzes the captured image received from the communication device 101 at the site A and determines that an event has occurred in which the conference participant faces a direction different from the display device 104, data transmission is performed. Switch the session used for. In other words, the distribution device 100 generates character data obtained by converting a statement when the conference participant at the site A is viewing the display device 104 and character data obtained by converting the statement when the conference participant is looking in another direction into text. Then, the data is transmitted to the communication device 101 at each site using a different session.

  Since the communication device 101 at each site can distinguish character data received using different sessions, the character data can be easily processed in different ways. For example, in the display device 104, it is possible to distinguish between characters in which utterances made before the occurrence of a predetermined event are converted into text and characters in which utterances made after the occurrence of the predetermined event are converted into text Can be displayed. Since the content of the utterance before and after the event occurrence is displayed in an identifiable manner, the user can easily understand the context of the utterance in the conference from the display on the display device 104.

  For example, in FIG. 5, the text in which the speech when the conference participant at the base B is looking at the display device 104 is displayed in the thread 501, and the conference participant at the base B sees the other direction. The character in which the utterance is converted into text is displayed in the thread 504. Note that the method of displaying the utterance contents before and after the occurrence of the event in an identifiable manner is not limited to the method of displaying the characters in which the utterance is converted into text at different positions according to the determination result of the event occurrence. For example, the communication device 101 may switch the color or font of characters displayed on the display device 104 according to the determination result.

  Next, another specific example relating to session switching according to the occurrence of an event will be described. The conference participant at site A may want to talk about the content that the conference participant at site B does not want to be known as the conference participant at site C. In this way, when a conversation with a specific site C is performed, a conference participant at the site A touches an image of the conference participant at the site B (captured image 502 in FIG. 5) displayed on the display device 104, for example. do.

  When the session management unit 301 analyzes the captured image received from the communication device 101 at the site A and determines that an event has occurred in which the conference participant touches the image of the conference participant at the site B, data transmission is performed. Switch the session used for. Specifically, the session management unit 301 transmits the text data, which is a comment when the conference participant at the base A touches the image of the conference participant at the base B, to the base A and the base C. Is transmitted using only the current session, and is not transmitted to the site B. In other words, the distribution device 100 determines that a predetermined event has occurred in the output device of the character data in which the utterance is converted to text among the plurality of communication devices 101 (communication devices 101 of the bases A, B, and C). Switching based on the determined result. In addition, the session management unit 301 switches the output destination of the audio data based on the sound collected at the site A in the same manner as the output destination of the character data. As a result, regarding the remarks directed only from the base A to the base C, the text and voice of the remarks are not transmitted to the base B. As a result, in a conference between a plurality of bases, a conversation transmitted only to a specific base can be performed, and further, the contents can be displayed in characters only on the display device 104 of the specific base.

  Heretofore, the event occurrence determination in the distribution apparatus 100 and the session control according to the determination result have been described. In the above description, the session management unit 301 determines that a predetermined event has occurred by analyzing the captured image received from the communication apparatus 101. Thereby, the user can switch the output destination of data without performing a complicated operation. Note that the method for determining event occurrence in the distribution apparatus 100 is not limited to this. For example, the communication apparatus 101 detects the occurrence of a predetermined event by analyzing an image captured by the camera 103 and transmits a notification indicating the occurrence of the predetermined event to the distribution apparatus 100. Then, the session management unit 301 may receive a notification indicating the occurrence of a predetermined event from the communication apparatus 101, and may determine that the predetermined event has occurred based on the notification. According to this method, the processing load on the distribution apparatus 100 can be reduced. In addition, the method for determining that a predetermined event has occurred is not limited to analysis of a captured image, and the occurrence of an event may be determined by, for example, analyzing sound collected by the microphone 102.

  In the present embodiment, the distribution apparatus 100 receives audio data generated by collecting voice at each site from the communication apparatus 101, and converts the speech included in the audio data into text by voice recognition, thereby converting the character data. The case of generating was explained. However, the method by which the distribution apparatus 100 acquires character data is not limited to this. For example, the distribution device 100 transmits the audio data received from the communication device 101 to an external conversion device, the conversion device generates character data from the received audio data, and the distribution device 100 receives the generated character data from the conversion device. You may get it. Further, for example, the distribution apparatus 100 outputs voice based on the audio data received from the communication apparatus 101 via a speaker, and an operator who has heard the voice inputs character data to the distribution apparatus 100 using an input device such as a keyboard. May be.

  Further, in the present embodiment, the case where the distribution apparatus 100 switches the session used for outputting the character data based on the utterance based on the determination result of determining the occurrence of the event has been mainly described. However, the distribution apparatus 100 may switch data output based on the determination result by a method other than session switching. The switching of output by the distribution apparatus 100 includes switching of an output destination, switching whether to output, switching of output contents, and the like.

  Further, the data to be switched is not limited to character data generated by converting the text into a text as long as the data is based on the text converted into text for display. For example, the distribution apparatus 100 may acquire audio data generated by collecting voice including speech from the communication apparatus 101 and switch the output of the audio data to the communication apparatus 101 based on the determination result of the event occurrence. Good. Then, the communication device 101 that has received the audio data output from the distribution device 100 may cause the display device 104 to display the result of converting the speech included in the audio data into text. Even in such a configuration, the textual contents of the meeting can be displayed on the display device 104 so as to be easily understood by the user.

  As described above, the distribution apparatus 100 according to the present embodiment acquires data based on a utterance of a person and converted into text for display, and responds to the action of the person who makes the utterance converted into text. It is determined that a predetermined event has occurred. Then, the distribution apparatus 100 switches the output of data based on the acquired text-formed utterance based on the determination result of the event occurrence. As a result, the communication device 101 that receives the output from the distribution device 100 can display an easy-to-understand display according to the occurrence of an event when displaying the result of converting the text into a text on the display device 104 and presenting it to the user. Become.

  In the present embodiment, the case where the distribution apparatus 100 that relays communication between the plurality of communication apparatuses 101 operates as an information processing apparatus that switches the output of data based on the utterances that are converted into text based on the determination result of the event occurrence. Explained. As described above, the distribution device 100 collectively controls communication between the plurality of communication devices 101, whereby the multipoint conference system 10 with simple processing can be configured. However, the present invention is not limited to this, and even when each communication device 101 operates as an information processing device having the same function as the distribution device 100 described above and the communication devices 101 communicate directly with each other without using the distribution device 100. The effect similar to this embodiment can be acquired. In the following, a case where the communication apparatus 101 that transmits data based on the utterance to be converted to text switches the output of the data, and a case where the communication apparatus 101 that has received data based on the utterance that is converted to the text from another base outputs the data. Two ways of switching are described. In the multipoint conference system 10 described below, the communication device 101 at each base has a conversion unit 300 and a session management unit 301, and the communication devices 101 are directly connected to each other.

  First, the case where the communication apparatus 101 on the data transmission side switches the output will be described. When a conference participant makes a statement at the site A, the voice is collected by the microphone 102 at the site A, and the communication device 101 at the site A obtains data based on the collected voiced statement and obtains data. B (output) to the communication device 101 at B and site C. Here, the data based on the utterances that are converted into text and output from the communication device 101 at the site A may be audio data generated by collecting voices or characters generated by converting the utterances into text. It may be data. When the character data is output, the communication devices 101 of the base B and the base C that have received the character data generate image data including the character indicated by the character data and cause the display device 104 to display the image data. On the other hand, when the audio data is output, the communication devices 101 of the bases B and C that have received the audio data convert the speech included in the audio data into text, and display the image data including the characters obtained as a result on the display device 104. Display.

  When the communication apparatus 101 at the site A determines that a predetermined event has occurred, the communication apparatus 101 switches the output of data based on the above-mentioned text. For example, when it is determined that the conference participant at the site A has touched the image of the conference participant at the site B displayed on the display device 104, the communication device 101 at the site A selects the device that is the data output destination as the site. Only the C communication apparatus 101 is switched. As a result, it is possible to prevent data related to conversation contents that the conference participants at the base B do not want to know from being transmitted to the communication device 101 at the base B. Further, for example, the communication device 101 at the site A switches whether to output the data based on the acquired text-like utterance to an external device based on the determination result of the event occurrence. Specifically, when it is determined that the conference participant at the site A is facing a different direction from the display device 104, the communication device 101 at the site A determines that a conversation is being performed within the site. However, the data based on the acquired text-formed utterance is not output to another device. As a result, it is possible to reduce the use of the communication band for the transmission of data related to conversation contents that are not necessary for other sites.

  Next, the case where the communication apparatus 101 on the data receiving side switches the output will be described. When the conference participant makes a statement at the site A, the communication device 101 at the site A transmits data based on the textized statement to the communication devices 101 at the site B and the site C. The communication devices 101 of the base B and the base C acquire data transmitted from the communication device of the base A, and output image data including characters obtained by converting the speech into text to the display device 104. When the communication device 101 at the site A detects that a predetermined event has occurred, the communication device 101 at the site A transmits a notification indicating the occurrence of the predetermined event to the communication devices 101 at the site B and the site C.

  Then, the communication devices 101 of the base B and the base C determine that a predetermined event has occurred by receiving this notification, and display data based on the textized message acquired from the communication device 101 of the base A The output to 104 is switched. For example, the communication device 101 at the site B switches the output content of the data based on the acquired text-formed utterance based on the determination result of the event occurrence. Specifically, the communication device 101 at the base B displays the content of the speech before the occurrence of the event and the content of the speech after the occurrence of the event in different areas (for example, another window or another thread) on the display device 104 at the base B. As described above, the contents of the image data to be output are switched. Thereby, the user can easily identify the utterance before the event occurrence and the utterance after the event occurrence, and can easily understand the contents of the conference. Further, the communication apparatus 101 may switch the output contents according to the determination result of the event occurrence so that the utterance contents displayed in the different areas are collectively displayed in one area.

  Note that the communication device 101 at the site B may output data based on the uttered text to a storage device or the like. Then, the output contents to the storage device may be switched based on the determination result of the event occurrence. As a result, for example, the result of converting the utterance into text, such as the minutes, can be stored in the storage device so that it can be displayed in a format that is easy for the user to understand.

  Also, an output device that converts the output contents of data based on the text-formed comments as described above into text based on the results of the event occurrence determination result and outputs the comments of the meeting held in one base You may apply to. For example, the output device generates text data by converting the voice collected at the site into text, and outputs image data based on the text data to the display device 104 connected to the output device. When the output device determines that a predetermined event has occurred, the output device switches the content of the image data to be output. Even in such a configuration, as in the case of the above-described conference between a plurality of bases, the result of converting the speech into text can be displayed so as to be easily understood by the user.

  The present invention supplies a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and one or more processors in a computer of the system or apparatus read and execute the program This process can be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions. Further, the program may be provided by being recorded on a computer-readable recording medium.

10 Multipoint Conference System 100 Distribution Device 101 Communication Device 104 Display Device

Claims (15)

An acquisition means for acquiring data based on an utterance of a person that is textified for display;
A discriminating means for discriminating that a predetermined event corresponding to the action of the person who makes the texted speech occurs;
An information processing apparatus comprising: a switching unit that switches output of data based on the text-generated utterance acquired by the acquisition unit based on a determination result by the determination unit. Having a second acquisition means for acquiring a captured image;
The information processing apparatus according to claim 1, wherein the determination unit determines that the predetermined event has occurred by analyzing a captured image acquired by the second acquisition unit. Receiving means for receiving a notification indicating the occurrence of the predetermined event;
The information processing apparatus according to claim 1, wherein the determination unit determines that the predetermined event has occurred based on a notification received by the reception unit.   The switching means includes a character in which a utterance made before the determination means determines that the predetermined event has occurred, and a character after the determination means determines that the predetermined event has occurred. The output of data based on the textualized speech acquired by the acquiring unit is switched so that characters in which the performed speech is converted into text are displayed in an identifiable manner in the display unit. Item 4. The information processing apparatus according to any one of Items 1 to 3.   5. The switching unit according to claim 1, wherein the switching unit switches a session used for outputting data based on the text-like utterance acquired by the acquiring unit based on a determination result by the determining unit. The information processing apparatus according to claim 1.   The switching means switches whether or not the information processing apparatus outputs data based on the textified message acquired by the acquiring means to an external device based on a determination result by the determining means. The information processing apparatus according to any one of claims 1 to 3.   4. The switch according to claim 1, wherein the switching unit switches a data output destination device based on the text-like utterance acquired by the acquiring unit based on a determination result by the determining unit. 5. The information processing apparatus according to item 1.   5. The switching unit according to claim 1, wherein the switching unit switches the output content of the data based on the textized utterance acquired by the acquiring unit based on a determination result by the determining unit. The information processing apparatus described in 1.   9. The data based on the text-like utterance acquired by the acquiring unit includes audio data generated by collecting voice including the utterance. The information processing apparatus described in 1.   The data based on the textized speech acquired by the acquiring means includes character data generated by speech recognition processing with respect to audio data generated by collecting speech including the speech. The information processing apparatus according to any one of claims 1 to 9.   The predetermined event includes at least one of the person who makes the utterance to be turned into text in a predetermined direction and the person who makes the utterance made into text touches a predetermined area. The information processing apparatus according to any one of claims 1 to 10. A second receiving means for receiving audio data generated by collecting voice including speech to be converted into text from a plurality of communication devices;
The acquisition means acquires character data generated by text conversion based on audio data received by the second reception means as data based on the text to be converted into text,
4. The switching device according to claim 1, wherein the switching unit switches the output device of the character data acquired by the acquisition unit among the plurality of communication devices based on a determination result by the determination unit. 5. The information processing apparatus according to claim 1. An acquisition step of acquiring data based on a utterance of a person and uttered as text for display;
A determination step of determining that a predetermined event corresponding to the action of the person who makes the texted statement occurs;
An information processing method comprising: a switching step of switching output of data based on the text-like utterance acquired in the acquisition step based on a determination result in the determination step. A second acquisition step of acquiring a captured image;
14. The information processing method according to claim 13, wherein the determination step determines that the predetermined event has occurred by analyzing the captured image acquired in the second acquisition step.   A program for causing a computer to operate as the information processing apparatus according to any one of claims 1 to 12.

Images