Conference support device, conference support method, conference support system, and conference support program

Abstract

To provide a technique capable of more accurately grasping states of attendants of a conference in the conference.SOLUTION: A conference support device comprises: conference attendance state acquisition means for acquiring conference attendance states of attendants of a conference; speaking intention detection means for detecting an attendant intending to speak in the conference based upon the conference attendance states; no-speaking detection means for detecting a detected attendant who intends to speak not effectively speaking, as no speaking of the attendant based upon the conference attendance states; and output means for outputting information concerned with the no speaking that the no-speaking detection means detects, to an output destination.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an apparatus and the like for providing information regarding a meeting.

Background Art

[0002] Patent Document 1 describes a communication support system that analyzes the speech and attitudes of meeting participants using a camera and a microphone, quantifies or encodes meeting situations such as the amount of speech, speech intervals, and activity levels, and presents information for supporting meeting communication to the chairperson and participants.

[0003] Patent Document 2 describes a meeting support information output system that detects the state of meeting participants and outputs, as meeting support information, the characteristics of the participants and points of attention and countermeasures in the meeting to the chairperson.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the systems described in Patent Document 1 and Patent Document 2, for participants who intended to speak but could not speak, they may be determined to have a low amount of speech or low activity level, and there is a possibility that the meeting situation of the participants cannot be accurately grasped.

[0006] An example of the object of the present disclosure is to provide a technique capable of more accurately grasping the situation of participants in a meeting.

Means for Solving the Problems

[0007] A conference support apparatus according to an aspect of the present disclosure includes: a conference participation status acquisition unit that acquires the conference participation status of conference participants; a speech intention detection unit that detects, based on the conference participation status, that a participant has an intention to speak in the conference; an unspoken speech detection unit that detects, based on the conference participation status, that a participant's speech has been canceled in order to avoid voice collision due to the participant speaking with the microphone off or the participant's speech timing overlapping with that of another participant's speech, as unspoken speech in which the speech of the participant detected as having the intention to speak is not made effective; and an output unit that outputs information regarding the unspoken speech detected by the unspoken speech detection unit to an output destination.

[0008] A conference support method according to an aspect of the present disclosure includes: a computer acquiring the conference participation status of conference participants, detecting, based on the conference participation status, that a participant has an intention to speak in the conference, detecting, based on the conference participation status, that a participant's speech has been canceled in order to avoid voice collision due to the participant speaking with the microphone off or the participant's speech timing overlapping with that of another participant's speech, as unspoken speech in which the speech of the participant detected as having the intention to speak is not made effective, and outputting information regarding the detected unspoken speech to an output destination.

[0009] A conference support program according to an aspect of the present disclosure causes a computer to execute a process of acquiring the conference participation status of conference participants, detecting, based on the conference participation status, that a participant has an intention to speak in the conference, detecting, based on the conference participation status, that a participant's speech has been canceled in order to avoid voice collision due to the participant speaking with the microphone off or the participant's speech timing overlapping with that of another participant's speech, as unspoken speech in which the speech of the participant detected as having the intention to speak is not made effective, and outputting information regarding the detected unspoken speech to an output destination.

[0010] In one aspect of the present disclosure, a meeting support system includes: a meeting participation status acquisition means for acquiring the meeting participation status of meeting participants; a speech intention detection means for detecting that a participant has an intention to speak in the meeting based on the meeting participation status; an unspoken speech detection means for detecting, based on the meeting participation status, that a participant's speech has been cancelled for the purpose of avoiding voice collision due to the participant speaking with the microphone off or the timing of the participant's speech overlapping with that of another participant's speech, as an unspoken speech in which the speech of the participant detected as having an intention to speak is not validated; and an output means for outputting information regarding the unspoken speech detected by the unspoken speech detection means to an output destination.

Effect of the Invention

[0011] An example of the effect according to the present disclosure is that the situation of meeting participants can be grasped more accurately.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

[0013] Embodiments of the present disclosure will be described in detail with reference to the drawings.

[0014] [First Embodiment] FIG. 1 is a block diagram showing the configuration of the conference support apparatus 100 according to the first embodiment. Referring to FIG. 1, the conference support apparatus 100 includes a conference participation status acquisition unit 101, a speech intention detection unit 102, a non-speech detection unit 103, and an output unit 104.

[0015] In the description of the embodiment, a participant refers to a person who participates in a conference. Also, a moderator refers to a person among the participants who is in charge of conducting and running the conference. Further, the moderator may include a person who is the organizer or host of the conference.

[0016] Next, the configuration of the conference support apparatus 100 according to the first embodiment will be described in detail. The conference support apparatus 100 may be used in an online conference described later. Alternatively, the conference support apparatus 100 may be used in a conference actually held face-to-face.

[0017] In FIG. 1, the meeting participation status acquisition unit 101 acquires the meeting participation status of the participants who are participating in the meeting. The meeting participation status is information for knowing how the participants are participating in the meeting. The meeting participation status is, for example, image data obtained by a camera capturing the participants, or voice data of the participants obtained by a microphone. The image data is either still image data or moving image data. For example, the image is image data obtained by a camera capturing the face region of the participants. Alternatively, in an online meeting, the meeting participation status includes input information for participating in the meeting by the operation of the participants. For example, it may also include information on whether the state of the camera or the microphone is on or off. The on or off state of the microphone in an online meeting is also called unmute or mute. The meeting participation status in an online meeting may be transmitted from the terminals of the participants equipped with cameras and microphones and received by the meeting participation status acquisition unit 101. The microphone may be a sound collection microphone that collects the voices of a plurality of participants. The camera may be a camera that captures a plurality of participants.

[0018] Specifically, an online meeting is a meeting in which participants use a network without actually meeting face-to-face and exchange voice data and image data. The number of participants in an online meeting is two or more. An example of an online meeting using the meeting support device 100 will be described. The terminals of the participants in the online meeting use an application to acquire the voices and images of the participants, that is, voice data and image data, and transmit them to the meeting support device 100. An example of the meeting support device 100 is a server. The server, which is an example of the meeting support device 100, may be provided with a function for providing an online meeting (not shown). For example, the server transmits the voice data and image data received from the terminals of a plurality of participants participating in the meeting to the terminals of each participant. The server may also synthesize the received voice data of a plurality of participants and transmit it to the terminals of each participant. In this way, an online meeting is held. Then, the meeting participation status acquisition unit 101 of the server acquires the voice data and image data of the participants as the meeting participation status.

[0019] The speech intention detection unit 102 detects that a participant has the intention to speak based on the meeting participation status detected by the meeting participation status acquisition unit 101 in a meeting. More specifically, the speech intention detection unit 102 detects an action indicating the intention of a participant to speak in a meeting.

[0020] An action indicating the intention to speak is, for example, that the participant opens their mouth. The speech intention detection unit 102 detects that the participant has opened their mouth based on the meeting participation status. Specifically, the meeting participation status acquisition unit 101 detects that the participant has opened their mouth by analyzing an image of the participant captured by a camera. Furthermore, the speech intention detection unit 102 may perform image analysis on the captured image to be able to detect that the participant has opened their mouth in an attempt to speak, excluding physiological phenomena such as yawning or sneezing.

[0021] Alternatively, an action indicating the intention to speak may be a change in the participant's posture or raising of a hand. The speech intention detection unit 102 analyzes the image data acquired by the meeting participation status acquisition unit 101, that is, the image data of the participant captured by a camera. The speech intention detection unit 102 may detect that the participant is about to speak by detecting a change in posture or raising of a hand through the analysis of the image data.

[0022] Also, for example, an action indicating the intention to speak is that the participant speaks. The speech intention detection unit 102 may detect that the participant has spoken by, for example, inputting the sound collected by a microphone near the participant as the meeting participation status and detecting the voice input.

[0023] Also, for example, an action indicating the intention to speak is that in an online meeting, a participant turns on the microphone, that is, the participant unmutes. At this time, the speech intention detection unit 102 inputs information indicating the on, off, or unmute of the microphone from the meeting participation status acquisition unit 101, and detects the on state of the participant's microphone as having the intention to speak. Alternatively, the speech intention detection unit 102 may detect as an action indicating the intention to speak that information indicating that a speech button or a raise hand button is operated on the terminal and the participant presses a button for expressing the intention to speak to the moderator or other participants is input from the meeting participation status acquisition unit 101.

[0024] Also, the speech intention detection unit 102 may detect the intention to speak when an action indicating the intention to speak or the on state of the microphone, that is, the unmuted state, continues for a certain period of time. Thereby, the speech intention detection unit 102 can prevent accidentally detecting that a participant who has accidentally performed an action indicating the intention to speak or turned on the microphone or unmuted has the intention to speak.

[0025] The speech intention detection unit 102 outputs the result of detecting that a participant has the intention to speak to the non-speech detection unit 103. The detected result may include information indicating a participant who is detected as not having the intention to speak.

[0026] The non - speech detection unit 103 detects, based on the meeting participation status, that the speech of a participant who has been detected as having the intention to speak has not been made effective as the non - speech of the participant. The non - speech detection unit 103 determines, for example, whether the speech of a participant who has been detected as having the intention to speak has been made effective or not, based on the meeting participation status. Specifically, when the speech of a participant has been made effective, it means that in the meeting, the speech of the participant has been made in a state where other participants can hear it. Also, when the speech of a participant has not been made effective, it means, for example, that the voice was too low to be heard, or that the timing of the speech overlapped with the speech of other participants and the participant stopped speaking. Also, in an online meeting, when the speech of a participant has not been made effective, it means that the participant spoke with the microphone off, or that the timing of the speech overlapped with the speech of other participants and the online meeting system avoided voice collision and the speech was canceled. An effective speech is a speech that can be heard by other participants, the moderator, the host, etc. of the meeting. The following shows multiple examples of the non - speech detection unit 103, but the non - speech detection unit 103 is not limited to those examples.

[0027] The non - speech detection unit 103 detects, for example, an effective speech while identifying the speaker by analyzing the voice of the meeting. Or, in an online meeting, the non - speech detection unit 103 may identify the speaker by the ID (identification) of the speaker's terminal or the application of the terminal. Furthermore, the non - speech detection unit 103 determines whether the speech of a participant, for whom the intention to speak has been detected by the speech intention detection unit 102, is included in the effective speeches.

[0028] In an in-person meeting where participants actually face each other, the non-speaking detection unit 103 identifies the speaker by analyzing, for example, the audio input from a microphone installed in the meeting room. Then, the non-speaking detection unit 103 detects the utterances made by the identified speaker that are considered valid. And the non-speaking detection unit 103 determines whether the utterances made by the participants whose speaking intention has been detected by the speaking intention detection unit 102 are included in the valid utterances. Alternatively, in an online meeting, the non-speaking detection unit 103 identifies the speaker by analyzing the audio output for the entire meeting from the server and detects the valid utterances. And the non-speaking detection unit 103 determines whether the utterances made by the participants whose speaking intention has been detected are included in the valid utterances. Hereinafter, the audio input from the microphone installed in the meeting room in an in-person meeting and the audio output for the entire meeting in an online meeting are referred to as the audio for the entire meeting. The entire meeting refers to the participants in the meeting or the terminals of the participants.

[0029] Also, for example, the non-speaking detection unit 103 may compare the overall text obtained by converting the audio for the entire meeting into text with the participant texts obtained by converting the audio of each participant into text on the respective terminals of the participants, and determine that the utterances included in the participant texts are valid utterances if they are included in the overall text. Also, at this time, in the conversion of the audio into text, by adding information on the time when the audio was uttered, it is possible to prevent misjudging the same utterances at different times and more reliably compare the overall text with the participant texts. Here, the time may be the elapsed time since the start of the meeting.

[0030] The non-speaking detection unit 103 performs the above-described exemplary determination and detects as the non-speaking of the participant the fact that the participant has been determined not to have made a valid utterance despite having the intention to speak. More specifically, the non-speaking detection unit 103 detects the non-speaking of the participant when the participant detected by the speaking intention detection unit 102 as having the intention to speak has not been able to make a valid utterance. The non-speaking detection unit 103 may store in a storage unit (not shown) together with the detected time the information indicating the non-speaking participant.

[0031] In addition, the non-speaking detection unit 103 may calculate the number of non-speaking times for each participant. Also, the number of non-speaking times may be referred to as non-speaking points. The non-speaking detection unit 103 may calculate the number of non-speaking times and output it to the output unit 104 as will be described later. When calculating the number of non-speaking times, the non-speaking detection unit 103 may add the number of non-speaking times after a certain period of time has elapsed since the time when non-speaking was last detected for a certain participant. Thereby, the non-speaking detection unit 103 can prevent erroneously detecting that there has been one non-speaking event as two or more non-speaking events.

[0032] The operation when the non-speaking detection unit 103 calculates the number of non-speaking times will be described with reference to the flowchart of FIG. 3.

[0033] FIG. 3 is a flowchart showing an overview of the operation when the non-speaking detection unit 103 calculates the number of non-speaking times. Note that the processing according to this flowchart may be executed based on program control by a processor.

[0034] As shown in FIG. 3, first, the non-speaking detection unit 103 detects non-speaking of a participant (step S111).

[0035] Next, the non-speaking detection unit 103 acquires the number of non-speaking times and the previous detection time from a storage unit (not shown) for the participant for whom non-speaking was detected in step S111 (step S112).

[0036] Next, the non-speaking detection unit 103 determines whether the number of non-speaking times of the participant is 0 (step S113).

[0037] Next, when the result in step S113 is NO, that is, when the number of non-speaking times of the participant is not 0, the non-speaking detection unit 103 determines whether a certain period of time has elapsed since the previous detection time when non-speaking was detected (step S114). If the result in step S114 is NO, the non-speaking detection unit 103 ends the operation of calculating the number of non-speaking times.

[0038] And when the answer is YES in step S113 or YES in step S114, the non-speaking detection unit 103 increments the number of times the participant has not spoken by one (step S115).

[0039] Next, the non-speaking detection unit 103 records the number of non-speaking times added in step S115 and the non-speaking detection time in step S111 in a storage unit (not shown) (step S116). The final non-speaking detection time recorded in step 116 is the non-speaking detection time detected in step S111.

[0040] Thus, the non-speaking detection unit 103 ends the operation of calculating the number of non-speaking times. The process according to the flowchart shown in FIG. 3 is repeated each time a non-speaking is detected. The operations from step S111 to step S116 performed for each participant may be performed in parallel for each participant, or a series of operations may be repeated. The operation when the non-speaking detection unit 103 calculates the number of non-speaking times is not limited to the above operations.

[0041] Referring again to FIG. 1, the description of the conference support device 100 of the first embodiment will be continued.

[0042] The output unit 104 outputs information regarding the non-speaking detected by the non-speaking detection unit 103 to the output destination. Specifically, the output unit 104 outputs the information regarding the non-speaking for at least one participant for notification. The timing at which the output unit 104 outputs is not limited. For example, the output unit 104 may output that there is no non-speaking from the start of the conference and perform output for updating the information each time a non-speaking is detected.

[0043] The output destination of the output unit 104 is the moderator or the terminal used by the moderator. Further, it may be displayed on a display device visible to the moderator. Also, the output destination of the output unit 104 may be the participant or the terminal used by the participant.

[0044] The information regarding non - speaking is information about whether each participant has not spoken. The information regarding non - speaking is, for example, the name of the participant who has not spoken or the identification information of the participant. The information regarding non - speaking may include the time when there was non - speaking. The information regarding non - speaking may also be information based on the non - speaking detected by the non - speaking detection unit 103 for each of the plurality of participants. By providing the information regarding non - speaking to the emcee by the output unit 104, the emcee can prompt the participant who has not spoken to speak. Thereby, the conference support device 100 can support the emcee in smoothly advancing the conference. The output unit 104 may execute a process for, for example, displaying or notifying by voice such as "Participant A has not spoken." Alternatively, when the non - speaking of Participant A is detected, the output unit 104 may notify such as "Please call on Participant A."

[0045] Also, for example, the output unit 104 may output information regarding a participant whose number of non - speaking times is more than a threshold value. In this case, the non - speaking detection unit 103 uses the number of non - speaking times calculated as shown in FIG. 3 to detect a participant whose number of non - speaking times is more than the threshold value. Further, the output unit 104 may use the number of non - speaking times calculated as shown in FIG. 3 by the non - speaking detection unit 103 to detect a participant whose number of non - speaking times is more than the number of non - speaking times of other participants, and output information regarding that participant. By performing such output, the emcee or the host can efficiently recognize a participant who wanted to speak but was unable to do so many times.

[0046] Further, the output unit 104 may output information regarding non - speech as data indicating the number of non - speech times for each participant. Alternatively, the output unit 104 may output, as information indicating participants who should be prompted to speak, the participants who had non - speech or the participants whose number of non - speech times was greater than a threshold value, to the terminal of the moderator. Also, for example, when there is silence during the meeting, the output unit 104 may output a comment or the like to prompt speech to the participants for whom non - speech has been detected by the non - speech detection unit 103. The output unit 104 performs these outputs to the terminals of the participants or the moderator, for example, by voice or display. Alternatively, the output unit 104 may display on a display (not shown).

[0047] So far, the output during the meeting of the output unit 104 has been described. Furthermore, the output unit 104 may output information regarding the non - speech of the participants after the meeting. For example, the output unit 104 may show the tendency of the participants' speech during the meeting by outputting the number of non - speech times for each participant during the meeting. Thereby, the moderator or the host can utilize the information regarding non - speech in subsequent meetings.

[0048] The operation of the conference support apparatus 100 configured as described above will be described with reference to the flowchart of FIG. 2.

[0049] FIG. 2 is a flowchart showing an overview of the operation of the conference support apparatus 100 in the first embodiment. Note that the processing according to this flowchart may be executed based on program control by a processor.

[0050] As shown in FIG. 2, first, the conference participation status acquisition unit 101 acquires the conference participation status of each participant (step S101).

[0051] Next, the speech intention detection unit 102 detects that a participant has an intention to speak based on the conference participation status (step S102).

[0052] Next, the non-speaking detection unit 103 detects that the speech of the participant who has been detected as having the intention to speak has not been made effective as the non-speaking of the participant (step S103).

[0053] Then, the output unit 104 outputs the information regarding the detected non-speaking to the output destination (step S104).

[0054] With the above, the conference support device 100 ends a series of operations. The operations from step S101 to step S103 performed for each participant may be performed in parallel for each participant, or a series of operations may be repeated.

[0055] In the conference support device according to the above-described embodiment, based on the conference participation status acquired by the conference participation status acquisition unit, the speech intention detection unit detects that a participant has the intention to speak. Then, the non-speaking detection unit determines, based on the conference participation status, whether or not the speech of the participant who has been detected as having the intention to speak has been made effective, and detects that the participant has not made an effective speech despite having the intention to speak as the non-speaking of the participant. Then, the output unit outputs the information regarding the non-speaking.

[0056] As a result, the conference support device according to the present embodiment can more accurately grasp the status of the participants in the conference. For example, by providing the information regarding the non-speaking to the moderator or the host, the moderator or the host can prompt the participant who has not spoken to speak. [Second Embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the description of the content overlapping with the above description will be omitted as long as the description of the present embodiment is not made unclear.

[0057] FIG. 4 is a block diagram showing the configuration of a conference support system according to a second embodiment of the present disclosure. The conference support apparatus 200 included in the conference support system 2000 of the second embodiment includes a speech intention detection unit 202 instead of the speech intention detection unit 102 in the configuration of the first embodiment, and an unspoken detection unit 203 instead of the unspoken detection unit 103. In addition to the conference support apparatus 200, the conference support system 2000 includes a participant terminal 210, a participant terminal 220, a participant terminal 230, and a moderator terminal 240. The speech intention detection unit 202 and the unspoken detection unit 203 include the same functions as the speech intention detection unit 102 and the unspoken detection unit 203 in the first embodiment, and will be described more specifically in the second embodiment.

[0058] In this embodiment, the conference is an online conference. The number of participant terminals and moderator terminals connected to the conference support apparatus 200 through the network is not limited to the example in FIG. 4.

[0059] The participant terminals 210, 220, and 230 are terminals used by conference participants. More specifically, conference participants use the terminal to access an application or a website to participate in the online conference. Also, the moderator terminal 240 may be the same as the participant terminals 210, 220, and 230. For example, on the online conference system, the moderator terminal 240 may be set as a certain participant terminal by the host or other participants. Alternatively, the moderator terminal 240 may not be distinguished from the participant terminal. In this case, the output of information regarding unspoken speech may be performed on all participant terminals, or may be output on a website or an application accessible to the moderator. Also, for example, the moderator terminal 240 may have functions such as controlling the on / off of the microphones and cameras of the participant terminals 210, 220, and 230. The moderator using the moderator terminal 240 may include the conference organizer, etc., and may also be called the host.

[0060] First, the speaking intention detection unit 202 detects whether or not a participant has an intention to speak based on the participant's conference participation status. The speaking intention detection unit 202 detects the intention to speak as follows. For example, the speaking intention detection unit 202 may detect, based on image data, an action such as a participant opening his / her mouth or a participant changing his / her posture to move closer to the microphone. Alternatively, the speaking intention detection unit 202 may detect that a participant has performed an operation to turn on the microphone, i.e., an operation to unmute, or an operation to press a speak button or the like indicating an intention to speak. The speaking intention detection unit 202 may also detect that such an action or operation has continued for a certain period of time or more as the intention of the participant to speak.

[0061] When detecting that a participant has the intention to speak, the speech intention detection unit 202 judges whether the participant has started speaking. The speech intention detection unit 202 may judge whether the participant has started speaking within a predetermined time after detecting the intention to speak. Here, when a participant detected as having the intention to speak starts speaking, the speech intention detection unit 202 may output predetermined information to the not-yet-spoken detection unit 203. The predetermined information is, for example, information indicating that a participant detected as having the intention to speak has started speaking, or an instruction to judge whether a participant detected as having the intention to speak has made a valid statement.

[0062] In response to the output of the speech intention detection unit 202, the not-yet-uttered detection unit 203 determines that the participant detected as having the intention to speak has not made a valid speech, and detects the participant's not-yet-uttered. In addition, when a participant detected as having the intention to speak starts to speak, the speech intention detection unit 202 outputs, for example, an instruction to the not-yet-uttered detection unit 203 to determine whether the participant detected as having the intention to speak has made a valid speech.

[0063] The non-speaking detection unit 203 determines whether the speech of a participant who has been detected by the speech intention detection unit 202 as having the intention to speak and has been determined to have started speaking is made valid. The determination as to whether the speech is made valid may be performed in the same manner as the non-speaking detection unit 103 of the first embodiment.

[0064] The operation of the conference support apparatus 200 configured as described above will be described with reference to the flowchart of FIG. 5.

[0065] FIG. 5 is a flowchart showing an example of the non-speaking detection operation of the conference support apparatus 200 in the second embodiment. The processing according to this flowchart may be executed based on program control by a processor.

[0066] As shown in FIG. 5, first, the conference participation status acquisition unit 101 acquires the conference participation status of each participant from the participant terminals 210, 220, and 230 (step S201).

[0067] Next, the speech intention detection unit 202 detects whether each participant has the intention to speak based on the conference participation status of each participant (step S202). Specifically, the speech intention detection unit 202 may detect the intention to speak based on the participant opening their mouth, turning on the microphone, or facing forward, as described in the first embodiment.

[0068] If the result in step S202 is YES, that is, if it is detected that a certain participant has the intention to speak, the speech intention detection unit 202 determines, based on the conference participation status, whether the participant who has been detected as having the intention to speak has started speaking (step S203). At this time, starting to speak may be determined by the participant's microphone receiving voice input, the participant moving their mouth, or the like. If the result in step S202 is NO, the processing of the non-speaking detection operation ends.

[0069] If the answer in step S203 is YES, the non-speaking detection unit 103 determines whether the speech of the participant, whose intention to speak has been detected, is included in the overall voice of the meeting (step S204).

[0070] If the answer in step S203 is NO, and if the answer in step S204 is NO, the non-speaking detection unit 103 detects the non-speaking of the participant (step S205).

[0071] With the above, the conference support device 200 ends the operation of non-speaking detection.

[0072] In the conference support device according to the above-described embodiment, in an online conference, based on the conference participation status acquired by the conference participation status acquisition unit, the speech intention detection unit detects that a participant has an intention to speak. Then, the non-speaking detection unit determines, based on the conference participation status, whether the speech of the participant, whose intention to speak has been detected, has been made effective, and detects that the participant has not made an effective speech despite having an intention to speak as the non-speaking of the participant. Then, the output unit outputs information regarding the non-speaking.

[0073] As a result, the conference support device according to the present embodiment can more accurately grasp the status of participants in an online conference. [Third Embodiment] Next, the third embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the description of the content overlapping with the above description will be omitted as long as the description of the present embodiment is not made unclear.

[0074] In the present embodiment, in an online conference, the detection of the intention to speak, whether a speech has been made effective in the conference, and the detection of non-speaking are performed on each participant's terminal. Similar to the second embodiment, the number of participant terminals and the moderator terminal connected to the conference support device 300 through the network is not limited to the example of FIG. 6.

[0075] FIG. 6 is a block diagram showing the configuration of a conference support system according to a third embodiment of the present disclosure. The conference support apparatus 300 included in the conference support system 3000 of the third embodiment includes an information acquisition unit 301, an information merge unit 302, and an output unit 303. The participant terminal 310 also includes a conference participation status acquisition unit 311, a speech intention detection unit 312, a non-speech detection unit 313, and an output unit 314. The participant terminals 320, 330, and the moderator terminal 340 included in the conference support system 3000 have the same configuration as the participant terminal 310.

[0076] First, the participant terminal 310 included in the conference support system 3000 will be described.

[0077] The conference participation status acquisition unit 311 detects the conference participation status of the participant using the participant terminal 310. The conference participation status acquisition unit 311 acquires voice data and image data as the conference participation status of the participant. For example, the conference participation status acquisition unit 311 acquires the conference participation status from a camera or a microphone provided or connected to the participant terminal 310. Further, the conference participation status acquisition unit 311 may detect the on or off state of the participant's microphone. Also, the conference participation status acquisition unit 311 may acquire the voice of the entire conference from the conference support apparatus 300 as the conference participation status.

[0078] The speech intention detection unit 312 and the non-speech detection unit 313 have the same functions as the speech intention detection unit 102 and the non-speech detection unit 103 of the first embodiment or the second embodiment, respectively.

[0079] The non-speech detection unit 313 determines whether or not the participant's speech has been effectively made based on the voice of the entire conference acquired from the conference support apparatus 300 or the text obtained by textifying the voice of the entire conference.

[0080] The output unit 314 transmits information regarding non - speech to the conference support device 300. The information regarding non - speech includes the fact that there was non - speech or the number of non - speech occurrences, and information identifying the participant using the participant terminal 310 or the participant terminal 310. Further, the information regarding non - speech may include information on the time when there was non - speech.

[0081] Regarding the operation of the participant terminal 310 configured as described above, it will be described with reference to the flowchart of FIG. 7.

[0082] FIG. 7 is a flowchart showing an example of the non - speech detection operation of the participant terminal 310 in the third embodiment. Note that the processing according to this flowchart may be executed based on program control by a processor.

[0083] As shown in FIG. 7, first, the conference participation status acquisition unit 311 detects the conference participation status of the participant using the participant terminal 310 (step S301).

[0084] Next, the speech intention detection unit 312 detects whether the participant has an intention to speak based on the conference participation status of the participant (step S302). At this time, the fact that there is an intention to speak may be detected by the participant opening their mouth, turning on the microphone, or facing forward in terms of posture, etc.

[0085] If the result in step S302 is YES, that is, if it is detected that the participant using the participant terminal 310 has an intention to speak, the speech intention detection unit 312 determines whether the participant who was detected to have an intention to speak has started speaking based on the conference participation status (step S303). At this time, the fact that the participant has started speaking may be determined by the participant's microphone receiving voice input, the participant moving their mouth, etc.

[0086] If the result in step S303 is YES, the non - speech detection unit 313 determines whether the speech of the participant who was detected to have an intention to speak is included in the overall conference voice (step S304).

[0087] If the answer in step S303 is NO, and if the answer in step S304 is NO, the non-speaking detection unit 313 detects that the participant is not speaking (step S305).

[0088] With the above, the participant terminal 310 ends the non-speaking detection operation.

[0089] Next, referring to FIG. 6 again, the conference support device 300 included in the conference support system 3000 will be described.

[0090] The information acquisition unit 301 acquires information from terminals participating in the conference, such as the participant terminals 310, 320, 330, and the moderator terminal 340. The information acquired by the information acquisition unit 301 is information such as video and audio output by the participant terminals in an online conference. Also, information regarding the non-speaking of the participant is acquired from the output unit 315 etc. of the participant terminal 310.

[0091] The information merge unit 302 merges the information acquired by the information acquisition unit 301. For example, the information merge unit 302 synthesizes the video and audio acquired from the terminals participating in the conference. Also, the information merge unit 302 may merge the information regarding non-speaking acquired from each of the participant terminals, summarize it into one table, and store it in a storage unit (not shown). Further, the information merge unit 302 may merge the information regarding non-speaking in the form of a table as in the example of FIG. 10 so as to output to the moderator terminal 340 the participants who have the intention to speak but cannot speak.

[0092] The output unit 303 outputs information regarding non-speaking, similarly to the output unit 104.

[0093] Regarding the operation of the conference support device 300 configured as above, it will be described with reference to the flowchart of FIG. 8.

[0094] FIG. 8 is a flowchart showing an example of the operation of the conference support device 300 in the third embodiment. Note that the processing according to this flowchart may be executed based on program control by a processor.

[0095] First, the information acquisition unit 301 acquires information such as information regarding the non - speech of participants from each terminal (step S311).

[0096] Next, the information merge unit 302 merges the information regarding non - speech acquired in step S311 (step S312).

[0097] Next, the output unit 303 outputs information regarding non - speech based on the merged information (step S313).

[0098] Thus, the conference support apparatus 300 ends its operation.

[0099] In the participant terminal included in the conference support system according to the above - described embodiment, based on the conference participation status detected by the conference participation status acquisition unit, the speech intention detection unit detects that a participant has an intention to speak. Then, the non - speech detection unit determines, based on the conference participation status, whether the speech of the participant detected as having an intention to speak has been made effectively, and detects that the participant has not made an effective speech despite having an intention to speak as the non - speech of the participant. Then, the output unit outputs information regarding non - speech to the conference support apparatus. Also, the information processing apparatus included in the conference support system according to the present embodiment acquires and merges information regarding non - speech of participants from each terminal, and outputs information regarding non - speech.

[0100] As a result, in the online conference, the participant terminal according to the present embodiment can grasp the status of participants more accurately. [Fourth Embodiment] Next, the fourth embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the description of the content overlapping with the above - mentioned description will be omitted as long as the description of the present embodiment is not made unclear.

[0101] FIG. 9 is a block diagram showing the configuration of the conference support device 400 in the fourth embodiment of the present disclosure. The conference support device 400 includes a speech rate calculation unit 405 in addition to the configuration of the first embodiment. Note that the speech rate calculation unit 405 may be additionally provided in the conference support devices of other embodiments, or may be provided in the participant terminal or the host terminal.

[0102] The speech rate calculation unit 405 calculates a speech rate, which is the degree of the amount of speech of each participant during the conference, based on the voice of the entire conference. The amount of speech is the amount of speech of the participant during the conference time. The speech rate may be calculated based on the speech time of the participant during the conference time. Alternatively, the speech rate may be calculated based on the number of characters or words of the text of the part where the participant spoke in the entire text obtained by converting the voice of the entire conference into text. Or, the speech rate calculation unit may calculate the amount of speech. Alternatively, the speech rate calculation unit 405 may calculate, as a silence rate, the degree to which each participant did not speak during the conference.

[0103] The output unit 104 may output information regarding the speech rate calculated by the speech rate calculation unit 405. At this time, the speech rate calculation unit 405 may output information on participants with a low speech rate and for whom non-speaking has been detected.

[0104] FIG. 10 is an example of an output screen of information regarding non-speaking, which is displayed on the display unit by the output unit 104. The display unit may be provided in the output unit 104, or may be the display of the participant's terminal. The output screen outputs, for example, the number of non-speaking times and the speech rate (%) for each participant from the start of the conference to the present. In FIG. 10, the participants are numbered. The data indicating the participants may be any data that can identify the participants. Also, in the example of FIG. 10, the data regarding the non-speaking of the participants is arranged in descending order of the number of non-speaking times. Further, as in the example of FIG. 10, the output unit 104 may display, in a different color, participants who are considered to have a high degree of inability to speak despite having the intention to speak, such as participants with a low speech rate and those who have not spoken. Also, in the example of FIG. 10, the number of non-speaking times and the speech rate of the host are not displayed, but the number of non-speaking times and the speech rate of the host may be displayed.

[0105] As a result, the conference support device 400 according to the fourth embodiment can easily recognize participants who have the intention to speak but have a high degree of inability to speak during the conference, and a moderator or the like can encourage them to speak. That is, the situation of the participants in the conference can be grasped more accurately. [Fifth Embodiment] Next, the fifth embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the description of the content overlapping with the above description will be omitted as long as the description of this embodiment is not made unclear.

[0106] FIG. 11 is a block diagram showing the configuration of a conference support device 500 according to the fifth embodiment of the present disclosure. The conference support device 500 includes a section switching unit 506 in addition to the configuration of the first embodiment. Note that the section switching unit 506 may be additionally provided in the conference support devices of other embodiments, or may be provided in the moderator terminal.

[0107] When there are a plurality of topics in a conference, the section switching unit 506 sets the time zone during which the same topic is being discussed as one section, and switches the section when the topic changes. For example, when the section is switched, the conference support device 500 resets to zero and calculates from scratch the presence or absence of non-speaking, the number of non-speaking times, or the speaking rate for each participant in the conference. Also, when the section is switched, the presence or absence of non-speaking, the number of non-speaking times, or the speaking rate for each participant during the section before the switch may be recorded in a storage unit that does not display them.

[0108] The switching of sections is performed, for example, by inputting section switching information. The section switching unit 506 is input with at least the end time of the section as the section switching information. The section switching unit 506 may switch the section, for example, based on an input by the emcee. The input by the emcee is, for example, pressing a section switching button from the conference support device 500 or the terminal of the emcee connected to the conference support device 500. The time when the section switching button is pressed is input to the section switching unit 506 as the end time of the section that was in progress. Alternatively, the section switching unit 506 may use a machine learning model that has learned conversations and conferences, recognize that the topic has changed with the input of the conference audio, and generate section switching information.

[0109] Also, the information included in the section switching information may include the start time of the next section. Thereby, the section switching unit 506 can handle the case where there is a break time at the time of section switching, for example, where the end time of the section before switching is different from the start time of the next section. Further, the section switching information may include the section name before or after switching.

[0110] FIG. 12 is an example of an output screen of information regarding non - speaking in a conference where section switching is performed. In this example, section 1 has ended and section 2 is in progress. For the ended section 1, the highlighting of participants with a large number of non - speaking times is not performed. Also, by displaying the in - progress section 2 above in this way, the emcee who outputs can easily recognize the participants with a large number of non - speaking times in the current section.

[0111] The section switching operation of the conference support device 500 configured as described above will be described with reference to the flowchart of FIG. 13.

[0112] FIG. 13 is a flowchart showing an example of a section switching operation of the conference support apparatus 500 in the third embodiment. Note that the processing according to this flowchart may be executed based on program control by a processor.

[0113] First, the section switching unit 506 receives section switching information (step S501).

[0114] Next, the section switching unit 506 obtains the end time of the section before switching from the section switching information (step S502).

[0115] Next, the section switching unit 506 associates the name of the section before switching, the section end time, and information regarding unspoken words during the section, and records them in a storage unit (not shown) (step S503). The information regarding unspoken words to be recorded may include the number of unspoken words and the speaking rate.

[0116] Next, the section switching unit 506 obtains the start time of the section after switching (step S504). The section switching unit 506 may obtain the name of the section after switching.

[0117] Next, the section switching unit 506 resets the information regarding unspoken words at the start time of the section after switching (step S505). The information to be reset includes the presence or absence of unspoken words, the number of unspoken words, the speaking rate, and the like.

[0118] Thus, the conference support apparatus 500 ends the section switching operation.

[0119] By including the section switching unit 506 as described above, the conference support apparatus 500 according to the fifth embodiment outputs information regarding unspoken words for each topic. As a result, it is possible to more accurately grasp the situation of the participants in the conference in response to changes in the content and frequency of what the participants want to say. [Modification Example 1] Modification Example 1 will explain the operation of the meeting support device in an actual face-to-face meeting to detect the non-speaking of participants. The configuration of the meeting support device is the same as that in the example of FIG. 1.

[0120] The meeting participation status acquisition unit 101 acquires the meeting participation status from one or more cameras or microphones provided in the space where the meeting is held.

[0121] The speech intention detection unit 102 and the non-speaking detection unit 103 have the same functions as in the first embodiment. In an actual face-to-face meeting, since the participants cannot be identified by the information of the terminals connected to the online meeting, it is necessary to identify the participants from the video and audio acquired as the meeting participation status. For the identification of participants, if it is video, it may be performed by the position of the seat where the participant is sitting, face authentication, etc. Also, by specifying the speaking participants from the movements of the people included in the video, the participants who made the speech included in the audio may be specified. Also, the participants may be identified based on the voice. The speech intention detection unit 102 and the non-speaking detection unit 103 identify the participants and perform speech intention detection, determination of whether the speech is made effectively, and detection of non-speaking for each participant.

[0122] Also, the output unit 104 also outputs information regarding non-speaking, as in the first embodiment.

[0123] In the meeting support device in the above-described embodiment, in a meeting where the participants actually face each other, based on the meeting participation status acquired by the meeting participation status acquisition unit, the speech intention detection unit detects that each participant has the intention to speak. Then, the non-speaking detection unit determines, based on the meeting participation status, whether the speech of the participant who has been detected as having the intention to speak has been made effectively, and detects that the participant has not made an effective speech despite having the intention to speak as the non-speaking of the participant. Then, the output unit outputs information regarding non-speaking.

[0124] As a result, the conference support device in the present embodiment can more accurately grasp the status of participants in an actual face-to-face conference. [Modification Example 2] The conference support device and participant terminals in each embodiment may, for example, calculate and output the non-speaking rate. The non-speaking rate may be calculated, for example, as the number of non-speaking times relative to the number of speaking times. For example, by outputting the non-speaking rate for each participant to the emcee, the emcee can know the conference participation tendency of the participants. Also, by outputting information including the non-speaking rate during the conference after the conference ends, it is possible to support the smooth progress of subsequent conferences.

[0125] [Hardware Configuration] Each component in each embodiment of the present disclosure described above is represented by a functional block, and like the computer device shown in FIG. 14, its function can be realized not only in hardware but also by a computer device or firmware based on program control.

[0126] FIG. 14 is a diagram showing an example of a hardware configuration in which the conference support device, participant terminal, or emcee terminal in each embodiment of the present disclosure is realized by a computer device 10 including a processor. As shown in FIG. 14, the computer device 10 includes a CPU (Central Processing Unit) 11, a memory 12, a storage device 13 such as a hard disk for storing programs, an input / output I / F (Interface) 14 for connecting an input device and an output device, and a communication I / F (Interface) 15 for network connection.

[0127] The CPU 11 operates an operating system to control the entire management server of the present disclosure. Also, the CPU 11 reads programs and data from a storage medium mounted on, for example, a drive device into the memory 12. Further, the CPU 11 functions, for example, as a part of the speech intention detection unit 102, 202 or the speech intention detection unit 312, the non-speaking detection unit 103, 203, or a part of the non-speaking detection unit 313, and executes processes or instructions based on programs.

[0128] The storage device 13 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory, etc. A part of the storage medium of the storage device is a non-volatile storage device, and a program is recorded therein. Also, the program may be downloaded from an external computer (not shown) connected to the communication network.

[0129] The input device connected to the input / output I / F (Interface) 14 is realized by, for example, a mouse, a keyboard, a built-in key button, etc., and is used for input operations. The input device is not limited to a mouse, a keyboard, or a built-in key button.

[0130] Similarly, the output device connected to the input / output I / F (Interface) 14 is realized by, for example, a display or a speaker, and is used to confirm the output. The output device functions as a part of the output unit.

[0131] The communication I / F (Interface) 15 performs wired communication or wireless communication with other devices. For example, it communicates with a conference support device, a participant terminal, a host terminal, etc. The communication I / F 15 functions as a part of the output units 104, 305, or a part of the output unit 314.

[0132] As described above, the conference support device, the participant terminal, and the host terminal of each embodiment and each modification example of the present disclosure are realized by the computer hardware shown in FIG. 14. However, the realization means and the hardware configuration of each part are not limited to the configurations described above. Also, the conference support device, the participant terminal, and the host terminal may be realized by a single physically combined device, or may be realized by two or more physically separated devices connected by wire or wirelessly. For example, the input device and the output device may be connected to the computer device 10 via a network.

[0133] Although the present invention has been described with reference to each embodiment above, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0134] For example, the speech intention detection unit and the non-speech detection unit may be configured to be divided between the conference support device and the participant terminal or the moderator terminal.

[0135] Also, although a plurality of operations are described in order in the form of a flowchart, the order of the description does not limit the order in which the plurality of operations are executed. Therefore, when implementing each embodiment, the order of the plurality of operations can be changed as long as there is no problem in terms of content.

[0136] Some or all of the above embodiments may be described as follows in the appended claims, but are not limited thereto.

[0137] (Appended Claim 1) Conference participation status acquisition means for acquiring the conference participation status of conference participants, Speech intention detection means for detecting that a participant has an intention to speak in the conference based on the conference participation status, Based on the conference participation status, it is determined whether the speech of the participant detected as having an intention to speak is made effective, and it is detected as non-speech that the participant is determined not to have made an effective speech despite having an intention to speak. Non-speech detection means, Output means for outputting information regarding the non-speech detected by the non-speech detection means to an output destination, A conference support device comprising:

[0138] (Appended Claim 2) The non-speech detection means calculates the number of times of non-speech for each participant The conference support device according to Appended Claim 1, characterized in that:

[0139] (Appended Claim 3) The output means outputs information regarding a participant with a large number of non-speech times The conference support device according to appendix 2, characterized by

[0140] (Appendix 4) Further comprising section switching means for switching the sections of the conference, wherein the non - speaking detection means detects the non - speaking of the participants for each of the sections The conference support device according to any one of appendices 1 to 3, characterized by

[0141] (Appendix 5) Further comprising speech rate calculation means for further calculating a speech rate which is the degree of the amount of speech of a participant during the conference, wherein the output means further outputs information regarding the speech rate The conference support device according to any one of appendices 1 to 4, characterized by

[0142] (Appendix 6) wherein the output means outputs information regarding a participant whose speech rate is low and for whom non - speaking has been detected The conference support device according to appendix 5, characterized by

[0143] (Appendix 7) wherein the conference is an online conference The conference support device according to any one of appendices 1 to 6, characterized by

[0144] (Appendix 8) wherein the conference participation status includes at least the on or off state of the microphone of the participant, and when the speech intention detection means detects the on state of the microphone and after a certain period of time has elapsed, and the non - speaking detection means does not determine that the speech of the participant has become effective, the non - speaking detection means detects the non - speaking of the participant The conference support device according to appendix 7, characterized by

[0145] (Appendix 9) The speech intention detection means detects that a participant has spoken, and further, when the non-speech detection means does not determine that the speech of the participant has been made effectively, the non-speech detection means detects the non-speech of the participant The conference support device according to appended note 7 or 8, characterized by the above.

[0146] (Appended note 10) Obtain the conference participation status of the participants in the conference, Based on the conference participation status, detect that there is an intention to speak of the participant in the conference, Based on the conference participation status, determine whether the speech of the participant detected as having an intention to speak has been made effectively, and detect that the participant has not been able to speak effectively despite having an intention to speak as non-speech of the participant, Output the information regarding the detected non-speech to the output destination Conference support method.

[0147] (Appended note 11) A conference participation status acquisition process for acquiring the conference participation status of the participants in the conference, A speech intention detection process for detecting that there is an intention to speak of the participant in the conference based on the conference participation status, Based on the conference participation status, determine whether the speech of the participant detected as having an intention to speak has been made effectively, and detect that the participant has not been able to speak effectively despite having an intention to speak as non-speech of the participant in the non-speech detection process, An output process for outputting the information regarding the non-speech detected in the non-speech detection process to the output destination, A conference support program for causing a computer to execute the above.

[0148] (Appended note 12) A conference participation status acquisition process for acquiring the conference participation status of the participants in the conference, A speech intention detection process for detecting that there is an intention to speak of the participant in the conference based on the conference participation status, Based on the meeting participation status, determine whether the speech of a participant who has been detected as having the intention to speak has been made valid, and detect as the non - speech of the participant that it has been determined that the participant could not speak validly despite having the intention to speak. The non - speech detection process, An output process for outputting information regarding the non - speech detected in the non - speech detection process to a server, A meeting support program that causes a computer to execute.

[0149] (Appendix 13) A meeting participation status acquisition means for acquiring the meeting participation status of meeting participants, Based on the meeting participation status, a speech intention detection means for detecting that a participant has the intention to speak in the meeting, Based on the meeting participation status, determine whether the speech of a participant who has been detected as having the intention to speak has been made valid, and detect as the non - speech of the participant that it has been determined that the participant could not speak validly despite having the intention to speak. The non - speech detection means, An output means for outputting information regarding the non - speech detected by the non - speech detection means to an output destination, A meeting support system comprising the above.

Explanation of symbols

[0150] 10 Computer device 11 CPU 12 Memory 13 Storage device 14 Input / output I / F 15 Communication I / F 100, 200, 300, 400 Meeting support devices 101 Meeting participation status acquisition section 102 Speech intention detection section 103, 313 Non - speech detection section 104, 304, 314 Output section 205 Speech rate calculation section 210, 220, 230, 310, 320, 330 Participant terminals 301 Information acquisition section 302 Information merge section 311 Meeting Participation Status Acquisition Unit 406 Section Switching Unit 2000, 3000 Conference Support System

Claims

1. A meeting participation status acquisition means for acquiring the meeting participation status of meeting participants; A speech intention detection means for detecting that a participant has an intention to speak in the meeting based on the meeting participation status; A non-speech detection means for detecting, based on the meeting participation status, that a participant has spoken with the microphone off as a non-speech where the speech of the participant detected as having an intention to speak has not been made effective; An output means for outputting information regarding the presence or absence of the non-speech of each participant detected by the non-speech detection means to a terminal device used by the moderator of the meeting; A meeting support device comprising the above.

2. The meeting is an online meeting The meeting support device according to Claim 1.

3. The speech intention detection means detects that the participant has spoken in the online meeting as the participant having an intention to speak The meeting support device according to Claim 2.

4. The speech intention detection means detects that the participant has unmuted in the online meeting as the participant having an intention to speak The meeting support device according to Claim 2 or 3.

5. The speech intention detection means detects that the state in which the participant has unmuted in the online meeting has continued for a certain period of time as the participant having an intention to speak The meeting support device according to Claim 4.

6. The non-speech detection means further detects, based on the meeting participation status, that the voice of the participant was too low to be heard as the non-speech The meeting support device according to any one of Claims 1 to 5.

7. The non-speech detection means further detects, based on the meeting participation status, that the speech of the participant overlapped in timing with the speech of other participants and the participant stopped speaking as the non-speech The meeting support device according to any one of Claims 1 to 6.

8. Comprising a meeting support device, a participant terminal, and a moderator terminal, A meeting participation status acquisition means for acquiring the meeting participation status of meeting participants; A speech intention detection means for detecting that a participant has an intention to speak in the meeting based on the meeting participation status; A non-speech detection means for detecting, based on the meeting participation status, that a participant has spoken with the microphone off as a non-speech where the speech of the participant detected as having an intention to speak has not been made effective; Output means for outputting information regarding the presence or absence of non-speaking of each participant detected by the non-speaking detection means to the moderator terminal used by the moderator of the meeting; A meeting support system provided in at least one of the meeting support device, the participant terminal, and the moderator terminal. **Claim 9** A computer acquires the meeting participation status of the participants in the meeting, detects that there is an intention to speak by the participants in the meeting based on the meeting participation status, detects, based on the meeting participation status, that the participant has spoken with the microphone off as non-speaking in which the speech of the participant detected as having an intention to speak has not been made effective, outputs information regarding the presence or absence of non-speaking of each detected participant to the terminal device used by the moderator of the meeting, A meeting support method. **Claim 10** acquires the meeting participation status of the participants in the meeting, detects that there is an intention to speak by the participants in the meeting based on the meeting participation status, detects, based on the meeting participation status, that the participant has spoken with the microphone off as non-speaking in which the speech of the participant detected as having an intention to speak has not been made effective, outputs information regarding the presence or absence of non-speaking of each detected participant to the terminal device used by the moderator of the meeting, A meeting support program for causing a computer to execute the processing.

Images