WO2019142230A1

WO2019142230A1 - Voice analysis device, voice analysis method, voice analysis program, and voice analysis system

Info

Publication number: WO2019142230A1
Application number: PCT/JP2018/000941
Authority: WO
Inventors: 武志水本; 哲也菅原
Original assignee: ハイラブル株式会社
Priority date: 2018-01-16
Filing date: 2018-01-16
Publication date: 2019-07-25
Also published as: JP6646134B2; JPWO2019142230A1

Abstract

The purpose of the present invention is to provide a voice analysis device, a voice analysis method, a voice analysis program, and a voice analysis system, which enable analysis of a discussion at low cost. A voice analysis device 100 according to one embodiment of the present invention includes: a voice acquisition unit 112 that acquires voices uttered by a plurality of participants; an analysis unit 114 that detects, in the voices, transition from a speech spoken by a first participant among the plurality of participants to a speech spoken by a second participant among the plurality of participants; and an output unit 115 that displays, on a display unit, information indicating the occurrence timing of the transition.

Description

Speech analysis device, speech analysis method, speech analysis program and speech analysis system

The present invention relates to a voice analysis device for analyzing voice, a voice analysis method, a voice analysis program and a voice analysis system.

The Harkness method (also referred to as the Harkness method) is known as a method for analyzing discussions in group learning and meetings (see, for example, Non-Patent Document 1). In the Harkness method, the transition of each participant's utterance is recorded in a line. In this way, it is possible to analyze the contribution of each participant to the discussion and the relationship with others. The Harkness Law can also be effectively applied to active learning where students take the initiative in learning.

However, with the Harkness method, the burden on the registrar is large because the registrar needs to constantly record the discussion. Also, in order to analyze a plurality of groups, it is necessary to arrange a recorder for each group. Therefore, there is a problem that high cost is required to implement the Harkness method.

The present invention has been made in view of these points, and it is an object of the present invention to provide a voice analysis device, a voice analysis method, a voice analysis program, and a voice analysis system that can analyze arguments at low cost.

According to a first aspect of the present invention, there is provided a voice analysis device comprising: an acquisition unit for acquiring voices uttered by a plurality of participants; and a plurality of the plurality of participants from the speech of a first participant among the plurality of participants It has an analysis part which detects transition to a statement of the 2nd participant among participants, and an output part which displays on a display part the information which shows the timing which the transition generated.

The output unit may display the information indicating the timing on the display unit by a line connecting a position corresponding to the first participant and a position corresponding to the second participant.

The output unit generates the line at the time when the transition occurs on the display unit, and erases the line after a predetermined time has elapsed from the time when the transition occurs, as information indicating the timing. The time change of the transition may be displayed.

The output unit may change the display mode of the line according to a combination of the first participant and the second participant.

The output unit may change the display mode of the line according to the number of times the transition occurs.

The analysis unit identifies a period in which each of the plurality of participants is speaking based on the voice, and the second participant speaks from the period in which the first participant speaks The transition may be detected when the period is switched.

The output unit may cause the display unit to display an amount of speech of each of the plurality of participants in addition to the time change of the transition.

The speech analysis method according to the second aspect of the present invention is characterized in that the processor acquires the speech uttered by a plurality of participants, and the speech of the first participant among the plurality of participants in the speech A step of detecting a transition to a second participant's utterance among a plurality of participants, and a step of displaying information indicating timing at which the transition has occurred on a display unit are performed.

The voice analysis program according to the third aspect of the present invention is characterized in that the step of obtaining voices uttered by a plurality of participants on a computer, and the utterance of the first participant among the plurality of participants in the voice A step of detecting a transition to a second participant's utterance among a plurality of participants, and a step of displaying information indicating a timing at which the transition has occurred on a display unit are performed.

A voice analysis system according to a fourth aspect of the present invention includes a voice analysis device and a communication terminal capable of communicating with the voice analysis device, the communication terminal having a display unit for displaying information, the voice The analysis device includes an acquisition unit for acquiring voices uttered by a plurality of participants, and a second participant among the plurality of participants from a statement of a first participant among the plurality of participants in the voice. An analysis unit that detects a transition to a message, and an output unit that causes the display unit to display information indicating a timing at which the transition has occurred.

According to the present invention, it is possible to analyze the argument at low cost.

It is a schematic diagram of the speech analysis system concerning this embodiment. It is a block diagram of a speech analysis system concerning this embodiment. It is a schematic diagram of the speech analysis method which the speech analysis system concerning this embodiment performs. It is a front view of the display part of the communication terminal which is displaying the setting screen. It is a schematic diagram of the matrix which shows the transition of the speaker which the analysis part calculated. It is a front view of the display part of the communication terminal which is displaying the speaker transition screen. It is a front view of the display part of the communication terminal which is displaying the speech order screen. It is a front view of the display part of the communication terminal which is displaying the analysis report screen. It is a sequence diagram of the speech analysis method which the speech analysis system concerning this embodiment performs.

[Overview of speech analysis system S]
FIG. 1 is a schematic view of a speech analysis system S according to the present embodiment. The voice analysis system S includes a voice analysis device 100, a sound collection device 10, and a communication terminal 20. The number of sound collectors 10 and communication terminals 20 included in the speech analysis system S is not limited. The voice analysis system S may include devices such as other servers and terminals.

The voice analysis device 100, the sound collection device 10, and the communication terminal 20 are connected via a network N such as a local area network or the Internet. At least a part of the voice analysis device 100, the sound collection device 10, and the communication terminal 20 may be directly connected without the network N.

The sound collector 10 includes a microphone array including a plurality of sound collectors (microphones) arranged in different orientations. For example, the microphone array includes eight microphones equally spaced on the same circumference in the horizontal plane with respect to the ground. The sound collection device 10 transmits the voice acquired using the microphone array to the voice analysis device 100 as data.

The communication terminal 20 is a communication device capable of performing wired or wireless communication. The communication terminal 20 is, for example, a portable terminal such as a smart phone terminal or a computer terminal such as a personal computer. The communication terminal 20 receives the setting of analysis conditions from the analyst and displays the analysis result by the voice analysis device 100.

The voice analysis device 100 is a computer that analyzes the voice acquired by the sound collection device 10 by a voice analysis method described later. Further, the voice analysis device 100 transmits the result of the voice analysis to the communication terminal 20.

[Configuration of speech analysis system S]
FIG. 2 is a block diagram of the speech analysis system S according to the present embodiment. Arrows in FIG. 2 indicate the main data flow, and there may be data flows not shown in FIG. In FIG. 2, each block is not a hardware (apparatus) unit configuration but a function unit configuration. As such, the blocks shown in FIG. 2 may be implemented in a single device or may be implemented separately in multiple devices. Transfer of data between the blocks may be performed via any means such as a data bus, a network, a portable storage medium, and the like.

The communication terminal 20 has a display unit 21 for displaying various information, and an operation unit 22 for receiving an operation by an analyst. The display unit 21 includes a display device such as a liquid crystal display or an organic light emitting diode (OLED) display. The operation unit 22 includes operation members such as a button, a switch, and a dial. The display unit 21 and the operation unit 22 may be integrally configured by using a touch screen capable of detecting the position of contact by the analyst as the display unit 21.

The voice analysis device 100 includes a control unit 110, a communication unit 120, and a storage unit 130. The control unit 110 includes a setting unit 111, a sound acquisition unit 112, a sound source localization unit 113, an analysis unit 114, and an output unit 115. The storage unit 130 includes a setting information storage unit 131, a voice storage unit 132, and an analysis result storage unit 133.

The communication unit 120 is a communication interface for communicating with the sound collection device 10 and the communication terminal 20 via the network N. The communication unit 120 includes a processor for performing communication, a connector, an electric circuit, and the like. The communication unit 120 performs predetermined processing on a communication signal received from the outside to acquire data, and inputs the acquired data to the control unit 110. Further, the communication unit 120 performs predetermined processing on the data input from the control unit 110 to generate a communication signal, and transmits the generated communication signal to the outside.

The storage unit 130 is a storage medium including a read only memory (ROM), a random access memory (RAM), a hard disk drive, and the like. The storage unit 130 stores in advance a program to be executed by the control unit 110. The storage unit 130 may be provided outside the voice analysis device 100, and in this case, data may be exchanged with the control unit 110 via the communication unit 120.

The setting information storage unit 131 stores setting information indicating analysis conditions set by the analyst in the communication terminal 20. The voice storage unit 132 stores the voice acquired by the sound collection device 10. The analysis result storage unit 133 stores an analysis result indicating the result of analyzing the voice. The setting information storage unit 131, the voice storage unit 132, and the analysis result storage unit 133 may be storage areas on the storage unit 130, or a database configured on the storage unit 130.

The control unit 110 is, for example, a processor such as a central processing unit (CPU), and executes the program stored in the storage unit 130 to set the setting unit 111, the sound acquisition unit 112, the sound source localization unit 113, the analysis unit 114, and the like. It functions as the output unit 115. The functions of the setting unit 111, the sound acquisition unit 112, the sound source localization unit 113, the analysis unit 114, and the output unit 115 will be described later with reference to FIGS. 3 to 8. At least a part of the functions of the control unit 110 may be performed by an electrical circuit. In addition, at least a part of the functions of the control unit 110 may be executed by a program executed via a network.

The speech analysis system S according to the present embodiment is not limited to the specific configuration shown in FIG. For example, the voice analysis device 100 is not limited to one device, and may be configured by connecting two or more physically separated devices in a wired or wireless manner.

[Description of voice analysis method]
FIG. 3 is a schematic view of the speech analysis method performed by the speech analysis system S according to the present embodiment. First, the analyst sets the analysis conditions by operating the operation unit 22 of the communication terminal 20. For example, the analysis condition is information indicating the number of participants in the argument to be analyzed and the direction in which each participant (that is, each of a plurality of participants) is located with reference to the sound collection device 10. The communication terminal 20 receives the setting of analysis conditions from the analyst, and transmits the setting as the setting information to the voice analysis device 100 (a). The setting unit 111 of the voice analysis device 100 acquires setting information from the communication terminal 20 and causes the setting information storage unit 131 to store the setting information.

FIG. 4 is a front view of the display unit 21 of the communication terminal 20 displaying the setting screen A. As shown in FIG. The communication terminal 20 displays the setting screen A on the display unit 21 and receives the setting of the analysis condition by the analyst. The setting screen A includes a position setting area A1, a start button A2, and an end button A3. The positioning area A1 is an area for setting the direction in which each participant U is actually positioned with reference to the sound collection device 10 in the argument to be analyzed. For example, the position setting area A1 represents a circle centered on the position of the sound collector 10 as shown in FIG. 4, and further represents an angle based on the sound collector 10 along the circle.

The analyst sets the position of each participant U in the position setting area A1 by operating the operation unit 22 of the communication terminal 20. In the vicinity of the position set for each participant U, identification information (here, U1 to U4) for identifying each participant U is allocated and displayed. In the example of FIG. 4, four participants U1 to U4 are set. The portion corresponding to each participant U in the positioning area A1 is displayed in a different color for each participant. Thereby, the analyst can easily recognize the direction in which each participant U is set.

The start button A2 and the end button A3 are virtual buttons displayed on the display unit 21, respectively. The communication terminal 20 transmits a signal of a start instruction to the voice analysis device 100 when the analyst presses the start button A2. The communication terminal 20 transmits a signal of a termination instruction to the voice analysis device 100 when the analyst presses the termination button A3. In the present embodiment, from the start instruction to the end instruction by the analyst is one discussion.

When the voice acquisition unit 112 of the voice analysis device 100 receives the signal of the start instruction from the communication terminal 20, the voice acquisition unit 112 transmits a signal instructing acquisition of voice to the sound collection device 10 (b). When the sound collection device 10 receives a signal instructing acquisition of voice from the voice analysis device 100, the collection of voice is started. Further, when the voice acquisition unit 112 of the voice analysis device 100 receives the signal of the termination instruction from the communication terminal 20, the voice acquisition unit 112 transmits a signal instructing the termination of the voice acquisition to the sound collection device 10. When the sound collection device 10 receives a signal instructing the end of the acquisition of sound from the speech analysis device 100, the sound collection device 10 ends the acquisition of sound.

The sound collection device 10 acquires voices in each of a plurality of sound collection units, and internally records the sound as the sound of each channel corresponding to each sound collection unit. Then, the sound collection device 10 transmits the acquired voices of the plurality of channels to the voice analysis device 100 (c). The sound collector 10 may transmit the acquired voice sequentially or may transmit a predetermined amount or a predetermined time of sound. Further, the sound collection device 10 may collectively transmit the sound from the start to the end of the acquisition. The voice acquisition unit 112 of the voice analysis device 100 receives voice from the sound collection device 10 and stores the voice in the voice storage unit 132.

The voice analysis device 100 analyzes voice at predetermined timing using the voice acquired from the sound collection device 10. The voice analysis device 100 may analyze the voice when the analyst gives an analysis instruction at the communication terminal 20 by a predetermined operation. In this case, the analyst selects a voice corresponding to the argument to be analyzed from the voices stored in the voice storage unit 132.

In addition, the voice analysis device 100 may analyze the voice when the voice acquisition ends. In this case, the speech from the start to the end of the acquisition corresponds to the argument to be analyzed. In addition, the voice analysis device 100 may analyze voice sequentially (that is, in real time processing) during acquisition of voice. In this case, the voice analysis device 100 goes back from the current time, and the voice for a predetermined time (for example, 30 seconds) in the past corresponds to the argument to be analyzed.

When analyzing speech, first, the sound source localization unit 113 performs sound source localization based on the plurality of channels of speech acquired by the speech acquisition unit 112 (d). The sound source localization is processing for estimating the direction of the sound source included in the sound acquired by the sound acquisition unit 112 for each time (for example, every 10 milliseconds to 100 milliseconds). The sound source localization unit 113 associates the direction of the sound source estimated for each time with the direction of the participant indicated by the setting information stored in the setting information storage unit 131.

If the sound source localization unit 113 can identify the direction of the sound source based on the sound acquired from the sound collection device 10, a known sound source localization method such as Multiple Signal Classification (MUSIC) method or beam forming method can be used. .

Next, the analysis unit 114 analyzes the voice based on the voice acquired by the voice acquisition unit 112 and the direction of the sound source estimated by the sound source localization unit 113 (e). The analysis unit 114 may analyze the entire completed discussion as an analysis target, or may analyze a part of the discussion in the case of real-time processing.

Specifically, based on the voice acquired by the voice acquisition unit 112 and the direction of the sound source estimated by the sound source localization unit 113, the analysis unit 114 first performs analysis (for example, 10 milliseconds to 100 milliseconds) in the discussion of the analysis target. Every second), it is determined which participant speaks (speaks). The analysis unit 114 specifies a continuous period from the start to the end of one participant's speech as a speech period, and causes the analysis result storage unit 133 to store the same. When a plurality of participants speak at the same time, the analysis unit 114 specifies a speech period for each participant.

In addition, the analysis unit 114 calculates the amount of speech of each participant for each time, and causes the analysis result storage unit 133 to store the amount. Specifically, in a certain time window (for example, 5 seconds), the analysis unit 114 calculates a value obtained by dividing the length of time during which the participant speaks by the length of the time window as the amount of speech per time Do. Then, the analysis unit 114 calculates the amount of speech per hour for each participant while shifting the time window by a predetermined time (for example, one second) from the start time of the discussion to the end time (currently in the case of real time processing). repeat.

Then, when the analysis unit 114 switches to another utterance period after a certain utterance period, the analysis unit 114 detects the transition of the speaker. For the transition of the speaker, the same participant participates when another participant (second participant) speaks after one participant (first participant) finishes speaking and after the one participant finishes speaking May make the following remarks. Also, it may be detected as one transition that the speech period has been switched two or more times. For example, after one participant (the first participant) finished speaking, another participant (the second participant) spoke and then another participant (the third participant) spoke May be detected as one transition. The analysis unit 114 counts the occurrence time of the transition detected in the discussion of the analysis target, the transition source participant, and the transition destination participant, associates them with one another, and stores the result in the analysis result storage unit 133.

FIG. 5 is a schematic view of the matrix B indicating the transition of the speaker collected by the analysis unit 114. As shown in FIG. Although in FIG. 5 the matrix B is represented as a table of character strings for visibility, it may be represented in other forms recognizable by a computer, such as binary data.

The matrix B represents the number of transitions from the transition source participant to the transition destination participant in the analysis target discussion. In the example of FIG. 5, the number of transitions from the participant U1 to the same participant U1 is two, and the number of transitions from the participant U1 to another participant U4 is eight. The diagonal components of matrix B indicate that the speakers did not alternate, and the non-diagonal components of matrix B indicate that the speakers alternate. Therefore, the analysis unit 114 can determine the atmosphere of the group by comparing the diagonal and non-diagonal components of the matrix B.

[Description of display method]
The output unit 115 performs control to display the analysis result by the analysis unit 114 on the display unit 21 by transmitting the display information to the communication terminal 20 (f). The display control method of the analysis result by the output unit 115 will be described below with reference to FIGS. 6 to 8.

When displaying the analysis result, the output unit 115 of the voice analysis device 100 reads the analysis result by the analysis unit 114 for the display target discussion from the analysis result storage unit 133. The output unit 115 may display a discussion immediately after the analysis by the analysis unit 114 is completed, or may display a discussion specified by the analyst.

First, a speaker transition screen C displaying information indicating the transition timing of the speaker will be described. FIG. 6 is a front view of the display unit 21 of the communication terminal 20 displaying the speaker transition screen C. As shown in FIG. The speaker transition screen C includes a circle C1 indicating the arrangement of the participants U, a line C2 indicating the transition of the speakers, and a bar C3 indicating the amount of speech of each participant U.

When displaying the speaker transition screen C, the output unit 115 displays the time change of the speaker transition as information indicating the transition timing of the speaker based on the analysis result read from the analysis result storage unit 133. To generate display information for Specifically, when a transition of an utterance from a participant to another participant occurs, the output unit 115 determines the position of the transition source participant for a predetermined period (for example, 5 seconds) from the time of occurrence of the transition. And display information for displaying a line connecting the position of the target and the transition destination participant.

The circle C1 is a circular area that schematically represents the arrangement of each participant U. The output unit 115 displays the identification information (that is, U1 to U4) of the participant U near the position on the circle C1 corresponding to the position of each participant U set in FIG.

A line C2 is a line connecting the position of the transition source participant U on the circle C1 and the position of the transition destination participant U on the circle C1 when the transition of the speaker occurs. The line C2 is displayed in a predetermined color and a predetermined thickness. The line C2 may be a straight line segment, a bent line, or a broken line like a dotted line.

The output unit 115 causes the display unit 21 to display a line C2 connecting the position of the transition source participant U and the position of the transition destination participant U for a predetermined period (five seconds in this case) from the transition generation time. Then, the output unit 115 causes the display unit 21 to erase the line C2 after a predetermined period from the occurrence time of the transition. The output unit 115 repeats generation and deletion of a line representing the transition of the speaker from the start time to the end time of the display target discussion. Thus, the output unit 115 can cause the display unit 21 to display the time change of the transition of the speaker. The output unit 115 may automatically advance the time during display (that is, may display as a moving image), or may advance the time during display according to the operation by the user.

As described above, the output unit 115 indicates how the transition tendency changes along the time series of the discussion by displaying the time change of the transition of the speaker as information indicating the timing of the transition of the speaker. be able to. As a result, the analyst can efficiently grasp the role of each participant U and the relationship between the participants U along the time series of the discussion.

When displaying a plurality of lines C2 for the same combination of participants U, the output unit 115 may shift the positions of both ends of the plurality of lines C2 by a predetermined amount and cause the display unit 21 to display the positions. As a result, the output unit 115 can prevent the plurality of lines C2 from matching each other even when a plurality of transitions occur in the same time between the same participants U.

In addition, when a plurality of transitions occur for the same combination of participants U in a short time (for example, within 5 seconds), the output unit 115 displays a display mode such as the thickness and color of the line C2 based on the number of transitions that occur. You may change the For example, the output unit 115 causes the display unit 21 to display a thicker line C2 as the number of transitions increases, or displays the line C2 in a different color according to the number of transitions. The output unit 115 can display the fact that a plurality of transitions have occurred in the same time between the same participants U in a manner easily understood by the analyst.

In addition, the output unit 115 may change the display mode such as thickness or color of the line C2 based on the number of times of transition from the start time of the discussion to the time during display in the same combination of the participants U . For example, the output unit 115 causes the display unit 21 to display the line C2 thicker as the number of cumulative transitions increases, or causes the line C2 to be displayed in a different color according to the number of cumulative transitions. As a result, the output unit 115 can display the fact that the number of transitions of the cumulative total is high or low for each combination of the participants U in a manner easily understood by the analyst.

Further, the output unit 115 may change the display mode such as the thickness and color of the line C2 depending on the combination of the participants U. For example, the output unit 115 causes the display unit 21 to display the line C2 with a different thickness or color depending on the combination of the participants U. Thereby, the output unit 115 can display the combination of the participants U corresponding to the line C2 in a manner easy for the analyst to understand.

A bar C3 is a bar-like area that represents the amount of speech of each participant U. The output unit 115 acquires the amount of speech of each participant U at each time during display, which is indicated by the analysis result read out from the analysis result storage unit 133. Then, the output unit 115 causes the bar C3 having a length or a size corresponding to the read amount of speech to be displayed at a position on the circle C1 corresponding to the position of each participant U. For example, the output unit 115 causes the display unit 21 to display the bar C3 such that the length from the circumference of the circle C1 toward the center becomes longer as the amount of speech of the participant U increases. As a result, the output unit 115 can display the amount of speech of each participant during the displayed time in an easily understandable manner to the analyst in addition to the time change of the transition of the speech.

In addition, the output unit 115 may display a bar C3 having a length or a size corresponding to the cumulative value of the amount of speech from the start time of the discussion to the time being displayed, not limited to the amount of speech for each time. In addition, the output unit 115 may change the display mode such as the color or pattern of the bar C3 depending on the participant U.

Further, the output unit 115 is not limited to the time change of the transition from one participant U to another participant U, and may display the time change of the combination of the participants U in which the transition has occurred. In this case, the output unit 115 causes the circle C1 to display identification information (for example, “U1-U2”, “U1-U3”, etc.) indicating the combination of the participants U.

Then, for example, when the transition between the participant U1 and the participant U3 occurs within a predetermined time after the transition between the participant U1 and the participant U2 occurs, the output unit 115 outputs “U1-U2 The display unit 21 displays a line C2 connecting the position of “” and the position of “U1-U3”. Then, the output unit 115 causes the display unit 21 to erase the line C2 a predetermined time after the line C2 is displayed. Thereby, the output unit 115 can represent how the combination of the participants U in which the transition has occurred changes along the time series of the discussion.

Next, the speech order screen D for displaying the order of speech in the discussion will be described. FIG. 7 is a front view of the display unit 21 of the communication terminal 20 displaying the speech order screen D. The speech order screen D includes a region D1 indicating the amount of speech of the participant U and an arrow D2 indicating the number of transitions between the speakers.

When displaying the speech order screen D, the output unit 115 acquires the amount of speech of each participant U in the discussion of the display target for each time indicated by the analysis result read out from the analysis result storage unit 133. Then, the output unit 115 calculates the total amount of speech of each participant U by summing up the amounts of speech for each time from the start time to the end time of the display target discussion. Further, the output unit 115 acquires, from the analysis result read out from the analysis result storage unit 133, the number of transitions (that is, the matrix B illustrated in FIG. 5) generated in the display target discussion for each combination of participants U.

A region D1 is a graphic representing the total amount of speech of each participant U. The output unit 115 causes the display unit 21 to display an area D1 having a size corresponding to the total amount of speech. For example, the output unit 115 causes the display unit 21 to display a circle with a larger radius as the total amount of speech of each participant U is larger as the area D1. The area D1 is not limited to a circle, but may be another figure such as a polygon.

An arrow D2 is a graphic representing the direction of transition and the number of transitions from one participant U to another participant U. The output unit 115 displays, from the area D1 corresponding to the transition source participant U, to the area D1 corresponding to the transition destination participant U, an arrow D2 of a thickness corresponding to the number of transitions on the display unit Let The arrow D2 may be a straight arrow, a curved arrow, or a broken arrow like a dotted line.

For example, the output unit 115 causes the display unit 21 to display the arrow D2 thicker as the number of transitions from the transition source participant U to the transition destination participant U increases. The output unit 115 may not display the arrow D2 for the combination of the participants U whose number of transitions is equal to or less than a predetermined threshold.

The output unit 115 may adjust the arrangement of the plurality of areas D1 based on the number of transitions between the participants U. In this case, the output unit 115 arranges two areas D1 corresponding to the participant U with many transition times near and arranges two areas D1 corresponding to the participant U with small transition numbers in the distance. Do. Alternatively, the output unit 115 may arrange the plurality of areas D1 based on the physical position of the participant U. In this case, the output unit 115 arranges the plurality of areas D1 so as to match the positions of the participants U set in FIG. 4.

Thus, the output unit 115 simultaneously indicates the amount of speech of the participant U and the number of transitions between the participants. As a result, the analyst can grasp at a glance the flow of utterances among the participants U and which participant U talks more or less.

Next, an analysis report screen E for displaying the whole discussion will be described. FIG. 8 is a front view of the display unit 21 of the communication terminal 20 displaying the analysis report screen E. The analysis report screen E includes a main statement order E1, a group atmosphere E2, and a participant classification E3.

When displaying the analysis report screen E, the output unit 115 acquires the amount of speech of each participant U in the discussion of the display target for each time indicated by the analysis result read out from the analysis result storage unit 133. Then, the output unit 115 calculates the total amount of speech of each participant U by summing up the amounts of speech for each time from the start time to the end time of the display target discussion. Further, the output unit 115 acquires, from the analysis result read out from the analysis result storage unit 133, the number of transitions (that is, the matrix B illustrated in FIG. 5) generated in the display target discussion for each combination of participants U.

The order of main utterances E1 is information indicating the transition of the speaker who frequently occurred in the discussion. The output unit 115 sums up the number of transitions for a series of transitions from one participant U to one or more other participants U and then returning to the first participant U. For example, the series of transitions includes transitioning from participant U1 to participant U4, then transitioning from participant U4 to participant U3, and then transitioning from participant U3 to the first participant U1. The output unit 115 determines the combination of the participants U indicated by a series of transitions having the largest number of transitions as the main utterance order E1 and causes the analysis report screen E to be displayed. The output unit 115 may determine the order E1 of two or more main utterances in descending order of the number of transitions. This allows the analyst to grasp the participant U who was at the center of the discussion.

The group atmosphere E2 is information indicating an atmosphere as to whether the number of speaker changes is large or small in the discussion. Specifically, in the matrix B shown in FIG. 5, the output unit 115 calculates the average value of the number of transitions of diagonal components (that is, between the same participants U) and non-diagonal components (that is, between different participants U). And the average value of the number of transitions of Then, the output unit 115 causes the analysis report screen E to display the ratio of the average value of the diagonal components and the average value of the non-diagonal components as the atmosphere E2 of the group. In the example of FIG. 8, the output unit 115 displays an arrow at a position corresponding to the ratio of the average value of the diagonal components and the average value of the non-diagonal components on the scale extending in the left-right direction. Further, the output unit 115 may display a value indicating an average value of diagonal components and an average value of non-diagonal components. This enables the analyst to grasp the atmosphere of the whole group who discussed.

Participant classification E3 is information for classifying each participant U based on the volume and transition of each participant U in the discussion. The output unit 115 classifies each participant U with respect to two axes of an axis indicating the amount of utterance of the participant U and an axis indicating whether the participant U was at the center of the discussion.

Specifically, the output unit 115 arranges the participant U whose utterance amount is equal to or more than a predetermined threshold above the origin (rightward in FIG. 8) on the axis indicating the utterance amount of the participant U, and the utterance amount Is arranged below the origin (to the left in FIG. 8). The output unit 115 arranges the participant U included in the main statement order E1 above the origin (upward in FIG. 8) with respect to an axis indicating whether the participant U was at the center of the discussion. , Place the participant U not included in the main statement order E1 below the origin (downward in FIG. 8).

The output unit 115 displays predetermined labels for four areas (quadrants) divided into two axes. The labels of the respective areas are preset in the voice analysis device 100. In the example of FIG. 8, the output unit 115 is “leader type” with respect to the upper right area (the participant U who has a large amount of speech and is the center of discussion) and the upper left area (the small amount of speech is the center of the discussion "Participant type" for one participant U), "One more for another type" for the lower right area (a large amount of talks, non-controversial participant U), lower left area (a small amount of speech , "Non-participatory" is displayed for the non-centered participant U). By classifying each participant U in this manner, the analyst can grasp the state of each participant U in the entire discussion.

Furthermore, the output unit 115 may determine the affinity of the participants U based on the transition of the speaker, and may display the analysis on the analysis report screen E. The output unit 115 sums up the numbers of transitions for all combinations of two participants U. The output unit 115 determines that the combination of participants U whose number of transitions is equal to or more than a predetermined threshold is good compatibility, and determines that the combination of participants U whose number of transitions is less than the predetermined threshold is bad. Then, the output unit 115 causes the analysis report screen E to display the compatibility determined for each combination of the participants U. Thereby, the analyst can grasp that there are more or less transitions for each combination of participants U.

The output unit 115 switches the speaker transition screen C, the speech order screen D, and the analysis report screen E and causes the display unit 21 to display the screen by receiving an operation by the analyst. The output unit 115 may cause the display unit 21 to display only a part of the speaker transition screen C, the speech order screen D, and the analysis report screen E. The output unit 115 is not limited to the display on the display unit, and may output the analysis result by other methods such as printing by a printer, data recording to a storage device, and the like.

[Sequence of voice analysis method]
FIG. 9 is a sequence diagram of the speech analysis method performed by the speech analysis system S according to the present embodiment. First, the communication terminal 20 receives the setting of analysis conditions from the analyst, and transmits the setting as setting information to the voice analysis device 100 (S11). The setting unit 111 of the voice analysis device 100 acquires setting information from the communication terminal 20 and causes the setting information storage unit 131 to store the setting information.

Next, the voice acquisition unit 112 of the voice analysis device 100 transmits a signal instructing voice acquisition to the sound collection device 10 (S12). When the sound collection device 10 receives a signal instructing acquisition of voice from the voice analysis device 100, recording of voice is started using a plurality of sound collection units, and the voice analysis device 100 collects voices of a plurality of channels recorded. (S13). The voice acquisition unit 112 of the voice analysis device 100 receives voice from the sound collection device 10 and stores the voice in the voice storage unit 132.

The voice analysis device 100 starts voice analysis at one of timings when an analyst gives instructions, when voice acquisition ends, or during voice acquisition (that is, real-time processing). When analyzing speech, first, the sound source localization unit 113 performs sound source localization based on the speech acquired by the speech acquisition unit 112 (S14).

Next, for each participant, the analysis unit 114 determines, based on the voice acquired by the voice acquisition unit 112 and the direction of the sound source estimated by the sound source localization unit 113, which participant has spoken at each time. The speech period and the speech volume are specified in (S15). The analysis unit 114 causes the analysis result storage unit 133 to store the utterance period and the utterance amount for each participant.

Further, when the analysis unit 114 switches to another utterance period after a certain utterance period, the analysis unit 114 detects the transition of the speaker (S16). The analysis unit 114 counts the time of occurrence of transition, the participant at the transition source, and the participant at the transition destination, associates them with one another, and stores them in the analysis result storage unit 133.

The output unit 115 performs control to display the analysis result on the display unit 21 of the communication terminal 20 (S17). Specifically, the output unit 115 transmits, to the communication terminal 20, display information for displaying the speaker transition screen C, the speech order screen D, and the analysis report screen E described above.

The communication terminal 20 causes the display unit 21 to display the analysis result in accordance with the display information received from the voice analysis device 100 (S18).

[Effect of this embodiment]
The voice analysis device 100 according to the present embodiment automatically analyzes the discussions of a plurality of participants based on the voice acquired using the sound collection device 10 having a plurality of sound collection units. Therefore, it is not necessary to have the recorder monitor the discussion as in the Harkness method described in Non-Patent Document 1, and it is not necessary to arrange the recorder for each group, so the cost is low.

In addition, the Harkness method described in Non-Patent Document 1 represents the transition of speech in the entire period from the start to the end of the discussion. Therefore, the analyst could not grasp the change of the transition tendency along the time series of the argument. On the other hand, the speech analysis device 100 according to the present embodiment displays the time change of the transition as information indicating the timing of the transition of the utterance between the participants in the discussion. Thereby, the analyst can grasp the role of each participant U and the relationship between the participants U along the time series of the discussion.

Further, the voice analysis device 100 simultaneously displays the amount of speech of the participant U and the number of transitions between the participants based on the acquired voice. As a result, the analyst can grasp at a glance the flow of utterances among the participants U and which participant U talks more or less.

In addition, the voice analysis device 100 displays the order of main utterances in the discussion, the atmosphere of the group, and the classification of the participants based on the acquired voice. This enables the analyst to understand the participants who were at the center of the discussion, the atmosphere of the whole group who discussed, and the state of each participant in the whole discussion.

As mentioned above, although the present invention was explained using an embodiment, the technical scope of the present invention is not limited to the range given in the above-mentioned embodiment, and various modification and change are possible within the range of the gist. is there. For example, a specific embodiment of device distribution and integration is not limited to the above embodiment, and all or a part thereof may be functionally or physically distributed and integrated in any unit. Can. In addition, new embodiments produced by any combination of a plurality of embodiments are also included in the embodiments of the present invention. The effects of the new embodiment generated by the combination combine the effects of the original embodiment.

The processor of the speech analysis device 100, the sound collection device 10, and the communication terminal 20 is the main body of each step (process) included in the speech analysis method shown in FIG. That is, the processors of the voice analysis device 100, the sound collection device 10 and the communication terminal 20 read a program for executing the voice analysis method shown in FIG. 9 from the storage unit, and execute the program to execute the voice analysis device 100. By controlling each part of the sound device 10 and the communication terminal 20, the voice analysis method shown in FIG. 9 is performed. The steps included in the speech analysis method shown in FIG. 9 may be partially omitted, the order between the steps may be changed, and a plurality of steps may be performed in parallel.

S voice analysis system 100 voice analysis device 110 control unit 112 voice acquisition unit 114 analysis unit 115 output unit 10 sound collector 20 communication terminal 21 display unit

Claims

An acquisition unit for acquiring voices uttered by a plurality of participants;
An analysis unit that detects a transition from a first participant's utterance among the plurality of participants in the voice to a second participant's utterance among the plurality of participants;
An output unit configured to display information indicating timing at which the transition has occurred on a display unit;
Voice analyzer with.
The said output part displays the information which shows the said timing by the line which ties the position corresponding to a said 1st participant, and the position corresponding to a said 2nd participant on the said display part. Voice analyzer as described.
The output unit generates the line at the time when the transition occurs on the display unit, and erases the line after a predetermined time has elapsed from the time when the transition occurs, as information indicating the timing. The voice analysis device according to claim 2, wherein the time change of the transition is displayed.
The voice analysis device according to claim 3, wherein the output unit changes a display mode of the line according to a combination of the first participant and the second participant.
The voice analysis device according to claim 3, wherein the output unit changes a display mode of the line according to the number of times the transition occurs.
The analysis unit identifies a period in which each of the plurality of participants is speaking based on the voice, and the second participant speaks from the period in which the first participant speaks The voice analysis device according to any one of claims 1 to 5, which detects the transition when switching to the period.
The voice analysis device according to any one of claims 1 to 6, wherein the output unit causes the display unit to display the amount of speech of each of the plurality of participants in addition to the time change of the transition.
Processor is
Acquiring voices uttered by a plurality of participants;
Detecting a transition from a first participant's utterance among the plurality of participants in the voice to a second participant's utterance among the plurality of participants;
Displaying information indicating timing at which the transition has occurred on a display unit;
Voice analysis method to perform.
On the computer
Acquiring voices uttered by a plurality of participants;
Detecting a transition from a first participant's utterance among the plurality of participants in the voice to a second participant's utterance among the plurality of participants;
Displaying information indicating timing at which the transition has occurred on a display unit;
Voice analysis program to run.
A voice analysis device; and a communication terminal capable of communicating with the voice analysis device;
The communication terminal has a display unit for displaying information;
The voice analysis device
An acquisition unit for acquiring voices uttered by a plurality of participants;
An analysis unit that detects a transition from a first participant's utterance among the plurality of participants in the voice to a second participant's utterance among the plurality of participants;
An output unit that causes the display unit to display information indicating timing at which the transition has occurred;
Voice analysis system.