JP4507905B2 - Communication control device, communication control method, program and recording medium for audio conference - Google Patents

Description

  The present invention relates to an apparatus, a method, and the like for starting communication with a partner when performing an audio conference.

  One method of performing a conference between two or more places apart from each other is called an audio conference. This is because microphones, speakers, and communication devices are prepared at each location, and audio input to the microphone is transmitted from the communication device to the other party's location via the communication line, and an audio signal received from the other party's location is received by the communication device. Is output to the speaker for audio output. A public telephone line may be used as a communication line, and in that case, it is also called a telephone conference.

  When starting such an audio conference, communication with the other party's location is performed from any one location based on the identification information of the communication device at the other party's location (for example, the telephone number of the other party's location in a conference call). It is necessary to perform a process for starting (for example, in a conference call, the telephone number of the other party's place is called).

Conventionally, as a terminal device for a telephone conference (a terminal device having a microphone and a speaker and having a telephone function), a terminal number generating unit storing identification number data unique to each terminal device, setting of a partner to be connected, etc. There has been proposed one provided with a key for performing various operations (see, for example, Patent Document 1).
JP 11-215240 A (paragraph number 0009, FIG. 1)

  However, in such a conventional telephone conference terminal device, the meeting partner is the same, but the partner's location is not constant at each meeting (for example, a vacant conference room among a plurality of conference rooms In the case of making a reservation, it is very inconvenient because the attendee of the conference must check the current location of the other party and select the terminal device at that location each time.

  In the audio conference such as a conference call, the present invention can easily communicate with the location of the other party even if the conference partner is the same but the location of the other party is not constant at each conference. It was made as an issue to be able to start a conference and hold a conference.

  In order to solve this problem, a communication control apparatus for voice conference according to the present invention includes voice recognition means for voice recognition of a voice signal from a microphone, and identification information of communication means at a plurality of locations used for the conference. By referring to the stored storage means and schedule data in which the meeting attendee's planned location among the plurality of places is associated with the name of the meeting attendee, the voice recognized by the voice recognition means Determine if at least one of the names of the meeting attendees is included, and if so, check the location corresponding to the meeting attendee with the included name from this schedule data, This processing is performed by controlling the processing means for acquiring the identification information of the communication means at the confirmed location from the storage means and the communication means for performing communication via the communication line. Characterized in that a control means for starting the communication identification information destined acquired by stage.

  In addition, the communication control method for audio conference according to the present invention includes a first step for recognizing an audio signal from a microphone, a location scheduled to be used by a conference attendant among a plurality of locations used for the conference, and Referring to the schedule data corresponding to the names of the meeting attendees, it is determined whether or not at least one meeting attendee name is included in the voice recognized by the voice recognition means. The location corresponding to the attendee of the name included in the schedule data is confirmed from the schedule data, and the identification information of the communication means at the confirmed location is identified as the identification information of the communication means at the plurality of locations. The second step of acquiring from the storage unit storing the information and the communication unit for performing communication via the communication line, the identification information acquired in the second step And having a third step for starting a communication destined.

  In addition, the program according to the present invention includes a first procedure for recognizing an audio signal from a microphone on a computer, a place to be used by a meeting attendee among a plurality of places used for the meeting, and the meeting attendance. Refers to the schedule data that corresponds to the name of the party, and determines whether or not the name of at least one of the meeting attendees is included in the voice recognized by the voice recognition means. In addition, the location corresponding to the meeting attendee with the name included is confirmed from the schedule data, and the identification information of the communication means at the confirmed location is stored as the identification information of the communication means at the plurality of locations. The second procedure acquired from the storage unit and the communication unit for performing communication via the communication line are controlled, and the communication addressed to the identification information acquired in the second procedure is controlled. Characterized in that to execute a third procedure to start.

  The computer-readable recording medium according to the present invention is intended to be used by a conference attendant among a plurality of locations used for a conference and a first procedure for recognizing a speech signal from a microphone. With reference to the schedule data in which the location and the name of the meeting attendee are associated with each other, it is determined whether or not at least one meeting attendee name is included in the voice recognized by the voice recognition means, If it is included, the location corresponding to the attendee of the included name is confirmed from the schedule data, and the identification information of the communication means of the confirmed location is confirmed by the communication means in the plurality of locations. The second procedure acquired from the storage unit storing the identification information and the communication unit for performing communication via the communication line are controlled. The program for executing the third procedure to start communication of the resulting identification information destined characterized by being recorded.

  In these inventions, whether or not a speech signal from a microphone is recognized and whether or not the recognized speech includes the name of at least one of the meeting attendees is a meeting attendance among a plurality of locations used for the meeting. It is determined by referring to schedule data that associates the place that the person intends to use with the names of the attendees of the meeting.

  If included, the location corresponding to the meeting attendee with the included name is confirmed from this schedule data, and the identification information of the communication means of the confirmed location is the plurality of locations. Obtained from the storage means storing the identification information of the communication means.

  And the communication means for communicating via a communication line is controlled, and communication addressed to the acquired identification information is started.

  Therefore, even if the other party is the same, but the location of the other party is not constant at each meeting (for example, if you reserve and use a vacant meeting room among multiple meeting rooms) Just speaking to the microphone of the other party's name, communication with the other party's location is automatically started.

  As a result, even if the other party is the same, but the other party's location is not constant every time the conference is held, it is possible to easily start communication with the other party's location and hold the conference.

  In addition, as an example, voiceprint data is extracted from a voice signal from a microphone, voiceprint authentication means for identifying a speaker by comparing the extracted voiceprint data with previously registered voiceprint data, and schedule data is further provided. If the speaker identified by this voiceprint authentication means is a meeting attendee who intends to use the location on his / her side, and is not a conference attendee who intends to use that location It is preferable that the identification information is not acquired from the storage means.

  As a result, communication with the other party's location starts only when the person who is scheduled to attend the meeting at his / her location speaks the name of the other party, so that the outsider can communicate with the other party's location. Can be prevented from starting.

  Also, as an example, when a meeting attendee whose name is included in the speech recognized by speech recognition corresponds to multiple locations in the schedule data, the speech for selecting the location is synthesized and output by speech synthesis. Then, the selection result is discriminated from the voice recognized by voice recognition, the identification information of the communication means at the selected place is acquired from the storage means, the communication means is controlled, and the communication addressed to the acquired identification information is performed. It is preferred to start.

  As a result, if there are multiple locations corresponding to the same name on the schedule data (for example, if multiple people with the same name are scheduled to attend the meeting in different locations), select the location The synthesized speech to be output is output. Then, when the selection result is uttered toward the microphone so as to respond to the synthesized speech, communication with the selected place is automatically started. Therefore, even when there are multiple locations corresponding to the same name partner in the schedule data, it is possible to properly select the location that the original partner uses this time and start communication with that location. become.

  According to the present invention, even if the other party is the same, but the other party's location is not constant at each meeting, the person's name is automatically spoken to the microphone, and the other party's location is automatically set. Since the communication with the other party is started, it is possible to easily start the communication with the other party's place and hold the conference.

  Hereinafter, the present invention will be specifically described with reference to the drawings. FIG. 1 is a diagram showing an example of the overall configuration of a telephone conference system in a certain company X to which the present invention is applied. A plurality of meeting rooms (A meeting room, B meeting room, C meeting room, D meeting room, E meeting room,...) Exist at the head office, branch office, or office of company X. In each conference room, a line connection device 1, an omnidirectional audio input device 2, and a personal computer 3 are installed (there are not shown in the conference rooms after the D conference room).

  The line connection device 1 is a device provided with a circuit that performs processing of calling / incoming calls and signal transmission / reception processing via the public telephone line 4 (that is, a circuit having the same calling / calling function and signal transmission / reception function as a telephone). And connected to the public telephone line 4.

  The line connection device 1 also has an analog audio signal input terminal 1a, analog audio signal output terminals 1b and 1c, and a control signal input terminal 1d, and the analog audio signal input to the input terminal 1a. Is always output from the output terminal 1c. Further, when a call is made based on the control signal input to the input terminal 1d and the telephone is connected, an analog voice signal input to the input terminal 1a is transmitted via the public telephone line 4, and the public telephone line 4 The audio signal received via is output from the output terminal 1b.

  An input terminal 1 a and an output terminal 1 b of the line connection device 1 are connected to the omnidirectional audio input device 2, and an output terminal 1 c and an input terminal 1 d of the line connection device 1 are connected to the personal computer 3.

  The omnidirectional voice input device 2 is a device in which a microphone and a speaker are integrated for voice conference. 2A and 2B are diagrams showing an example of the external configuration of the omnidirectional audio input device 2, FIG. 2A is a perspective view, and FIG. 2B is a top view of the inside of the microphone housing portion 11 of FIG. It is.

  As shown in FIG. 2A, the omnidirectional audio input device 2 includes a microphone accommodating portion 11 for accommodating a microphone, a speaker accommodating portion 12 for accommodating a speaker that reproduces the audio of the conference partner, And an operation unit 13.

  As shown in FIG. 2B, six microphones MC <b> 1 to MC <b> 6 are equally arranged in all directions inside the microphone housing portion 11. Each microphone is a unidirectional microphone.

  The speaker accommodated in the speaker accommodating portion 12 is positioned at the center of the accommodating housing, and is configured such that sound from the speaker reaches the microphones MC1 to MC6 with substantially the same volume and phase.

  A meeting attendee in each conference room sits so as to surround the omnidirectional audio input device 2 and speaks to any of the microphones MC1 to MC6.

  FIG. 3 is a block diagram illustrating a circuit configuration example of the omnidirectional audio input device 2. The omnidirectional audio input device 2 includes an A / D converter block 51, an A / D converter 517, a DSP 52, a DSP 53, a CPU 54, D / A converters 551 and 552, amplifiers 561 and 562, The speaker 57 is included. In FIG. 3, six A / D converters 511 to 516 corresponding to the microphones MC1 to MC6 are shown as an example of the A / D converter block 51.

  The omnidirectional audio input apparatus 2 is a board in which these circuits are mounted, for example, inside a microphone housing portion 11 shown in FIG.

The CPU 54 performs overall control processing of the omnidirectional audio input device 2.
The DSP 52 performs processing (microphone selection processing) for selecting a sound signal of one microphone based on the sound signals from the six microphones MC1 to MC6 converted into digital signals by the A / D converters 511 to 516. Perform various signal processing. The internal processing of the DSP 52 will be described later.

  The DSP 53 functions as an echo canceller. That is, the size and delay amount of the audio signal from the partner conference room input via the A / D converter 517 are calculated, and a signal corresponding to the calculated audio signal size and delay amount is input via the DSP 52. Echo cancellation processing is performed by performing processing to subtract from the audio signal.

  The processing result of the DSP 53 is converted into an analog signal by the D / A converters 551 and 552. The analog audio signal from the D / A converter 552 is amplified by the amplifier 562, then output from the output terminal 571, and sent to the input terminal 1a of the line connection device 1 in FIG.

  The analog audio signal output from the output terminal 1b of the line connection device 1 in FIG. 1 is input to the input terminal 572 of the omnidirectional audio input device 2, digitally converted by the A / D converter 517, and input to the DSP 53. In addition to being used for echo cancellation processing, the sound is output from the speaker 57 via the D / A converter 551 and the amplifier 561.

  On the other hand, the sound signal of the microphone selected by the DSP 52 is also output as sound from the speaker 57 via the DSP 53. In other words, in addition to the voice of the speaker selected by the omnidirectional voice input device 2 arranged in the other party's conference room, the conference attendee in each conference room can hear the voice uttered by the speaker in his / her conference room. Can also be heard through the speaker 57.

The six microphones MC1 to MC6 built in the omnidirectional audio input device 2 are microphones having directivity.
When an omnidirectional microphone is used, all sounds around the microphone are collected. Therefore, the S / N of the voice of the speaker and the ambient noise is confused and a very good sound cannot be collected. In order to avoid this, the omnidirectional audio input device 2 collects sound with a directional microphone, thereby improving the S / N with surrounding noise.

Next, processing contents performed by the DSP 52 will be described.
The main processing performed in the DSP 52 is selection / switching processing of a microphone (hereinafter sometimes simply referred to as a microphone).
That is, based on the sound from each microphone, one microphone is specified, and the process of selecting and outputting the sound from the specified microphone is performed. At that time, if a plurality of conference participants who use the omnidirectional audio input unit 3 speak at the same time, the audio is mixed and difficult to hear for the other party, so only the audio signal from the selected microphone is output.

In order to perform this process accurately, the DSP 52 performs various signal processes exemplified below.
(A) Microphone signal band separation and peak hold processing
(B) Speech start / end determination processing (c) Speaker direction microphone detection processing (d) Microphone signal selection switching processing

FIG. 4 is a functional block diagram showing processing executed in the DSP 52.
As shown in FIG. 4, the DSP 52 performs BPF processing on each microphone signal and generates BPF blocks 521 including BPFs 5211 to 5216 that generate sound pressure level data, and the sound pressure level data of each microphone subjected to BPF processing. PH processing is performed on the PH block 522 including PHs 5221 to 5226 for generating peak values to be described later, and each process such as speech start determination and microphone switching processing to be described later is performed on the peak values of each microphone. And a determination processing unit 523.

The signal processing (a) to (d) described above by the DSP 52 having such a configuration will be described below.
(A) Band separation of microphone signal and peak hold processing This processing is performed by the BPF block 521 and the PH block 522 shown in FIG.
Each BPF process of the BPF block 521 is performed based on a predetermined band-pass characteristic (for example, 100 to 600 Hz) necessary for the start and end determination of a speech, which will be described later.
The PH processing generates a peak value that is data after performing processing for holding (peak holding) the maximum value of the sound pressure level data (microphone signal) subjected to BPF processing.
The subsequent processes, that is, the processes (b) to (d) are executed by the determination processing unit 523 that inputs the peak value calculated based on each microphone signal.

(B) Speech start / end determination processing The speech start determination / end determination processing is performed independently for each microphone, for example, by comparing a predetermined threshold with a sound pressure level to determine the start / end of the speech. To do. Further, a steady noise level may be sequentially measured so that the predetermined threshold value is variable.
For example, when the DSP 52 determines the start of speech from the microphone MC1, the DSP 52 increases the output gain set in the microphone MC1. On the contrary, when the end of the speech of the microphone MC1 is determined, the output gain set in the microphone MC1 is decreased.

(C) Speaker Direction Microphone Detection Processing This processing is processing for selecting one microphone having a high sound pressure level when the speakers facing each microphone speak at the same time. That is, when one speaker starts speaking, the above-described processing may be performed based on sound pressure level data from one microphone, but a plurality of speakers may speak at the same time. Therefore, the microphone related to the main speaker in that case is specified.
As shown in FIG. 4, the sound pressure level data of each microphone necessary for the process of detecting the microphone in the direction of the speaker is a band pass filter (BPF) process for the sound pressure level data input through each microphone. And a peak value obtained by performing a peak hold (PH) process.

(D) Microphone signal selection switching process In this process, (c) a process of switching the output of the DSP 52 to the microphone selected by the speaker direction microphone detection process is performed.
Specifically, it is performed by changing the output gain set for each microphone. For example, as shown in FIG. 5, the microphone signal selection switching process includes a multiplier of 6 circuits and an adder of 6 inputs, and the channel gain (CH Gain) of the multiplier to which the selected microphone signal is connected. ) To “1” and the channel gain of the other multipliers to “0”, the processing results of [selected microphone signal × 1] and [other microphone signal × 0] are added to the adder. Is done. As a result, the selected microphone signal (selected microphone signal) is sent to the DSP 53 (FIG. 3) at the subsequent stage.

  The personal computer 3 in each conference room in FIG. 1 is connected to a dedicated line (not shown) in the company X. Web-based groupware is introduced in the company X, and the schedule data of employees can be downloaded from a server (not shown) in the company X by the Web browser of the personal computer 3 in each conference room.

  Further, in the personal computer 3, as shown in FIG. 6, data of a telephone number table in which the name of each conference room is associated with the telephone number of the line connection device 1 installed in the conference room is stored in advance. ing.

  The personal computer 3 is installed with a voice recognition program, a voice synthesis program, a voice print authentication program, and a communication control program. These programs may be provided as a recording medium such as a CD-ROM, or may be downloaded from a website.

  The voice recognition program is a program for performing voice recognition of an unspecified speaker, and is voice data (here, sent from the omnidirectional voice input device 2 to the personal computer 3 via the line connection device 1 to be personalized. The acoustic features of the voice data (digitally converted by the sound board in the computer 3) are extracted, and the extracted features are collated with a previously registered voice model, and the closest candidate is output as a voice recognition result. As the voice recognition technique, a known technique may be applied to this voice recognition program.

  The speech synthesis program is a program for converting character data into speech data. As a speech synthesis technique, a known technique may be applied to this speech synthesis program.

The voiceprint authentication program converts voice data (here, voice data sent from the omnidirectional voice input device 2 to the personal computer 3 via the line connection device 1 and digitally converted by the sound board in the personal computer 3). This is a program for performing voiceprint authentication every unit time (for example, 3 seconds) to identify a speaker. As the voiceprint authentication technique, a known technique may be applied to this voiceprint authentication program.
Note that this unit time is preferably as short as possible if the processing capability of the CPU of the personal computer 3 allows, from the viewpoint of speaker identification accuracy, considering the case where there are a plurality of speakers and the speakers are switched.

The voiceprint authentication process of the voiceprint authentication program includes the following processes (1) to (3).
(1) Generation of voiceprint model A voiceprint model is created by analyzing the spectrum of voice data every unit time and extracting features of the voiceprint. That is, the voiceprint model is a representation of a collection of various sounds included in speech by a three-dimensional pattern of time, frequency, and sound intensity.

(2) Collation of voiceprint model The voiceprint model generated in the process of (1) above is compared with the voiceprint model registered in advance in the voiceprint register (storage area in the personal computer 3) together with the ID of the person who is the subject of voiceprint authentication. Then, a matching score SCR (larger as the feature amount approximates) corresponding to the degree to which the feature amount of the model approximates is calculated. Then, the ID corresponding to the voiceprint model that most closely approximates the voiceprint model generated by the process (1) is specified among the voiceprint models in the voiceprint register.

(3) Comparison between collation score and threshold value The collation score SCR calculated in the process (2) is compared with a predetermined threshold value THD, and if the collation score SCR exceeds the threshold value THD, the process (2) The identified ID is determined to be valid.

  In the voiceprint register in the personal computer 3 installed in each conference room, a voiceprint model of a company X employee (an employee who at least attends the meeting) is registered in advance as a voiceprint authentication target. The name of the employee is registered as the ID.

  Before starting the conference, the communication control program controls the line connection device 1 using the above speech recognition program, speech synthesis program, voiceprint authentication program, Web browser, and telephone number table shown in FIG. It is a program to do.

  FIG. 7 is a flowchart showing the processing contents of this communication control program. First, the Web browser is called to download schedule data relating to the use schedule of the employee's meeting room on the day created by the groupware, and the schedule data is acquired (step S1).

  FIG. 8 is a diagram illustrating this schedule data. From 10:00 to 12:00, three people Ichiro Tanaka, Jiro Honda and Saburo Suzuki use the A meeting room, three people Ito Rokuro, Hanako Sakata, and Nanao Sasaki use the C meeting room, and Sakata Taro, Shiro Tsurumaki and Goro Toda are scheduled to use the E meeting room.

  From 13:00 to 15:00, two people, Ichiro Tanaka and Jiro Honda, will use the B meeting room, and three people, Hachiro Kagawa, Kuro Sato, and Yoshiko Shinnai, will use the E meeting room. Yes.

  From 15:00 to 17:00, two people, Hanako Sakata and Shichiro Sasaki, will use the A meeting room, and two people, Taro Sakata and Goro Toda, will use the D meeting room.

  As shown in FIG. 7, following step S1, the voiceprint authentication program is called to execute the above-described voiceprint authentication processing, and the voice recognition program is called to perform voice recognition (step S2). Then, the process waits until the speaker is specified by the voiceprint authentication program (the specified ID is determined to be valid) (step S3).

  When the speaker is specified, the schedule data downloaded in step S1 is referred to and the specified speaker plans to use the conference room in which the personal computer 3 is installed in the current time zone. It is determined whether or not the employee is an employee (ie, a meeting attendee) (step S4).

  If no, return to step S3. On the other hand, if yes, the speech recognition result of the speaker by the speech recognition program is acquired (step S5). Then, referring to the schedule data downloaded in step S1, the employee who plans to use one of the conference rooms in the current time zone and the word “connect” are recorded in the voice that has been recognized. It is determined whether it is included (step S6).

  If no, refer to this schedule data and the voice recognized voice will contain the name of one of the conference rooms scheduled to be used in the current time zone and the word “connect” It is determined whether or not (step S7). If the answer is no again, the process returns to step S3.

  If yes in step S6, it is determined whether there are a plurality of recognized persons in the current time zone column in the schedule data (step S8).

  If no (if it exists only in one place), the conference room used by his employee is confirmed from the schedule data (step S9). Subsequently, the telephone number of the line connection device 1 in the confirmed conference room is acquired from the telephone number table shown in FIG. 6 (step S10).

  Then, a control signal for calling the acquired telephone number is sent to the line connection device 1 (FIG. 1) (step S11), and the process is terminated.

  If yes in step S8, a plurality of conference rooms used by the employee of the employee are confirmed from the schedule data (step S12). Then, the voice synthesis program is called to synthesize the voice for selecting the conference room, and the synthesized voice is output from the built-in speaker of the personal computer 3 (or the attached speaker connected to the personal computer 3 main body) (step S13). .

  Subsequently, the recognition result of the speech of the speaker by the speech recognition program after outputting the synthesized speech is acquired (step S14). And the selection result of a meeting room is discriminate | determined from the recognition result (step S15).

  In Step S13, for example, “OO □□” (where “OO” is the voice recognized in Step S5 and □□ is the name) is in the X meeting room from XX hours to XX hours. The synthesized voice of the inquiry “Is it?” Is output for each conference room used by the employee of that person while leaving a certain time (for example, several seconds).

  In step S15, if the word "Yes" is included in the words recognized by the voice recognition program immediately after the voice of this inquiry is output for one meeting room, the meeting room is selected. Determine.

  Following step S15, the determined telephone number of the line connection device 1 in the conference room is obtained from the telephone number table shown in FIG. 6 (step S16). Then, the process proceeds to step S11 described above.

  If yes in step S7, the telephone number of the line connection device 1 in the conference room with the recognized name is acquired from the telephone number table shown in FIG. 6 (step S17). Then, the process proceeds to step S11 described above.

  Next, a state of a conference in this telephone conference system (a state in which a telephone number of a conference room of a partner is called from one conference room) is shown as A at 10:00 to 12:00 on the schedule data shown in FIG. A conference room will be described as an example.

  In the schedule data of FIG. 8, from 10:00 to 12:00, three people Ichiro Tanaka, Jiro Honda and Saburo Suzuki use the A meeting room, and three people Taro Sakata, Shiro Tsurumaki and Goro Toda use the E meeting room. It is scheduled.

  Here, using A meeting room and E meeting room, Ichiro Tanaka, Jiro Honda and Saburo Suzuki from one department and Taro Sakata, Shiro Tsurumaki and Goro Toda from another department call The explanation will be made assuming that the meeting is scheduled.

  FIG. 9 is a diagram illustrating a state in which a conference is started from the conference room A side by speaking the partner of the conference. The three persons using the A meeting room know that at least Mr. Sakata will attend as the meeting partner, but do not know which meeting room the other party will use.

  Therefore, for example, Ichiro Tanaka among conference attendees using the A meeting room has reached 10 o'clock, so after starting the voice control program on the personal computer 3, any one of the omnidirectional voice input devices 2 Say “Mr. Sakata, connect” to the microphone.

  Then, a voice signal from the microphone that has input the voice is sent from the omnidirectional voice input device 2 to the personal computer 3 via the line connection device 1.

  In the personal computer 3, it is specified by voiceprint authentication that the speaker is Ichiro Tanaka (steps S2 and S3 in FIG. 7). And it is confirmed that Ichiro Tanaka plans to use the conference room A in the current time zone (10:00 to 12:00) on the schedule data (step S4 in FIG. 7).

  Furthermore, it is confirmed that the voice of “Mr. Sakata, connected” that has been voice-recognized includes the employee “Sakata” and the word “connected” (step S2, FIG. 7). S5, S6).

  However, as shown in FIG. 8, in the column of the current time zone (10:00 to 12:00) in the schedule data, Hanako Sakata (scheduled to use the C meeting room), Taro Sakata (scheduled to use the E meeting room) Thus, it is confirmed that there are two Mr. Sakata (step S8 in FIG. 7).

  Therefore, as shown in FIG. 10, first, a synthesized voice of an inquiry “Hanako Sakata is in the C meeting room from 10:00 to 12:00. Do you want to connect?” Is output from the personal computer 3 ( Steps S12 and S13 in FIG.

  Ichiro Tanaka who listened to the synthesized speech responds “No” (or remains silent) as shown in FIG. 10 because the conference partner is not Hanako Sakata. Then, as shown in FIG. 10, a synthesized voice of the query “Taro Sakata is in the E meeting room from 10:00 to 12:00. Do you want to connect?” Is output (step in FIG. 7). S13).

  Ichiro Tanaka who listened to this synthesized voice responds with “Yes” as shown in FIG. 10 because the other party is Taro Sakata. Then, it is determined that the E meeting room is selected (steps S14 and S15 in FIG. 7), and the telephone number of the line connection device 1 in the E meeting room is acquired from the telephone number table shown in FIG. 6 (FIG. 7). Step S16).

  Then, a control signal for calling the telephone number of the line connection apparatus 1 in the E meeting room is sent from the personal computer 3 to the line connection apparatus 1 (step S11 in FIG. 7).

  The line connection device 1 in the A conference room calls the telephone number of the line connection device 1 in the E conference room based on this control signal. Thereby, since the telephone connection is established between the line connection device 1 in the A meeting room and the line connection device 1 in the E meeting room, the telephone conference can be started between the A meeting room and the E meeting room.

  In the example of FIG. 9, Mr. Taro Sakata, who is one of the meeting partners, is uttered. However, when Mr. Shiro Tsurumaki and Mr. Goro Toda are uttered, the current time zone in the schedule data (10:00 to Since there is only one Tsurumaki or Toda in the column of “12:00” (step S8 in FIG. 7), the telephone of the line connection device 1 in the E meeting room is immediately output without outputting the synthesized voice of the inquiry. The number is acquired (steps S9 and S10 in FIG. 7), and a control signal for calling the telephone number of the line connection device 1 in the E meeting room is sent to the line connection device 1 (step S11 in FIG. 7).

  In addition, in the example of FIG. 9, the meeting partner is uttered, but it is known that the meeting party is in the E meeting room, but the other party's attendees are not known. If you say “E-conference room, connect”, the telephone number of the line connection device 1 in the E-conference room is immediately acquired (see FIG. 7 (steps S7 and S17), a control signal for calling the telephone number of the line connection device 1 in the E meeting room is sent to the line connection device 1 (step S11 in FIG. 7).

  Further, in the example of FIG. 9, a conference attendee who uses the conference room A speaks, but when a party other than the conference attendee speaks, the talker sets the conference room A in the current time zone ( Since it is not confirmed that it will be used at 10:00 to 12:00 (step S4 in FIG. 7), the telephone number of the line connection device 1 in the E meeting room is called from the line connection device 1 in the A meeting room. There is nothing.

  Also, in the example of FIG. 9, the conference attendee using the A conference room speaks, but when the conference attendee using the E conference room speaks, the line of the E conference room is exactly the same. The connection device 1 calls the telephone number of the line connection device 1 in the A conference room, and the telephone connection is established between the line connection device 1 in the E conference room and the line connection device 1 in the A conference room.

  As described above, according to this conference call system, when the other party is the same, but the other party's meeting room is not constant every meeting (reserving a vacant meeting room among a plurality of meeting rooms) Even when the other party's name is spoken to the microphone, communication with the other party's conference room is automatically started.

  As a result, even if the other party is the same, but the other party's conference room is not constant at each meeting, it is possible to easily start communication with the other party's conference room and hold a meeting.

  In addition, even if you know the conference room of the other party but you do not know the other party's attendees, you can automatically speak to the other party's conference room simply by speaking to the microphone. Since communication is started, it is possible to easily start communication with the other party's conference room and hold a conference.

  In addition, communication with the other party's conference room is started only when the person who is scheduled to attend the meeting in the conference room on his / her own side speaks the other party's name (or the name of the other party's conference room). It is possible to prevent the outsider from starting communication with the other party's conference room. Therefore, security in conference operation can be increased.

  In addition, even if there are multiple meeting rooms corresponding to the same name on the schedule data, a synthesized voice that selects the meeting room is output, and if the selection result is uttered in response to the synthesized voice, it is automatically Since the communication with the selected conference room is started, it is possible to appropriately select the conference room used by the original party this time and start the communication with the conference room.

  Note that in the above example, communication with the conference room of the other party of the conference is started by speaking an individual Mr. as the name of the conference attendee. However, when the name of the meeting partner is listed in the schedule data, or when the company name of the meeting partner is listed in the schedule data when the meeting is held outside the company, You may make it start communication with the meeting room of the other party by speaking the name of the other party's department or the company name of the other party as the name.

  In the above example, the present invention is applied to a telephone conference. However, the present invention is also applied to a voice conference other than a telephone conference (for example, a conference in which voice is transmitted and received between each conference room via a LAN or a dedicated line). May apply. Even in this case, the personal computer 3 may control the communication device used in the audio conference in the same manner as the line connection device 1 in FIG.

  In the above example, the voice recognition program, the voice synthesis program, the voiceprint authentication program, and the communication control program are separate software, but one piece of software having all the functions of these software is created and the personal computer 3 is created. You may install it on

  In the above example, the personal computer 3 in which application software such as a speech recognition program, a speech synthesis program, a voiceprint authentication program, and a communication control program is installed is provided. However, as another example, a device that executes a firmware having the same processing contents as those application software and includes a dedicated processor having a Web browser function may be provided instead of the personal computer 3.

  Moreover, in the above example, three apparatuses, the line connection apparatus 1, the omnidirectional voice input apparatus 2, and the personal computer 3, are installed in each conference room. However, the present invention is not limited to this, and the line connection device 1 and the omnidirectional audio input device 2 are integrated into a single device, or further, the dedicated processor as described above is mounted on the single device. The whole may be a single device.

  In the above example, the present invention is applied to a conference system in one company. However, the present invention may be applied to other conference systems (for example, a conference system between a plurality of companies).

1 is a diagram illustrating an example of the overall configuration of a telephone conference system to which the present invention is applied. It is a figure which shows the example of an external appearance structure of an omnidirectional audio | voice input apparatus. It is a block diagram which shows the circuit structural example of an omnidirectional audio | voice input apparatus. FIG. 4 is a functional block diagram of the DSP 52 in FIG. 3. It is a functional block diagram which shows the microphone signal selection switching process of DSP52. It is a figure which shows the telephone number table | surface in a personal computer. It is a flowchart which shows the processing content of a communication control program. It is a figure which illustrates schedule data. It is a figure which illustrates a mode that utters the other party of a meeting and starts a meeting. It is a figure which illustrates the synthetic voice etc. which select a meeting room.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 Line connection apparatus, 2 Omnidirectional audio input device, 3 Personal computer, 4 Public telephone line, 11 Microphone accommodating part, 12 Speaker accommodating part, 13 Operation part, MC1-MC6 microphone, 511-516 A / D converter, 52 , 53 DSP, 54 CPU, 57 Speaker

Claims (8)

Voice recognition means for recognizing a voice signal from a microphone;
Storage means for storing identification information of communication means at a plurality of locations used for the meeting;
Refer to schedule data in which the meeting attendee's planned location and the name of the meeting attendee are associated with each other among the plurality of locations, and at least one of the meetings attended by the voice recognized by the voice recognition means It is determined whether or not a person's name is included, and if included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and communication of the confirmed place is performed. Processing means for obtaining identification information of the means from the storage means;
Control means for controlling communication means for performing communication via a communication line, and starting communication addressed to the identification information acquired by the processing means ;
Voice print data is extracted from a voice signal from the microphone, and the extracted voice print data is compared with pre-registered voice print data to identify a speaker.
The processing means refers to the schedule data to determine whether or not the speaker identified by the voiceprint authentication means is a meeting attendee who plans to use a place where the communication control device is installed. And the communication control apparatus for audio | voice conferencing which does not acquire the said identification information from the said memory | storage means, when it is not the meeting attendee who is going to use this place . Voice recognition means for recognizing a voice signal from a microphone;
Storage means for storing identification information of communication means at a plurality of locations used for the meeting;
Refer to schedule data in which the meeting attendee's planned location and the name of the meeting attendee are associated with each other among the plurality of locations, and at least one of the meetings attended by the voice recognized by the voice recognition means It is determined whether or not a person's name is included, and if included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and communication of the confirmed place is performed. Processing means for obtaining identification information of the means from the storage means;
Control means for controlling communication means for performing communication via a communication line, and starting communication addressed to the identification information acquired by the processing means ;
Voice synthesis means,
The processing means, when a meeting attendee whose name is included in the voice recognized by the voice recognition means corresponds to a plurality of places in the schedule data, the voice synthesizing means A communication control device for voice conference , wherein the selection result is discriminated from the voice recognized by the voice recognition means, and the identification information of the communication means at the selected place is obtained from the storage means . A first step of recognizing a voice signal from a microphone by voice recognition means included in the communication control device ;
With reference to schedule data in which a meeting attendee plans to use a location among a plurality of locations used for a meeting and the name of the meeting attendee, the voice recognized by the voice recognition means is at least It is determined whether the name of the meeting attendee is included, and if it is included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and the confirmation A second step of acquiring the identification information of the communication means at the location from the storage means storing the identification information of the communication means at the plurality of locations;
A third step of controlling communication means for performing communication via a communication line and starting communication addressed to the identification information acquired in the second step;
Extracting voice print data from a voice signal from the microphone, and comparing the extracted voice print data with pre-registered voice print data to identify a speaker;
In the second step, referring to the schedule data, whether or not the speaker identified in the fourth step is a meeting attendee who plans to use the place where the communication control device is installed A communication control method for audio conferencing that does not acquire the identification information from the storage means if it is not a meeting attendee who intends to use the place . A first step of recognizing a voice signal from a microphone by voice recognition means included in the communication control device;
With reference to schedule data in which a meeting attendee plans to use a location among a plurality of locations used for a meeting and the name of the meeting attendee, the voice recognized by the voice recognition means is at least It is determined whether the name of the meeting attendee is included, and if it is included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and the confirmation A second step of acquiring the identification information of the communication means at the location from the storage means storing the identification information of the communication means at the plurality of locations;
A third step of controlling communication means for performing communication via a communication line and starting communication addressed to the identification information acquired in the second step;
In the second step, when a meeting attendee having a name included in the voice recognized by the voice recognition unit corresponds to a plurality of places in the schedule data, a voice for selecting a place is transmitted in the communication Synthesized by the speech synthesizer included in the control device and output, and then the selection result is determined from the speech recognized by the speech recognition unit, and the identification information of the communication unit at the selected location is acquired from the storage unit
Communication control method for voice conference. On the computer,
A first procedure for recognizing a voice signal from a microphone by voice recognition means included in the communication control device ;
With reference to schedule data in which a meeting attendee plans to use a location among a plurality of locations used for a meeting and the name of the meeting attendee, the voice recognized by the voice recognition means is at least It is determined whether the name of the meeting attendee is included, and if it is included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and the confirmation A second procedure for acquiring the identification information of the communication means at the location from the storage means storing the identification information of the communication means at the plurality of locations;
A third procedure for controlling communication means for performing communication via a communication line and starting communication addressed to the identification information acquired in the second procedure ;
A fourth procedure for extracting voice print data from a voice signal from the microphone, and comparing the extracted voice print data with previously registered voice print data to identify a speaker;
A program for executing
In the second procedure, referring to the schedule data, whether or not the speaker identified by the fourth procedure is a conference attendee who plans to use the place where the communication control device is installed A program that does not acquire the identification information from the storage means if it is not a meeting attendee who intends to use the place . On the computer,
A first procedure for recognizing a voice signal from a microphone by voice recognition means included in the communication control device;
With reference to schedule data in which a meeting attendee plans to use a location among a plurality of locations used for a meeting and the name of the meeting attendee, the voice recognized by the voice recognition means is at least It is determined whether the name of the meeting attendee is included, and if it is included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and the confirmation A second procedure for acquiring the identification information of the communication means at the location from the storage means storing the identification information of the communication means at the plurality of locations;
A third procedure for controlling communication means for performing communication via a communication line and starting communication addressed to the identification information acquired in the second procedure;
A program for executing
In the second procedure, when a meeting attendee whose name is included in the voice recognized by the voice recognition unit corresponds to a plurality of places in the schedule data, a voice for selecting a place is transmitted in the communication. Synthesized by the speech synthesizer included in the control device and output, and then the selection result is determined from the speech recognized by the speech recognition unit, and the identification information of the communication unit at the selected location is acquired from the storage unit
program. On the computer,
A first procedure for recognizing a voice signal from a microphone by voice recognition means included in the communication control device ;
With reference to schedule data in which a meeting attendee plans to use a location among a plurality of locations used for a meeting and the name of the meeting attendee, the voice recognized by the voice recognition means is at least It is determined whether the name of the meeting attendee is included, and if it is included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and the confirmation A second procedure for acquiring the identification information of the communication means at the location from the storage means storing the identification information of the communication means at the plurality of locations;
A third procedure for controlling communication means for performing communication via a communication line and starting communication addressed to the identification information acquired in the second procedure ;
A fourth procedure for extracting voice print data from a voice signal from the microphone, and comparing the extracted voice print data with previously registered voice print data to identify a speaker;
A computer-readable recording medium storing a program for executing
In the second procedure, referring to the schedule data, whether or not the speaker identified by the fourth procedure is a conference attendee who plans to use the place where the communication control device is installed And a computer-readable recording medium on which a program that does not acquire the identification information from the storage means is recorded if the person is not a meeting attendee who intends to use the place . On the computer,
A first procedure for recognizing a voice signal from a microphone by voice recognition means included in the communication control device;
With reference to schedule data in which a meeting attendee plans to use a location among a plurality of locations used for a meeting and the name of the meeting attendee, the voice recognized by the voice recognition means is at least It is determined whether the name of the meeting attendee is included, and if it is included, the location corresponding to the meeting attendee with the included name is confirmed from the schedule data, and the confirmation A second procedure for acquiring the identification information of the communication means at the location from the storage means storing the identification information of the communication means at the plurality of locations;
A third procedure for controlling communication means for performing communication via a communication line and starting communication addressed to the identification information acquired in the second procedure;
A computer-readable recording medium storing a program for executing
In the second procedure, when a meeting attendee whose name is included in the voice recognized by the voice recognition unit corresponds to a plurality of places in the schedule data, a voice for selecting a place is transmitted in the communication. Synthesized by the speech synthesizer included in the control device and output, and then the selection result is determined from the speech recognized by the speech recognition unit, and the identification information of the communication unit at the selected location is acquired from the storage unit
A computer-readable recording medium on which a program is recorded.

Images