JP2017168903A - Information processing apparatus, conference system, and method for controlling information processing apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing apparatus having a speaker tracking function, and not to use at least some microphones of microphones in a microphone array for inputting voices of speakers according to the state of speaker tracking so as to use some of the microphones for another purpose.SOLUTION: An information processing apparatus comprises: a microphone array 114 that includes a plurality of microphones; a speaker 115 that outputs voices; a sound source direction detection part 130 that detects the directions of the voices input to the microphone array 114 on the basis of the voices input to the plurality of microphones; and a voice input control part 132 that does not use at least one or more microphones of the microphones for collecting the voices from speakers according to a result of detection performed by the sound source direction detection part 130.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an information processing apparatus, a conference system, and a method for controlling the information processing apparatus.

  In recent years, a conference system (remote conference system, which connects a terminal device (also called a conference terminal) installed in a remote place (base) via a network such as the Internet and performs a remote conference (also called a video conference or a video conference) Video conferencing systems and video conferencing systems) are widely used.

  A conference terminal in this conference system is installed in a conference room or the like at each base, and performs a remote conference by exchanging images and sounds of conference attendees with the conference terminal of the other party. Specifically, each conference terminal captures a conference attendee attending a remote conference with a camera, collects the conference attendee's voice with a microphone, and transmits image data and audio data to the destination conference terminal. On the other hand, it receives image data and audio data transmitted from the conference terminal of the other party, displays a conference screen using the received image data on a display unit (monitor), and outputs audio data from a speaker. .

  As a microphone of a conference terminal, it is known to use a microphone array (also referred to as a voice input unit) in which a plurality of microphones (also referred to as voice input units) for inputting voice are arranged. Based on the time difference between the sound sources that reach the microphone, the direction in which the sound (that is, the speech of the conference participant) is input is specified (referred to as the sound source direction detection function or the sound source direction detection process). A device having a function of detecting a participant who speaks (referred to as a speaker) and imaging the speaker with a camera (referred to as a speaker tracking function) is known.

  However, remote conferences are not always conducted in an environment free of ambient noise. For example, a conference terminal is installed in a space separated by a simple partition or a conference room with a thin wall next to it. For example, noise from the surroundings that is not related to the remote conference may be collected by the microphone of the conference terminal. In this case, it becomes difficult to hear the voice of the conference participant at the destination site.

  On the other hand, for example, in Patent Document 1, the arrangement of a person is determined based on an image photographed by a camera, and sounds input from a plurality of microphones are individually amplified according to the determined arrangement of the person. A video conferencing apparatus that automatically sets the sound collection characteristics of an appropriate microphone corresponding to the arrangement of the conference attendees without depending on the user's operation and accurately collects the speech sound of the conference attendees. It is disclosed.

  Usually, in a remote conference, there are few participants evenly around the microphone array, and the voice input direction is often limited to a predetermined number of directions. Even in such a case, conventionally, all the microphones in the microphone array are used for collecting the voice of the speaker, and there remains room for study in controlling the sound collection characteristics of the microphone array.

  Therefore, the present invention provides an information processing apparatus having a speaker tracking function, in which at least some of the microphones in the microphone array are not used for voice input of a speaker according to the speaker tracking status. An object of the present invention is to provide an information processing apparatus that can use the microphones of other parts for other purposes.

  In order to achieve this object, an information processing apparatus according to the present invention includes a voice input unit including a plurality of voice input units, a voice output unit that outputs voice, and a voice input to the plurality of voice input units. Based on the sound source direction detecting means for detecting the input direction of the sound to the sound input means, and at least one of the sound input sections is uttered according to the detection result of the sound source direction detecting means. Voice input control means serving as a voice input unit that is not used for collecting voice from a person.

  According to the present invention, in the information processing apparatus having the speaker tracking function, depending on the situation of the speaker tracking, at least some of the microphones of the microphone array are not used for voice input of the speaker. Some microphones can be used for other purposes.

It is a block diagram which shows the structural example of a video conference system. It is a block diagram which shows the main internal structural examples of a conference terminal. It is explanatory drawing of a sound source direction detection process. It is explanatory drawing (1) of the sound collection control of a microphone array. It is explanatory drawing (2) of the sound collection control of a microphone array. It is explanatory drawing of the input signal in a noise cancellation process. It is a flowchart which shows an example of the sound collection control of a microphone array. It is explanatory drawing (3) of the sound collection control of a microphone array.

  Hereinafter, the configuration according to the present invention will be described in detail based on the embodiment shown in FIGS.

[First Embodiment]
(Conference system configuration)
A configuration of a video conference system which is an embodiment of the conference system according to the present invention will be described.

  FIG. 1 is a block diagram illustrating a configuration example of the video conference system 1. As shown in FIG. 1, the video conference system 1 includes a server 3 and a plurality of conference terminals 5 (5-1, 5-2, 5-3, 5-4...), Such as the Internet. It is configured to be connected via a network N. A server computer or a workstation can be used as the server 3, and a general-purpose information processing device such as a personal computer can be used as the conference terminal 5 in addition to a dedicated conference terminal device (information processing device). Can do.

  The server 3 performs processing for monitoring whether or not a communication connection is established with each conference terminal 5, and the conference terminal 5 installed at a base (participating base) that participates in the video conference at the start of the conference. Processing for calling and processing for transferring image data and audio data transmitted during the video conference from the conference terminal 5 at the participating site where communication connection is established in response to the call to the conference terminal 5 at the other party (other participating site) Etc.

  Each of the conference terminals 5 is installed in a conference room or the like at a base in a remote place and operated by attendees of the video conference. The conference terminal 5 at each participating site during the video conference transmits to the server 3 the image data of the conference attendee imaged by the camera 112 to be described later and the audio data of the conference attendee collected by the microphone array 114. Image data and audio data transmitted from the conference terminal 5 at the participating base and transferred by the server 3 are received, displayed on the display 120 as a conference screen, and output (sound) from the speaker 115.

  For example, in the video conference in which three conference terminals 5-1 to 5-3 shown in FIG. 1 participate in the video conference system 1, image data and audio data transmitted from the conference terminal 5-1 are controlled by the server 3. Is transferred to the conference terminals 5-2 and 5-3 as the other party, but not transferred to the conference terminal 5-4. Similarly, the image data and audio data transmitted from the conference terminals 5-2 and 5-3 are controlled by the server 3 to the conference terminals 5-1 and 5-3 and the conference terminals 5-1 and 5 which are the respective counterparts. -2 and not transferred to the conference terminal 5-4. In this manner, in the video conference system 1, a video conference is performed between participating sites where two or more conference terminals 5 having established communication connections with the server 3 are installed.

(Conference terminal configuration)
FIG. 2 is a block diagram illustrating a main internal configuration example of the conference terminal 5. As shown in FIG. 2, the conference terminal 5 stores a program used to drive a CPU 101 such as a CPU (Central Processing Unit) 101 that controls the entire operation of the conference terminal 5 and an IPL (Initial Program Loader). ROM (Read Only Memory) 102, RAM (Random Access Memory) 103 used as a work area for CPU 101, flash memory 104 for storing various data such as terminal programs, image data, and audio data, and control of CPU 101 Therefore, an SSD (Solid State Drive) 105 that controls reading or writing of various data with respect to the flash memory 104, a media drive 107 that controls reading or writing (storage) of data with respect to the recording medium 106 such as a flash memory, and the destination of the conference terminal 5 Operation when selecting Operation unit 108 is a power switch 109 for switching ON / OFF the power of the conference terminal 5, and a network I / F (Interface) 111 for using a network N to the data transmission.

  The operation unit 108 is realized by an input device such as a keyboard, a mouse, a touch panel, and various switches, and outputs input data corresponding to the operation input to the CPU 101.

  The network I / F 111 is used for data communication with the outside (for example, the server 3). The network I / F 111 is connected to the network N via the LAN and transmits image data, audio data, and the like with the conference terminal 5 of the other party. Transmission / reception is performed via the server 3. This network I / F 111 is connected to Ethernet (registered trademark) by performing control corresponding to 10Base-T, 100Base-TX, 1000Base-T, etc., or IEEE802.11a / b / g / n. A device according to the connection mode such as a device that performs corresponding control (wireless LAN) or the like can be appropriately adopted and used.

  The conference terminal 5 also includes a built-in camera 112 that captures an image of a subject under the control of the CPU 101 to obtain image data, an image sensor I / F 113 that controls driving of the camera 112, and a built-in microphone array 114 that inputs sound. The built-in speaker 115 that outputs sound, the sound input / output I / F 116 that processes input / output of sound signals between the microphone array 114 and the speaker 115 according to the control of the CPU 101, and the external display 120 according to the control of the CPU 101 A display I / F 117 for transmitting image data, an external device connection I / F 118 for connecting various external devices, and a bus line 110 such as an address bus and a data bus for electrically connecting the above components. I have.

  The camera 112 as an imaging unit includes a lens and a solid-state imaging element that converts light into electric charges and digitizes an object image (video). As the solid-state imaging element, a CMOS (Complementary Metal Oxide Semiconductor) image sensor, A CCD (Charge Coupled Device) image sensor or the like is used.

  The camera 112 is for inputting images of the attendees of the conference. The camera 112 captures the situation in the conference room and outputs the generated image data to the CPU 101 as needed. The camera 112 follows the direction of the speaker detected by the microphone array 114 and controls to switch the imaging direction and imaging range.

  The microphone array 114 includes a plurality of microphones for inputting the voices of conference attendees, and outputs collected voice data of conference attendees to the CPU 101 as needed.

  The microphone array 114 may be a separate microphone array unit from the main body of the conference terminal 5 including the camera 112 and the speaker 115. In this case, the microphone array unit and the main body are connected by wire or wirelessly. Thereby, the freedom degree of the arrangement position of a microphone array can be improved.

  The speaker 115 is an audio output unit that outputs audio data input from the CPU 101.

  External devices such as an external camera, an external microphone, and an external speaker can be connected to the external device connection I / F 118 by a USB (Universal Serial Bus) cable or the like. For example, when an external camera is connected, the external camera may be operated in preference to the built-in camera 112 under the control of the CPU 101. Similarly, when an external microphone is connected or when an external speaker is connected, the external microphone is given priority over the built-in microphone array 114 or the built-in speaker 115 according to the control of the CPU 101. Alternatively, an external speaker may be driven.

  Note that the recording medium 106 is detachable from the conference terminal 5. Further, as long as it is a non-volatile memory that reads or writes data according to the control of the CPU 101, not only the flash memory 104 but also an EEPROM (Electrically Erasable and Programmable ROM) or the like may be used.

  Further, the terminal program may be recorded in a computer-readable recording medium such as the recording medium 106 and distributed as a file in an installable or executable format. The terminal program may be stored in the ROM 102 instead of the flash memory 104.

  The display 120 is a display unit configured by an LCD, an EL display, a CRT display, or the like that displays a subject image, an operation icon, and the like, and displays various screens such as a conference screen that displays image data input from the CPU 101. Output. The display 120 is connected to the display I / F 117 by a cable 120c. The cable 120c may be an analog RGB (VGA) signal cable, a component video cable, HDMI (registered trademark) (High-Definition Multimedia Interface) or DVI (Digital Video). Interactive) signal cable may be used.

  The CPU 101 receives image data input from the camera 112, audio data input from the microphone array 114, image data and audio data from the destination conference terminal 5 input from the network I / F 111, and input from the operation unit 108. Based on the input data to be recorded, the program or data recorded in the flash memory 104 or the like, and performs overall control of the operation of the conference terminal 5 by instructing each unit constituting the conference terminal 5 and transferring the data. . For example, the CPU 101 receives a call from the server 3 and establishes a communication connection with the server 3 and then transmits image data input from the camera 112 and audio data input from the microphone array 114 to the server 3. The process of receiving image data and audio data from the destination conference terminal 5 transferred from the server 3 is repeatedly performed in parallel.

  Specifically, the CPU 101 encodes the image data input from the camera 112 as needed during the video conference and the audio data input from the microphone array 114 as needed, and outputs them to the network I / F 111 so that they are stored in the server I / F 111. The process of transmitting to 3 is performed. The CPU 101 performs codec based on standards such as H.264 / AVC and H.264 / SVC, for example.

  In parallel with this, the CPU 101 receives image data and audio data transmitted from the destination conference terminal 5 and transferred by the server 3 via the network I / F 111. The CPU 101 has a codec function that decodes the received image data and audio data and transmits them to the display 120 and the speaker 115. As a result, the image and sound input at the destination conference terminal 5 are reproduced.

  In addition, the CPU 101 includes a sound source direction detection unit 130 that executes a sound source direction detection process based on input from each microphone of the microphone array 114. FIG. 3 is an explanatory diagram of sound source direction detection processing by the sound source direction detection unit 130. The sound source direction detection process is to identify the direction in which sound is input based on the time difference between sound sources reaching each microphone constituting the microphone array 114. That is, for example, as shown in FIG. 3, when voice is input from the speaker S1 as a sound source to four microphones (microphones 1 to 4), the arrival time difference (Δt1) between the microphone 1 and the microphone 2 Based on the arrival time difference between the microphone 1 and the microphone 3 (Δt2) and the arrival time difference between the microphone 1 and the microphone 4 (Δt3), the voice input direction (that is, the direction of the speaker) can be detected. As the sound source direction detection process, a known or new method can be applied.

  The CPU 101 also includes an imaging range control unit 131 (imaging range control means) that controls the imaging range of the camera 112 based on the detection result of the sound source direction detection unit 130. For example, the camera 112 is provided so that the imaging direction can be turned, and the turning is controlled by the CPU 101 based on the detected direction of the speaker. Further, the camera 112 is configured by using a wide-angle lens so that all the attendees of the conference are included in the visual field range (angle of view), and imaged by digital processing based on the detected direction of the speaker. Control for switching the range may be performed.

  In addition, the CPU 101 includes an audio input control unit 132 that controls the sound collection characteristics of the microphone array 114 based on the detection result of the sound source direction detection unit 130. The voice input control unit 132 will be described below.

(Voice input control)
FIG. 4 is an explanatory diagram of the sound collection control of the microphone array 114 by the voice input control unit 132. In the example illustrated in FIG. 4, the microphone array 114 includes eight microphones A to H. The voice input control unit 132 directs the directivity of the microphone (microphone beam) based on the detection result of the sound source direction detection process (that is, the direction of the speaker). FIG. 4 shows a range D1 in which directivity control is performed according to the voice input direction I1 from the speaker S1, and a range D2 in which directivity control is performed according to the voice input direction I2 from the speaker S2. This shows an example in which is formed.

  Here, consider a situation in which a remote conference is started and a certain time has passed. It is not a frequent occurrence that a conference participant newly joins, sits down, or changes the seating position during the conference, so that the microphone directivity of the microphone array 114 is not long after the remote conference is started. It can be recognized that there are a limited number of directions from the beginning.

  In other words, the position of the conference participant with respect to the installed microphone array 114 is normally fixed, and is used for voice input of the speaker in the remote conference among the plurality of microphones provided in the microphone array 114. It can be said that it is possible to distinguish between a microphone that should be used and a microphone that is unnecessary for the voice input of the speaker. In addition, it can be said that there is a high possibility that the sound is input from a direction in which no speaker is present.

  In the present embodiment, focusing on this point, the microphone array 114 recognizes microphones that may be unnecessary for the voice input of the speaker, and performs control for turning off the microphone input for these microphones, or The control is used for other purposes.

  FIG. 5 is an explanatory diagram showing details of the sound collection control of the microphone array 114 in the situation shown in FIG. For example, in the example of FIG. 5, the microphones A, G, and H of the microphone array 114 are enabled in the voice input direction I1 from the speaker S1, and the microphone array 114 is set in the voice input direction I2 from the speaker S2. Sound collection control of the microphone array 114 is performed with the microphones A, B, and C enabled.

  That is, in the example of FIG. 5, five microphones (also referred to as sound collection microphones 14 a) of microphones A, B, C, G, and H are used for collecting voice from the speaker. It can be said that the three microphones D, E, and F are microphones (also referred to as non-sound-collecting microphones 14b) that are unnecessary for collecting voice from the speaker. In addition, the sound input from the input direction I3 is highly likely to be noise.

  Therefore, the information processing apparatus (conference terminal 5) according to the present embodiment includes an audio input unit (microphone array 114) including a plurality of audio input units (microphones A to H), and an audio output unit that outputs audio ( Speaker 115), sound source direction detecting means (sound source direction detecting unit 130) for detecting the sound input direction to the sound input means based on the sound input to the plurality of sound input units, and detection by the sound source direction detecting means Depending on the result, voice input control means (voice input control) using a voice input unit (non-sound collecting microphone 14b) that does not use at least one of the voice input units for collecting voice from the speaker. Part 132). In addition, the code | symbol in embodiment and the example of application are shown in a parenthesis.

  For example, the voice input control unit 132 controls the voice input to be turned off for the non-sound collecting microphone 14b (mics D, E, and F). As a result, it is possible to eliminate the remaining microphones from being used in the microphone array 114, and to suppress the noise from being input and the noise being output from the conference terminal 5 at the connection destination, thereby preventing the conference participants from being connected. It is possible to prevent the voice from becoming difficult to hear and to realize a smooth conversation.

  In addition, the voice input control unit 132 controls, for example, diversion of the non-sound collecting microphone 14b (mics D, E, and F) to other uses. For example, the non-collecting microphone 14b is preferably a noise canceling microphone. The noise canceling process is a process of reducing noise by collecting noises and superimposing signals with opposite phases so as to cancel the collected sounds (noises). As the noise canceling process, a known or new technique can be applied.

  FIG. 6 is an explanatory diagram of an input signal in the noise cancellation process. As shown in FIG. 6A, the audio signal input to the microphone array 114 includes an audio input signal (main audio signal M) from a speaker to be collected, and an audio input signal (such as other noise) ( A noise signal N) is included.

  Then, noise is reduced as shown in FIG. 6C by noise cancellation processing in which the signal C for noise cancellation processing as shown in FIG. 6B is superimposed on the input signal shown in FIG. The signal R after noise reduction can be obtained.

  For example, in the example shown in FIG. 5, in the voice input direction I1 from the speaker S1, voice is collected from the microphone 14a (mics A, G, H) of the microphone array 114 and is not collected. The microphone 14b (microphones D, E, and F) collects noise, and performs noise cancellation processing on the sound collected by the non-collecting microphone 14b. At this time, the remaining microphones B and C are in a state in which voice input is possible because there is a possibility of speech from the speaker S2.

  Further, in the voice input direction I2 from the speaker S2, voice is collected from the microphone 14a (mics A, B, C) of the microphone array 114, and the non-sound microphone 14b (mics D, E, In F), noise is collected, and noise cancellation processing is performed on the sound collected by the non-collecting microphone 14b. At this time, the remaining microphones G and H are in a state in which voice input is possible because there is a possibility of speech from the speaker S1.

  The sound collection control of the microphone array 114 described so far will be described with reference to the flowchart of FIG. First, when a video conference is started by pressing a conference start button on the conference terminal 5 or a conference call from the destination conference terminal 5 (S101), the sound source direction detection unit 130 inputs sound to the microphone array 114. The direction is detected (S102). The detection result is accumulated in the temporary storage device (S103).

Next, the sound input control unit 132 determines the sound collecting microphone 14a and the non-sound collecting microphone 14b among the microphones of the microphone array 114 based on the detection result of the accumulated sound input direction (S104). . In this case, the determination criterion is not limited as long as it is determined based on the detection ratio and the number of detections in the sound source direction detection process. For example,
In the sound source direction detection process, the microphone corresponding to the direction that has not been detected as the sound source direction for a predetermined time can be set as the non-sound collecting microphone 14b, and the other microphones can be set as the sound collecting microphone 14a. Further, for example, the microphone corresponding to the direction detected at a predetermined ratio or more of the number of detections detected in the sound source direction detection process is set as the sound collecting microphone 14a, and the other microphones are set as the non-sound collecting microphone 14b. It can be.

  Next, in the determination in S104, the microphone determined as the non-collecting microphone 14b is set as a noise canceling microphone (S105), and noise cancellation is performed on the input sound (noise) from the non-collecting microphone 14b. The process is executed (S106).

  As described above, the conference terminal 5 according to the present embodiment is a conference terminal 5 having a function of performing speaker tracking based on the input direction of sound to the microphone array 114, and further, with the progress of the conference. For microphones that are not in the voice input direction (microphones in the direction in which no speaker is present), some microphones in the microphone array 114 are used for purposes other than voice input by not using the voice input microphone for the speaker. It is possible to do.

  In conventional conference terminals, the sound collection range of the microphone and the image capture range of the camera were focused on collecting and capturing the image over a wide range and transmitting it to the other party's base. It is now possible to treat the other speech and imaging range as noise.

  In the conference terminal 5 according to the present embodiment, when the microphone array 114 detects the input direction of the sound source and performs speaker tracking for a while, the position where the conference participant exists is found, and the microphone array 114 Focusing on the fact that the microphones that are not used are identified by fixing the direction of directivity, the microphones of the microphone array 114 are divided into microphones for obtaining necessary sound and other microphones.

  Then, by using a microphone other than the microphone for obtaining the necessary sound, for example, for noise removal, it is possible to effectively use each microphone of the microphone array 114 and to reduce noise. It is possible to improve the conference environment by improving the ease of listening to voice at the previous conference terminal 5.

[Second Embodiment]
Hereinafter, another embodiment of the conference terminal 5 which is an example of the information processing apparatus according to the present invention will be described. In addition, the description about the same point as the said embodiment is abbreviate | omitted suitably.

  As sound collection control using the microphone array 114, a microphone input at the highest sound pressure (sound level) among the microphones of the microphone array 114 is used as a sound collection microphone 14a, and at least some of the other microphones are used. The non-sound collecting microphone 14b may be controlled.

  FIG. 8 is an explanatory diagram of the sound collection control of the microphone array 114 by the voice input control unit 132 according to the second embodiment. In the example shown in FIG. 8, the voice is input from the speaker S2 in the voice input direction I2.

  In the present embodiment, among the microphones of the microphone array 114, the microphone B closest to the speaker S2 and input at the highest sound pressure (sound level) is used as the sound collection microphone 14a. Since it can be determined that the input from the microphone farthest from the microphone 14a for sound collection (the microphone F at the diagonal position in the example shown in FIG. 8) is likely to be noise, This is a non-sound collecting microphone 14b, which is a noise canceling microphone.

  In the example of FIG. 8, an example is shown in which one microphone is selected as each of the sound collecting microphones 14a and the non-sound collecting microphones 14b. However, two or more microphones may be selected.

  The above-described embodiment is a preferred embodiment of the present invention, but is not limited thereto, and various modifications can be made without departing from the gist of the present invention.

1 Video conference system 3 Server 5 Conference terminal 101 CPU
102 ROM
103 RAM
104 Flash memory 105 SSD
106 Recording medium 107 Media drive 108 Operation unit 109 Power switch 110 Bus line 111 Network I / F
112 Camera 113 Image sensor I / F
114 Microphone array 14a Microphone for sound collection 14b Microphone for non-sound collection 115 Speaker 116 Audio input / output I / F
117 Display I / F
118 External device connection I / F
120 Display 120c Cable 130 Sound Source Direction Detection Unit 131 Imaging Range Control Unit 132 Audio Input Control Unit N Network

Japanese Patent No. 5418327

Claims (9)

Voice input means comprising a plurality of voice input units;
Audio output means for outputting audio;
Sound source direction detection means for detecting the input direction of the sound to the sound input means based on the sound input to the plurality of sound input units;
A voice input control unit configured to use at least one or more voice input units among the voice input units as voice input units that are not used for collecting voice from a speaker according to a detection result of the sound source direction detection unit. An information processing apparatus characterized by that.   The voice input control means is a voice that does not use at least one voice input unit corresponding to a direction that has not been detected as a voice input direction for a predetermined time in the sound source direction detection means for collecting voice from a speaker. The information processing apparatus according to claim 1, wherein the information processing apparatus is an input unit.   The information processing apparatus according to claim 1, wherein the voice input control unit uses a voice input unit that is not used for collecting voice from a speaker as a voice input unit for noise cancellation.   The information processing apparatus according to claim 1, wherein the voice input control unit turns off voice input of a voice input unit that is not used for collecting voice from a speaker.   The sound source direction detecting means uses at least one voice input unit including a voice input having the highest voice level among voice inputs from the plurality of voice input units as a voice input unit used for collecting voice from a speaker. The information processing apparatus according to claim 1, wherein at least one of the other voice input units is a voice input unit that is not used for collecting voice from a speaker.   The sound source direction detecting means uses a voice input unit having the highest voice level among voice inputs from the plurality of voice input units as a voice input unit for collecting sound, and inputs a voice farthest from the voice input unit. The information processing apparatus according to claim 5, wherein the voice input unit is not used for collecting sound. Imaging means for imaging a predetermined range;
The information processing apparatus according to claim 1, further comprising: an imaging range control unit that controls an imaging range of the imaging unit according to a detection result of the sound source direction detection unit.   A conference system comprising the information processing apparatus according to claim 1 as at least one of a plurality of conference terminals, wherein voice data is transmitted and received between the conference terminals. Voice input means comprising a plurality of voice input units;
A method of controlling an information processing apparatus comprising: audio output means for outputting sound;
A sound source direction detection process for detecting a voice input direction to the voice input unit based on voices input to the plurality of voice input units;
A voice input control process in which at least one voice input unit of the voice input units is a voice input unit that is not used for collecting voice from a speaker according to a detection result in the sound source direction detection process; A method for controlling an information processing apparatus.

Images