Abstract: Speakers are identified based on sound origination detection through use of infrared detection of satellite microphones, estimation of distance between satellite microphones and base unit utilizing captured audio, and/or estimation of satellite microphone orientation utilizing captured audio. Multiple sound source localization results are combined to enhance sound source localization and/or active speaker detection accuracy.

Abstract: Architecture that uses near-end speech detection and far-end energy level detection to notify a user when a local microphone and/or speaker that the user is using, are muted. A voice activity detector is employed to detect the presence of near-end speech, sense the existing mute state of the near-end microphone, and then notify the user when the current microphone is muted. Separately or in combination therewith, received far-end voice signals are detected, the associated energy level computed, the existing mute state of the near-end audio speaker is sensed, and the user notified when the speaker is muted and/or at a reduced volume setting. These determinations enhance the user experience when the architecture is employed for communications sessions where participants connect via different communications modalities by automatically notifying the user of the audio device state, without attempting to contribute only to find that a microphone or speaker was muted.

Abstract: Techniques to detect a display device are described. An apparatus may include a video camera operative to receive video information for an image, and a microphone operative to receive audio information for an image. The apparatus may further include a monitor detection module communicatively coupled to the video camera and the microphone, where the monitor detection module is operative to detect a temporal watermark signal displayed by the monitor within the image, and determine a location for the monitor within the image based on the detection. The apparatus may also include an active speaker detector module communicatively coupled to the monitor detection module, where the active speaker detector module is operative to exclude false positives caused by the monitor. Other embodiments are described and claimed.

Abstract: A camera speakerphone having a microphone array may be used for videoconferencing. Example microphone array designs described herein may be used to perform Sound Source Localization (SSL) and improve audio quality of captured audio. In one example, an omni-directional camera speakerphone includes a base having a speaker and at least one microphone. A neck is coupled to the base which is coupled to a head. The head includes an omni-directional camera and at least one microphone.

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: Architecture that employs a signal (e.g., audible or inaudible sounds) to detect if endpoints of a communications session are sufficiently close to each other to induce echo, and then control (e.g., muting) is applied to one or more of the endpoints to prevent echo. The signals can be played and detected from the endpoints or a central conferencing component such as a multiple control unit (MCU). The MCU can provide support for legacy endpoints as well. When echo is detected, the offending endpoint(s) can be controlled to mute one or more onboard devices such as a speaker or microphone. The device(s) can be muted from a remote component or for a local component or locally by the endpoint user. A notification can be sent that notifies the endpoint user that the mute operation has been applied or should be applied to one or more of the local devices.

Abstract: Eye gaze reduction may be provided. First, a location of a near-end camera relative to a near-end screen may be determined. Next, based upon the determined location of the near-end camera, a location may be determined for a video window on the near-end screen. The determined location for the video window may be configured to reduce an eye gaze error in a near-end image transmitted to a far-end device from the near-end camera. Then video data from a far-end camera corresponding to the far-end device may be received and rendered in the video window at the determined location for the video window on the near-end screen.

Abstract: Gaze tracking or other interest indications are used during a video conference to determine one or more audio sources that are of interest to one or more participants to the video conference, such as by determining a conversation from among multiple conversations that a subset of participants are participating in or listening to, for enhancing the audio experience of one or more of the participants.

Abstract: A dynamically adjustable framed view of occupants in a room is captured through an automatic framing system. The system employs a camera system, including a pan/tilt/zoom (PTZ) camera and one or more depth cameras, to automatically locate occupants in a room and adjust the PTZ camera's pan, tilt, and zoom settings to focus in on the occupants and center them in the main video frame. The depth cameras may distinguish between occupants and inanimate objects and adaptively determine the location of the occupants in the room. The PTZ camera may be calibrated with the depth cameras in order to use the location information determined by the depth cameras to automatically center the occupants in the main video frame for a framed view. Additionally, the system may track position changes in the room and may dynamically adjust and update the framed view when changes occur.

Abstract: The claimed subject matter relates to an architecture that can preprocess audio portions of communications in order to enrich multiparty communication sessions or environments. In particular, the architecture can provide both a public channel for public communications that are received by substantially all connected parties and can further provide a private channel for private communications that are received by a selected subset of all connected parties. Most particularly, the architecture can apply an audio transform to communications that occur during the multiparty communication session based upon a target audience of the communication. By way of illustration, the architecture can apply a whisper transform to private communications, an emotion transform based upon relationships, an ambience or spatial transform based upon physical locations, or a pace transform based upon lack of presence.

Abstract: Embodiments of the invention compensate for the movement of a meeting capture device during a live meeting when performing speaker indexing of a recorded meeting. In one example, a first position of a capture device is determined. A second position of the capture device is determined after the capture device has been moved from the first position to the second position. The movement data associated with movement of the capture device from the first position to the second position is determined. The movement data is outputted and used in speaker indexing of the recorded meeting.

Abstract: Architecture for exploiting satellite microphones and employing other techniques of conference room camera/microphone systems to significantly improve the true positive rate (reduce false positives) in sound source localization (SSL). Techniques for realizing the improvement include using an LED emitter to determine the precise location of the satellite microphones on a table, using the base SSL and external sounds to determine the approximate location of the satellite microphone on the table, using the satellite microphone phase to improve the SSL performance, using the satellite microphone amplitude to improve the active speaker detector (ASD) performance, and using the satellite microphones to estimate camera zoom.

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: Techniques to detect a display device are described. An apparatus may include a video camera operative to receive video information for an image, and a microphone operative to receive audio information for an image. The apparatus may further include a monitor detection module communicatively coupled to the video camera and the microphone, where the monitor detection module is operative to detect a temporal watermark signal displayed by the monitor within the image, and determine a location for the monitor within the image based on the detection. The apparatus may also include an active speaker detector module communicatively coupled to the monitor detection module, where the active speaker detector module is operative to exclude false positives caused by the monitor. Other embodiments are described and claimed.

Abstract: Speakers are identified based on sound origination detection through use of infrared detection of satellite microphones, estimation of distance between satellite microphones and base unit utilizing captured audio, and/or estimation of satellite microphone orientation utilizing captured audio. Multiple sound source localization results are combined to enhance sound source localization and/or active speaker detection accuracy.

Abstract: An audio start service method for enabling and scheduling ad hoc distributed meetings. Only a short (in some embodiments less than or equal to about 32 bits) unique device identification is needed to enable distributed meeting devices participating in the meeting to rendezvous at a common rendezvous network address. Once the participants know the unique meeting network address they can take part in the meeting, while others can join or leave the meeting. The data string is each device's unique identification that is encoded into an inaudible watermark and continuously exchanged between devices over the telephone network. A first distributed meeting device requests a network address from a distributed meeting server. This unique meeting network address then is sent to an audio start service that identifies “buddies” of the first device and sends out meeting invitations and the network address to other devices so they can join the meeting.

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: Eye gaze reduction may be provided. First, a location of a near-end camera relative to a near-end screen may be determined. Next, based upon the determined location of the near-end camera, a location may be determined for a video window on the near-end screen. The determined location for the video window may be configured to reduce an eye gaze error in a near-end image transmitted to a far-end device from the near-end camera. Then video data from a far-end camera corresponding to the far-end device may be received and rendered in the video window at the determined location for the video window on the near-end screen.

Abstract: Speakers are identified based on sound origination detection through use of infrared detection of satellite microphones, estimation of distance between satellite microphones and base unit utilizing captured audio, and/or estimation of satellite microphone orientation utilizing captured audio. Multiple sound source localization results are combined to enhance sound source localization and/or active speaker detection accuracy.

Abstract: A region of interest may be determined using any or all of sound source location, multi-person detection, and active speaker detection. An weighted mean may be determined using the region of interest and a set of backlight weight regions, or, only the set of backlight weight regions if a region of interest could not be found. The image mean is compared to a target value to determine if the image mean is greater than or less than the target value within a predetermined threshold. If the image mean is greater than the predetermined target value and predetermined threshold value, the gain and exposure are decreased. If the image mean is lesser than the predetermined target value minus the predetermined threshold value, the gain and exposure are decreased.