Polycom, Inc.

Plantronics, Inc.

Picturetel Corporation

Hewlett-packard Development Company, L.p.

Peter L Chu

Yibo Liu

Jinwei Feng

Kwan Kin Truong

Michael Kenoyer

Richard Gene Washington

Thao D Hovanky

Denton L Simpson

Scott H Wakefield

Steven L Potts

Eric David Elias

Christopher Ramm

Wayne Grosvenor Dunlap

Robert W Spaller

Xiangdong Wang

Tom Eagan

Jonathan Gallmeier

Zhemin Tu

Alain Elon Nimri

Jeffrey C Rodman

Edmund S Thompson

Krishna Sai

Stephen Paul Schaefer

Stephen C Botzko

Michael Pocino

Jacob T Meyberg Guzman

Jesse Coleman

Hong Wang

Jim McGroddy

William F Barton

David A Bryan

Anthony Martin Duys

Yong Yan

John C Baumhauer, Jr

Larry Allen Marcus

Youssef Saleh

Erwin Goesnar

Jian David Wang

Uri Avni

Varun Ajay Kulkarni

John Paul Spearman

Martin G Sexton

Andrew Stewart Lochbaum

Niall Deloughry

Ami Noy

John Allen

Kyle Brookshire

Brant Martin Helf

Minjie Xie

Cody Schnacker

Greg Pelton

John Dietz

Greg Goldfarb

Steve Potts

Wendi Beth Rabiner

Gary Brown

Chad Terry

Dan Paquette

Richard Kos

Jay McArdle

Greg Godfarb

Andrew Lochbaum

Feng Jinwei

Wayne Dunlap

Michael A Pocino

A method includes, during a teleconference between a first audio input/output device and a second audio input/output device, receiving, at an analysis and response device, a signal indicating a spoken command, the spoken command associated with a command mode. The method further includes, in response to receiving the signal, generating, at the device, a reply message based on the spoken command, the reply message to be output to one or more devices selected based on the command mode. The one or more devices includes the first audio input/output device, the second audio input/output device, or a combination thereof.

Responding to a spoken command in a communication session

A method and apparatus for capturing audio including a ceiling mountable second-order differential microphone module. The module including a solid planar baffle having a generally centered aperture, at least one mounting foot to suspend the solid planar baffle approximately parallel with a rear reflecting plane and to space the solid planar baffle at a predetermined distance below the rear reflecting plane, a differential microphone sealably coupled to the planar baffle with a first side of the differential microphone acoustically exposed to an area above the planar baffle and a second side of the differential microphone acoustically exposed to an area below the planar baffle, and a mounting means for mounting the solid rear reflecting panel to the room ceiling.

Distributed network of ceiling image-derived directional microphones

A videoconferencing system includes a camera acquiring image data and a microphone array acquiring audio data. Image data is used in conjunction with sound source localization (SSL) data to locate a talker depicted in the image data. SSL processes the audio data and determines SSL pan angle values indicative of an estimated direction of a sound. Columns of pixels in an image are associated with bins. A bin count is incremented for each SSL pan angle value of the audio data that falls within a given bin. A bounding box in the image data is determined that encompasses a face depicted in the image data. A range of pixels is determined for the bounding box, such as extending from a leftmost column to a rightmost column. The bin with the highest bin count that also overlaps a range of pixels for a bounding box is deemed to contain the talker.

Face detection guided sound source localization pan angle post processing for smart camera talker tracking and framing

A method may include obtaining a plurality of training samples with a plurality of classifications that include a first classification and a second classification, training an initial tree with an initial set of training samples selected from the plurality of training samples using an initial set of feature values extracted from the set of training samples, and, in response to determining that the initial tree incorrectly classified the initial set of training samples at an output node of the initial tree, training a subsequent tree using a subsequent set of feature values extracted from a subsequent set of training samples.

Decision tree training with difference subsets of training samples based on a plurality of classifications

Replying to a spoken command

Determining the angle of sound relative to the centerline of a microphone array. The angle of the centerline of a camera field-of-view (FoV) and the angle of the camera FoV is determined. Knowing the angle from the centerline of the microphone array of the particular sound and then the angle of the centerline of the camera FoV and angles of the camera FoV allows a determination if the sound is inside the FoV of the camera. If so, the microphones are unmuted. If not, the microphones are muted. As the camera zooms or pans, the changes in camera FoV and centerline angle are computed and used with the sound angle, so that the muting and unmuting occurs automatically as the camera zoom and pan angle change.

Camera-view acoustic fence

A method for hybrid noise suppression includes receiving a processed audio signal from an audio device. The processed audio signal results from a partial audio processing performed on a noisy audio input signal. The method further includes predicting a noise suppression parameter using a neural network model operating on the processed audio signal and generating a noise-suppressed audio signal from the processed audio signal, using the noise suppression parameter. The method further includes generating a noise-suppressed audio output signal from the noise-suppressed audio signal using an additional audio processing and outputting the noise-suppressed audio output signal.

Hybrid noise suppression for communication systems

An audio device including a housing having a side facing outwardly of the housing, the housing further having a first mounting position disposed on the side. The side has a first portion and a second portion, the first portion opposite the second portion relative to the first mounting position. The audio device also includes a first omnidirectional microphone disposed on the first portion. The audio device also includes a second microphone disposed on the first mounting position. The second microphone may be a second-order microphone. The second-order microphone has a first-order microphone disposed within a first platform mounted a distance from the first mounting position. The audio device also includes a first speaker disposed on the second portion. The first speaker is further disposed such that an audio output of the first speaker falls within a null of the second microphone.

Second-order gradient microphone system with baffles for teleconferencing

Multiple cameras in a conference room, each pointed in a different direction and including a microphone array to perform sound source localization (SSL). The SSL is used in combination with the video image to identify the speaker from among multiple individuals that appear in the video image. Neural network or machine learning processing is performed on the identified speaker to determine the quality of the front or facial view of the speaker. The best view of the speaker's face from the various cameras is selected to be provided to the far end. If no view is satisfactory, a default view is selected and that is provided to the far end. The use of the SSL allows selection of the proper individual from a group of individuals in the conference room, so that only the speaker's head is analyzed for the best facial view and then framed for transmission.

Intelligent multi-camera switching with machine learning

A method for hybrid noise suppression. The method involves obtaining a noisy audio input signal, generating a noise-suppressed audio output signal by performing a combination of a noise spectrum estimate-based noise suppression and a machine learning-based noise suppression, and outputting the noise-suppressed audio output signal.

Hybrid noise suppression

A video conferencing device for video conferencing between at least one local participant and a remote participant includes a video camera, a microphone array, and a speaker tracker. The video camera provides a local video input signal. The microphone array provides a local audio input signal. The speaker tracker is configured to identify a local speaker from the at least one local participant using a sound source localizer. The video conferencing device processes the local video input signal without the local speaker, based on the video conferencing device receiving a signal from a computing system, the signal dependent on a loopback audio output signal indicating that the remote participant is speaking.

Method and system for controlling speaker tracking in a video conferencing system

A method for hybrid noise suppression involves receiving a first processed audio signal and a second processed audio signal from an audio device. The first processed audio signal results from a comprehensive audio processing including a noise spectrum estimate-based noise suppression performed on a noisy audio input signal obtained by the audio device. The second processed signal results from a partial audio processing excluding the noise spectrum estimate-based noise suppression performed on the noisy audio input signal. The method further involves temporally aligning the second processed audio signal with the first processed audio signal, predicting a noise suppression parameter using a neural network model operating on the second processed audio signal after the temporal alignment, generating a noise-suppressed audio output signal from the first processed audio signal after the temporal alignment using the noise suppression parameter, and outputting the noise-suppressed audio output signal.

PTP timestamps are obtained and correlated to internal audio time and timestamps. This allows Ethernet/IP audio devices to be closely aligned with local digital audio devices to allow improved AEC operations. By performing repetitive PTP timestamps based on local audio time, drift between PTP time and local audio time is determined and corrected. By performing the PTP to local audio time operations on each independent Ethernet network, the Ethernet/IP audio devices can be split between independent LANs. If some local digital audio inputs formed from analog inputs are not aligned with other local digital audio inputs, signals can be provided in analog format and audio samples of the signals can be correlated to local audio time. With correlations performed as necessary based on the various audio inputs in use, high quality AEC operations are performed.

PTP-based audio clock synchronization and alignment for acoustic echo cancellation in a conferencing system with IP-connected cameras, microphones and speakers

A videoconferencing system has a videoconferencing unit that use portable devices as peripherals for the system. The portable devices obtain near-end audio and send the audio to the videoconferencing unit via a wireless connection. In turn, the videoconferencing unit sends the near-end audio from the loudest portable device along with near-end video to the far-end. The portable devices can control the videoconferencing unit and can initially establish the videoconference by connecting with the far-end and then transferring operations to the videoconferencing unit. To deal with acoustic coupling between the unit's loudspeaker and the portable device's microphone, the unit uses an echo canceller that is compensated for differences in the clocks used in the A/D and D/A converters of the loudspeaker and microphone.

Pairing devices in conference using ultrasonic beacon and subsequent control thereof

The amount of far-field noise transmitted by a primary communication device in an open-plan office environment is reduced by defining an acoustic perimeter of reference microphones around the primary device. Reference microphones generate a reference audio input including far-field noise in the proximity of the primary device. The primary device generates a main audio input including the voice of the primary speaker as well as background noise. Reference audio input is compared to main audio input to identify the background noise portion of the main audio signal. A noise reduction algorithm suppresses the identified background noise in the main audio signal. The one or more reference microphones defining the acoustic perimeter may be included in separate microphone devices placed in proximity to the main desktop phone, microphones within other nearby desktop telephone devices, or a combination of both types of devices.

Acoustic perimeter for reducing noise transmitted by a communication device in an open-plan environment

Growing community of inventors

Lexington, MA, United States of America

Peter L Chu