Abstract: A conference recording method includes: A multipoint control unit determines, based on feature information of a person, an audio video bitstream that needs to be recorded, from audio video bitstreams sent by site terminals. The feature information includes picture information or sound information. The multipoint control unit sends, to a recording server, the audio video bitstream that needs to be recorded, so that the recording server performs conference recording. The feature information of the person is used to implement automatic screening on the audio video bitstream that need to be recorded.

Abstract: An imaging system including: first camera and second camera; depth-mapping means; gaze-tracking means; and processor configured to: generate depth map of real-world scene; determine gaze directions of first eye and second eye; identify line of sight and conical region of interest; determine optical depths of first object and second object present in conical region; determine one of first camera and second camera having lesser occlusion in real-world scene; adjust optical focus of one of first camera and second camera to focus on one of first object and second object having greater optical depth, and adjust optical focus of another of first camera and second camera to focus on another of first object and second object; and capture first image(s) and second image(s) using adjusted optical focuses of cameras.

Abstract: A display device includes a head including a display formed on a front surface thereof, a circumference having a pair of long sides and a pair of short sides, and one or more first speakers provided on a left short side and one or more second speakers provided on a right short side of the display and configured to be pivotable between a landscape mode in which the long sides are in a horizontal state and a portrait mode in which the long sides are in a vertical state, a sensor configured to detect pivot of the head, and a processor configured to determine a pivot state indicating whether the head is in the landscape mode or the portrait mode based on a result of detection and switch sound signals output by the first speakers and the second speakers when the pivot state of the head is switched.

Abstract: The invention relates to a videoconferencing system 1, comprising: a display screen 10, for displaying an image Ie(ti) containing N images Iint(k)(ti); a camera 20, for acquiring an image Ic(tj); a single-pixel-imager-employing optical device suitable for determining N images Ico(k)(tj) on the basis of sub-matrices SMimp(k)(tj) comprising: an optical source 31, suitable for irradiating an ocular portion Po(tj) of the face of the user; a matrix of single-pixel imagers that are suitable for reconstructing a correction image Ico(k)(tj) on the basis of the light beam reflected by the ocular portion Po(tj); a processing unit 40, suitable for: determining, in each image Iint(k)(ti) of the image Ie(ti), a target point Pc(k)(tj), then selecting N sub-matrices SMimp(k)(tj) each centred on a target point Pc(k)(tj); correcting the image Ic(tj), by replacing a region of the image Pc(tj) representing the ocular portion Po(tj) with the N images Ico(k)(tj).

Abstract: An information processing apparatus according to the present disclosure includes an executing unit that associates a head-related transfer function corresponding to a user with an identifier that identifies equipment that is used by the user and a providing unit that provides the head-related transfer function and the identifier associated with the head-related transfer function to a providing destination to which the head-related transfer function corresponding to the user is provided.

Abstract: A method for associating perception data with a first content, which is implemented by a processor includes: triggering at least one capture using a capturing device in the direction of at least one individual, referred to as an observer, consulting the first content, the result of the capture being designated as second content; analyzing distinctive elements of the second content and transposing the distinctive elements into perception data; and associating the perception data with the first content.

Abstract: An audio signal processing method, includes acquiring a first distance between a current position and an initial position of a mobile device, and a second distance between the current position of the mobile device and a wearable device. Determining a first deflection angle according to the first distance, the second distance and the initial distance between the mobile device and the wearable device. Acquiring a second deflection angle of the wearable device reflecting a posture change. Determining relative position information between the mobile device and the wearable device according to the first deflection angle, the second deflection angle and the second distance and processing an audio signal based on the relative position information to obtain a playing audio played by the wearable device.

Abstract: A system may obtain a set of features characterizing a segment of inertial measurement unit (IMU) data generated by an IMU of an ear-wearable device. The system may apply a machine learning model (MLM) that takes the features characterizing the segment of the IMU data as input. The system may determine, based on output values produced by the MLM, whether a user of the ear-wearable device has potentially been subject to physical abuse. The system may then perform an action in response to determining that the user of the ear-wearable device has potentially been subject to physical abuse.

Abstract: An image acquisition system is disclosed. The image acquisition system includes: an object area configured to form an image on an image side; a condenser lens configured to converge light from the object area, the condenser lens being located on a light path of the object area; a color filter configured to filter the light collected by the condenser lens to obtain single wavelength of light, according to a forward direction of the light, the color filter being placed in front of the condenser lens; and an image sensor configured to receive the image on an imaging plane position of an image space, the image sensor being placed in front of the imaging plane position according to the forward direction of the light. The matrix image acquisition system and the matrix image projection system including the image acquisition system are also disclosed.

Abstract: Method and devices for testing a headphone with increased sensation are provided. The headphone can filter and amplify low frequency audio signals, which are then sent to a haptic device in the headphone. The haptic device can cause bass sensations at the top of the skull and at both ear cups. The testing system can evaluate the haptic and acoustic sensations produced by the headphone to evaluate if they have been properly assembled and calibrate the headphones if necessary.

Abstract: An apparatus and method of rendering audio. A binaural signal is split on an amplitude weighting basis into a front binaural signal and a rear binaural signal, based on perceived position information of the audio. In this manner, the front-back differentiation of the binaural signal is improved.

Abstract: The present disclosure is related to a method and system for a room calibration in a speaker system using an internal microphone. The method comprises calculating an impulse response of a sound signal received at an internal microphone from at least one speaker, and performing the room calibration based on the calculated impulse response.

Abstract: Joint noise and echo suppression may be performed for enhancing two-way audio communications. Audio data is captured at a communication device and audio data transmitted to the communication device from another communication device are used as input features to a trained machine learning model that uses the transmitted audio data as a reference signal to eliminate residual echo in the captured audio data when also suppressing noise in the captured audio data.

Abstract: Methods and systems for performing at least one audio activity (e.g., conducting a phone call or playing music or other audio content) in an environment including by determining an estimated location of a user in the environment in response to sound uttered by the user (e.g., a voice command), and controlling the audio activity in response to determining the estimated user location. The environment may have zones which are indicated by a zone map and estimation of the user location may include estimating in which of the zones the user is located. The audio activity may be performed using microphones and loudspeakers which are implemented in or coupled to smart audio devices.

Abstract: An online video distribution support method is executed by an online video distribution support system including one or more computers connected to communicate with a plurality of viewer terminals used by viewers who view an online video. The online video distribution support method includes: displaying a video distribution screen including a material designated by a distributor that distributes the online video; acquiring information on a line-of-sight position of each of the viewers on the video distribution screen from each of the viewer terminals; detecting and acquiring a line-of-sight position of the distributor on the video distribution screen by using a captured image obtained by capturing the distributor; and calculating and outputting a degree of interest of each of the viewers based on the line-of-sight position of the corresponding viewer and the line-of-sight position of the distributor.

Abstract: Disclosed herein are wearable devices, their configurations, and methods of operation that use self-mixing interferometry signals of a self-mixing interferometry sensor to recognize user inputs. The user inputs may include voiced commands or silent gesture commands. The devices may be wearable on the user's head, with the self-mixing interferometry sensor configured to direct a beam of light toward a location on the user's head. Skin deformations or vibrations at the location may be caused by the user's speech or the user's silent gestures and recognized using the self-mixing interferometry signal. The self-mixing interferometry signals may be used for bioauthentication and/or audio conditioning of received sound or voice inputs to a microphone.

Abstract: A smart speaker power controller may be configured to receive power conforming to one of a plurality of power modes from an input power source. The power controller may be further configured to communicate the power mode to at least one component of a processing system or at least one component of an audio system for operating the smart speaker according to the received power mode, including determining a current limit of a power converter; determining a shutdown voltage threshold and safely shutting down the smart speaker if the input voltage falls below the threshold, and/or modifying audio operation of the smart speaker in response to the power mode. The smart speaker can further include an audio power supply controller configured to monitor energy required to reproduce an audio signal and to servo a power supply voltage provided to an audio amplifier in response to this energy level.

Abstract: An apparatus for generating loudspeaker signals includes an object metadata processor configured to receive metadata, to calculate a second position of the audio object depending on the first position of the audio object and on a size of a screen if the audio object is indicated in the metadata as being screen-related, to feed the first position of the audio object as the position information into the object renderer if the audio object is indicated in the metadata as being not screen-related, and to feed the second position of the audio object as the position information into the object renderer if the audio object is indicated in the metadata as being screen-related. The apparatus further includes an object renderer configured to receive an audio object and to generate the loudspeaker signals depending on the audio object and on position information.

Abstract: A device (100) includes a display (110) itself including pixel groups. A bottom and sides of each of the pixel groups are covered with non-reflective material. The pixel groups are electrically coupled together with transparent conductive interconnections. A camera (122) is located beneath the display and the camera is configured to sense light that passes through the display.

Abstract: Higher Order Ambisonics represents three-dimensional sound independent of a specific loudspeaker set-up. However, transmission of an HOA representation results in a very high bit rate. Therefore, compression with a fixed number of channels is used, in which directional and ambient signal components are processed differently. The ambient HOA component is represented by a minimum number of HOA coefficient sequences. The remaining channels contain either directional signals or additional coefficient sequences of the ambient HOA component, depending on what will result in optimum perceptual quality. This processing can change on a frame-by-frame basis.