This disclosure describes an apparatus and method of an embodiment of an invention that is improves Direction of Arrival (DOA) determinations. This embodiment of the apparatus includes a plurality of microphones coupled together as a microphone array used for beamforming, the plurality of microphones are positioned at predetermined locations and produce audio signals to be used to form a directional pickup pattern; a processor, memory, storage, and a power supply operably coupled to the microphone array, the processor configured to execute the following steps: processing an algorithm for a Direction of Arrival (DOA) determination; supplemental processing that improves the DOA processing.

A method for audio beam steering, tracking, and audio effects for an immersive reality application is provided. The method includes receiving, from an immersive reality application, a first audio waveform from a first acoustic source to provide to a user of a headset, identifying a perceived direction for the first acoustic source relative to the headset based on a location of the first acoustic source, and providing, to a first speaker in a client device, an audio signal including the first audio waveform, wherein the audio signal includes a time delay and an amplitude of the first audio waveform based on the perceived direction. A non-transitory, computer-readable medium storing instructions which, when executed by a processor, cause a system to perform the above method, and the system, are also provided.

A method to assess user condition for wearable devices using electromagnetic sensors is provided. The method includes receiving a signal from an electromagnetic sensor, the signal being indicative of a health condition of a user of a wearable device, selecting a salient attribute from the signal, and determining, based on the salient attribute, the health condition of the user of the wearable device. A non-transitory, computer-readable medium storing instructions which, when executed by a processor, cause a system to perform the above method, and the system, are also provided.

An electronic module is provided. The electronic module includes a first transducer and a second transducer. The first transducer is configured to radiate a first ultrasonic wave. The second transducer is configured to radiate a second ultrasonic wave. The first transducer and the second transducer are disposed on noncoplanar surfaces.

Techniques and systems are described for generating and using a sound localization model. A described technique includes obtaining for a building a sound sensor map indicating locations of first and second sound sensor devices in respective first and second rooms of the building; causing an autonomous device to navigate to the first room and to emit, during a time window, sound patterns at one or more frequencies within the first room; receiving sound data including first and second sound data respectively from the first and second sound sensor devices that are observed during the time window; and generating and storing a sound localization model based on the sound sensor map, autonomous device location information, and the received sound data, the model being configured to compensate for how sounds travels among rooms in at least a portion of the building such that an origin room of a sound source is identifiable.

Described is a device for the reproduction of three-dimensional sound, in particular headphones, including a pair of specular pads, having a shape such as to substantially form a portion of geoid or a hemisphere where each pad defines a concave inner surface having a plurality of recesses distributed according to a predetermined distribution. The device includes a plurality of loudspeakers, designed for sound reproduction and housed in these recesses. The device also includes a control unit, connected to the plurality of loudspeakers, configured to perform an analysis of a digital sound source and to determine a sound reproduction configuration of the loudspeakers as a function of the analysis of the sound source.

A microphone array system, comprises N microphones, including a first microphone . . . a Nth microphone, wherein N is a natural number greater than 2. Each of the N microphones is provided with: an acoustic transducer for picking up a sound signal and converting the sound signal into an electric signal; a voice activation detector, connected to a corresponding acoustic transducer, and configured to perform a voice activation detection on the electric signal and form an activation signal; a buffer memory, connected to the acoustic transducer, and configured to store a 1/N electric signal of a predetermined segment; a sound wire interface, connected to a corresponding acoustic transducer, the buffer memory, and the voice activation detector, wherein the sound wire interface is connected to an external master chip via a sound wire bus for outputting the activation signal to the external master chip.

Techniques for speech processing using a deep neural network (DNN) based acoustic model front-end are described. A new modeling approach directly models multi-channel audio data received from a microphone array using a first model (e.g., multi-geometry/multi-channel DNN) that is trained using a plurality of microphone array geometries. Thus, the first model may receive a variable number of microphone channels, generate multiple outputs using multiple microphone array geometries, and select the best output as a first feature vector that may be used similarly to beamformed features generated by an acoustic beamformer. A second model (e.g., feature extraction DNN) processes the first feature vector and transforms it to a second feature vector having a lower dimensional representation. A third model (e.g., classification DNN) processes the second feature vector to perform acoustic unit classification and generate text data. The DNN front-end enables improved performance despite a reduction in microphones.

This disclosure relates to speakers and more specifically to an array speaker for distributing music uniformly across a room. A number of audio drivers can be radially distributed within a speaker housing so that an output of the drivers is distributed evenly throughout the room. In some embodiments, the exit geometry of the audio drivers can be configured to bounce off a surface supporting the array speaker to improve the distribution of music throughout the room. The array speaker can include a number of vibration isolation elements distributed within a housing of the array speaker. The vibration isolation elements can be configured reduce the strength of forces generated by a subwoofer of the array speaker.

A sound collecting apparatus includes a base of a substantially spherical body and a plurality of microphones provided on the base, a number of the microphones having a predetermined constraint, the plurality of microphones being alternately arranged vertically relative to a horizontal plane including a center of the substantially spherical body in order to improve resolution in a horizontal direction.