Meta Platforms Technologies, LLC

Facebook Technologies, LLC

Gm Global Technolgoy Operations, Inc.

Vladimir Tourbabin

Ravish Mehra

Jacob Ryan Donley

Antonio John Miller

Andrew Lovitt

Eli Tzirkel-Hancock

Nava K Balsam

Ilan Malka

Morteza Khaleghimeybodi

Philip Robinson

Vamsi Krishna Ithapu

Nils Thomas Fritiof Lunner

Peter Harty Dodds

Sharon Gannot

A device and/or method for storing one or more sound filters in a discretized pose space. The device determines that a microphone array during a first time period is in a first discrete pose of a plurality of discrete poses, wherein the plurality of discrete poses discretizes a pose space. The pose space includes at least an orientation component and may further include a translation component. The device retrieves a sound filter associated with the first discrete pose from a memory cache (e.g., for memoization). The device generates audio content using the sound filter and presents the audio content via a transducer array.

Memory recall of sound filter stored in association with a discrete pose for audio beamforming

A communication system provides audio content to one or more client devices capable of playing spatialized audio content. For example, the communication system receives audio content from a client device and transmits the audio content to other client devices to be played for users. The communication system dynamically modifies audio content transmitted to different client devices based on a payload including audio parameters (e.g., local area acoustic properties, an audiogram for a user, a head related transfer function for a user, etc.) received from a client device.

Modifying audio data transmitted to a receiving device to account for acoustic parameters of a user of the receiving device

An audio system presents enhanced audio content to a user of a headset. The audio system detects sounds from the local area, at least a portion of which originate from a human sound source. The audio system obtains a voice profile of an identifies human sound source that generates at least the portion of the detected sounds. Based in part on the voice profile, the audio system enhances the portion of the detected sounds that are generated by the human sound source to obtain enhanced audio. The audio system presents the enhanced audio to the user.

Social network based voice enhancement system

An electronic device localizes an audio source by normalizing an amplitude of an audio signal over a time period. The electronic device receives, from one or more microphones of the electronic device, signal(s) representative of audio emitted by an audio source over a time period. The electronic device estimates amplitudes of the signal(s) at a first time within the time period and at a second time within the time period, where the second time is different from the first time. The electronic device normalizes the amplitudes associated with the first and second times to generate normalized amplitudes. The electronic device determines a combined amplitude representative of the audio emitted by the audio source by combining the normalized amplitudes. The electronic device determines, based at least in part on the combined amplitude and motion of the electronic device, an estimated position of the audio source relative to the electronic device.

Audio source localization

A system and method for storing data samples in discrete poses and recalling the stored data samples for updating a sound filter. The system determines that a microphone array at a first time period is in a first discrete pose of a plurality of discrete poses, wherein the plurality of discrete poses discretizes a pose space. The pose space includes at least an orientation component and may further include a translation component. The system retrieves one or more historical data samples associated with the first discrete pose, generated from sound captured by the microphone array before the first time period, and stored in a memory cache (e.g., for memorization). The system updates a sound filter for the first discrete pose using the retrieved one or more historical data samples. The system generates and presents audio content using the updated sound filter.

Memory recall of historical data samples bucketed in discrete poses for audio beamforming

The disclosed computer-implemented method may include receiving a signal for each channel of an audio transducer array on a wearable device. The method may also include calculating a beamformed signal for each beam direction of a set of beamforming filters for the wearable device. Additionally, the method may include classifying a first beamformed signal from the calculated beamformed signals into a first class of sound and a second beamformed signal from the calculated beamformed signals into a second class of sound. The method may also include adjusting, based on the classifying, a gain of the first beamformed signal relative to the second beamformed signal. Furthermore, the method may include converting the beamformed signals into spatialized binaural audio based on a position of a user. Finally, the method may include transmitting the spatialized binaural audio to a playback device. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for classifying beamformed signals for binaural audio playback

A wearable device includes an audio system. In one embodiment, the audio system includes a sensor array that includes a plurality of acoustic sensors. When a user wears the wearable device, the audio system determines an acoustic transfer function for the user based upon detected sounds within a local area surrounding the sensor array. Because the acoustic transfer function is based upon the size, shape, and density of the user's body (e.g., the user's head), different acoustic transfer functions will be determined for different users. The determined acoustic transfer functions are compared with stored acoustic transfer functions of known users in order to authenticate the user of the wearable device.

Wearer identification based on personalized acoustic transfer functions

An eyewear device includes an audio system. In one embodiment, the audio system includes a microphone array that includes a plurality of acoustic sensors. Each acoustic sensor is configured to detect sounds within a local area surrounding the microphone array. For a plurality of the detected sounds, the audio system performs a direction of arrival (DoA) estimation. Based on parameters of the detected sound and/or the DoA estimation, the audio system may then generate or update one or more acoustic transfer functions unique to a user. The audio system may use the one or more acoustic transfer functions to generate audio content for the user.

Audio system for dynamic determination of personalized acoustic transfer functions

A headset generates an acoustic map that is a visual representation of sound pressure of sound within a local area. The acoustic map is displayed as a virtual object that is overlaid onto visual content being presented by the headset. Sound is adjusted in accordance with a command. The acoustic map is updated based on the adjusted sound, and the adjusted sound is presented and the updated acoustic map is presented.

Adjustment of acoustic map and presented sound in artificial reality systems

An audio system for a wearable device dynamically updates acoustic transfer functions. The audio system is configured to estimate a direction of arrival (DoA) of each sound source detected by a microphone array relative to a position of the wearable device within a local area. The audio system may track the movement of each sound source. The audio system may form a beam in the direction of each sound source. The audio system may identify and classify each sound source based on the sound source properties. Based on the DoA estimates, the movement tracking, and the beamforming, the audio system generates or updates the acoustic transfer functions for the sound sources.

Acoustic transfer function personalization using sound scene analysis and beamforming

One embodiment of the present application sets forth a computer-implemented method that includes receiving, from a first microphone, a first input acoustic signal, generating a first audio spectrum from at least the first input acoustic signal, wherein the first audio spectrum includes a set of time-frequency bins, and selecting a first time-frequency bin from the set based on a first local space-domain distance (LSDD) computed for the first time-frequency bin.

Techniques for selecting a direct path acoustic signal

One embodiment of the present application sets forth a computer-implemented method that includes receiving, from a first microphone, a first input acoustic signal, generating a first audio spectrum from at least the first input acoustic signal, where the first audio spectrum includes a set of time-frequency bins, for each time-frequency bin included in the set of time-frequency bins, computing a weighted local space-domain distance (LSDD) spectrum value based on a portion of the first audio spectrum that is included in the time-frequency bin, generating a combined spectrum value based on a set of the weighted LSDD spectrum values computed for the set of time-frequency bins, and determining a first estimated direction of the first input acoustic signal based on the combined spectrum value.

Growing community of inventors

Sammamish, WA, United States of America

Vladimir Tourbabin