Device-independent audio for electronic devices
AssigneeApple Inc.
InventorsMehrez SOUDEN, Jason WUNG, Jonathan D. SHEAFFER, Joshua D. ATKINS, Siyuan YUAN
Life of this patent
Estimating the term…
Abstract
Aspects of the subject technology relate to providing device-independent audio for electronic devices. In one or more implementations, microphone data captured by multiple microphones at an electronic device may be provided to a device-specific audio generalizer at the electronic device. The device-specific audio generalizer may utilize device specific information to generalize the microphone data to form device-independent audio data. The device-independent audio data may then be provided to a device-independent machine learning model at the electronic device or another electronic device for further processing.
Claims20
A method, comprising:
- obtaining microphone data, generated by a plurality of microphones of an electronic device responsive to an audio input to the plurality of microphones, wherein the plurality of microphones are disposed at a plurality of respective locations on or in the electronic device, and wherein the microphone data includes a first representation of at least a portion of the audio input, the first representation including at least one feature corresponding to the plurality of respective locations of the plurality of microphones;
- generating, at the electronic device based on the microphone data, a second representation of at least the portion of the audio input, the second representation independent of the plurality of respective locations of the plurality of microphones;
- providing the second representation as an input to a machine learning model;
- obtaining, responsive to providing the second representation as the input, at least one audio feature of the audio input as an output of the machine learning model;
- and
- providing the at least one audio feature to at least one of:
- another electronic device or an audio-based process at the electronic device.
A non-transitory computer-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to:
- obtain microphone data, generated by a plurality of microphones of an electronic device responsive to an audio input to the plurality of microphones, wherein the plurality of microphones are disposed at a plurality of respective locations on or in the electronic device, and wherein the microphone data includes a first representation of at least a portion of the audio input, the first representation including at least one feature corresponding to the plurality of respective locations of the plurality of microphones;
- generate, at the electronic device based on the microphone data, a second representation of at least the portion of the audio input, the second representation independent of the plurality of respective locations of the plurality of microphones;
- provide the second representation as an input to a machine learning model;
- obtain, responsive to providing the second representation as the input, at least one audio feature of the audio input as an output of the machine learning model;
- and
- provide the at least one audio feature to at least one of:
- another electronic device or an audio-based process at the electronic device.
A device, comprising;
- a plurality of microphones disposed at a plurality of respective locations on or in the device;
- a memory;
- and
- one or more processors configured to:
- obtain microphone data, generated by the plurality of microphones responsive to an audio input to the plurality of microphones, and wherein the microphone data includes a first representation of at least a portion of the audio input, the first representation including at least one feature corresponding to the plurality of respective locations of the plurality of microphones;
- generate, based on the microphone data, a second representation of at least the portion of the audio input, the second representation independent of the plurality of respective locations of the plurality of microphones;
- provide the second representation for input to a machine learning model;
- obtain, responsive to providing the second representation for the input, at least one audio feature of the audio input as an output of the machine learning model;
- and
- provide the at least one audio feature to at least one of:
- another electronic device or an audio-based process at the electronic device.
Dependencies are inferred from the claim text.