公开(公告)号：US20230162750A1

公开(公告)日：2023-05-25

申请号：US17531687

申请日：2021-11-19

Applicant: Apple Inc.

Inventor： Prateek MURGAI ,  Ashrith DESHPANDE

IPC: G10L21/0208 ,  G10L25/78 ,  G10L15/22 ,  H04R1/40

CPC classification number: G10L21/0208 ,  G10L25/78 ,  G10L15/22 ,  H04R1/406

Abstract: Aspects of the subject technology provide for identifying a portion of one or more audio signals from one or more microphones of an electronic device that correspond to a sound-generating component of the electronic device. The identification of the portion of the audio signals may be based on a near-field impulse response for the sound-generating component and the one or more microphones. The electronic device may then be operated based on the audio signals and the identified portion of the audio signals. The sound-generating component may be a speaker, and operating the electronic device based on the audio signals and the identified portion of the audio signals may include performing a residual echo suppression by removing the identified portion of the audio signals from the audio signals, and transmitting, storing, and/or otherwise processing the residual echo suppressed audio signals.

公开(公告)号：US20210074316A1

公开(公告)日：2021-03-11

申请号：US16708296

申请日：2019-12-09

Applicant: Apple Inc.

Inventor： Mehrez SOUDEN ,  Ante JUKIC ,  Jason WUNG ,  Ashrith DESHPANDE ,  Joshua D. ATKINS

IPC: G10L25/81 ,  G10L25/18 ,  G10L21/0232 ,  G06K9/00 ,  G10L15/25 ,  G10L15/22 ,  G06N7/00 ,  G06N20/00

Abstract: A device implementing a system for processing speech in an audio signal includes at least one processor configured to receive an audio signal corresponding to at least one microphone of a device, and to determine, using a first model, a first probability that a speech source is present in the audio signal. The at least one processor is further configured to determine, using a second model, a second probability that an estimated location of a source of the audio signal corresponds to an expected position of a user of the device, and to determine a likelihood that the audio signal corresponds to the user of the device based on the first and second probabilities.