公开(公告)号：US10074380B2

公开(公告)日：2018-09-11

申请号：US15227885

申请日：2016-08-03

Applicant: Apple Inc.

Inventor： Jason Wung ,  Ramin Pishehvar ,  Daniele Giacobello ,  Joshua D. Atkins

IPC: G10L21/02 ,  G10L21/0232 ,  G10L25/30 ,  G10L25/87 ,  G10L21/0208

CPC classification number: G10L21/0232 ,  G10L25/30 ,  G10L25/87 ,  G10L2021/02082

Abstract: Method for performing speech enhancement using a Deep Neural Network (DNN)-based signal starts with training DNN offline by exciting a microphone using target training signal that includes signal approximation of clean speech. Loudspeaker is driven with a reference signal and outputs loudspeaker signal. Microphone then generates microphone signal based on at least one of: near-end speaker signal, ambient noise signal, or loudspeaker signal. Acoustic-echo-canceller (AEC) generates AEC echo-cancelled signal based on reference signal and microphone signal. Loudspeaker signal estimator generates estimated loudspeaker signal based on microphone signal and AEC echo-cancelled signal. DNN receives microphone signal, reference signal, AEC echo-cancelled signal, and estimated loudspeaker signal and generates a speech reference signal that includes signal statistics for residual echo or for noise. Noise suppressor generates a clean speech signal by suppressing noise or residual echo in the microphone signal based on speech reference signal. Other embodiments are described.

公开(公告)号：US20250104687A1

公开(公告)日：2025-03-27

申请号：US18895319

申请日：2024-09-24

Applicant: Apple Inc.

Inventor： Christopher C. Painter ,  Axit H. Patel ,  Joshua D. Atkins ,  Moshe H. Malkin ,  Nicholas C. Soldner ,  Robert D. Silfvast ,  Zhengrong Shang ,  Timo Birnschein ,  Qinghung Lee

IPC: G10K11/178

Abstract: Embodiments are disclosed for active cancellation of noise in motion sensor signals. In some embodiments, a method comprises: obtaining a motion sensor signal from a motion sensor; obtaining a reference signal indicative of parasitic vibration from a vibration source mechanically coupled to the motion sensor; generating, using an adaptive noise canceller, an estimate of the parasitic vibration; and using the estimated parasitic vibration to cancel the parasitic vibration from the motion sensor signal.

公开(公告)号：US12200458B1

公开(公告)日：2025-01-14

申请号：US18487534

申请日：2023-10-16

Applicant: Apple Inc.

Inventor： Ismael H. Nawfal ,  Joshua D. Atkins ,  Stephen J. Nimick ,  Guy C. Nicholson ,  Jason M. Harlow

IPC: H04R5/04 ,  H04R1/10 ,  H04R5/027 ,  H04R5/033

Abstract: Digital audio signal processing techniques used to provide an acoustic transparency function in a pair of headphones. A number of transparency filters can be computed at once, using optimization techniques or using a closed form solution, which are based on multiple re-seatings of the headphones and that are as a result robust for a population of wearers. In another embodiment, a transparency hearing filter of a headphone is computed by an adaptive system that takes into consideration the changing acoustic to electrical path between an earpiece speaker and an interior microphone of that headphone while worn by a user. Other embodiments are also described and claimed.

公开(公告)号：US20240312468A1

公开(公告)日：2024-09-19

申请号：US18605688

申请日：2024-03-14

Applicant: Apple Inc.

Inventor： Ismael H. Nawfal ,  Symeon Delikaris Manias ,  Mehrez Souden ,  Joshua D. Atkins

IPC: G10L19/008 ,  H04S7/00

CPC classification number: G10L19/008 ,  H04S7/30 ,  H04S2420/11

Abstract: A sound scene is represented as first order Ambisonics (FOA) audio. A processor formats each signal of the FOA audio to a stream of audio frames, provides the formatted FOA audio to a machine learning model that reformats the formatted FOA audio in a target or desired higher order Ambisonics (HOA) format, and obtains output audio of the sound scene in the desired HOA format from the machine learning model. The output audio in the desired HOA format may then be rendered according to a playback audio format of choice. Other aspects are also described and claimed.

公开(公告)号：US20240163609A1

公开(公告)日：2024-05-16

申请号：US18423933

申请日：2024-01-26

Applicant: Apple Inc.

Inventor： Tomlinson Holman ,  Christopher T. Eubank ,  Joshua D. Atkins ,  Soenke Pelzer ,  Dirk Schroeder

IPC: H04R5/027 ,  G10L19/16 ,  G10L21/0216 ,  H04R3/00 ,  H04R3/04 ,  H04R5/033 ,  H04R5/04

CPC classification number: H04R5/027 ,  G10L19/167 ,  G10L21/0216 ,  H04R3/005 ,  H04R3/04 ,  H04R5/033 ,  H04R5/04 ,  G10L2021/02082

Abstract: An audio device can sense sound in a physical environment using a plurality of microphones to generate a plurality of microphone signals. Clean speech can be extracted from microphone signals. Ambience can be extracted from the microphone signals. The clean speech can be encoded at a first compression level. The ambience can be encoded at a second compression level that is higher than the first compression level. Other aspects are also described and claimed.

公开(公告)号：US20220369030A1

公开(公告)日：2022-11-17

申请号：US17322539

申请日：2021-05-17

Applicant: Apple Inc.

Inventor： Mehrez Souden ,  Jason Wung ,  Ante Jukic ,  Ramin Pishehvar ,  Joshua D. Atkins

IPC: H04R3/04 ,  H04R3/00 ,  H04R5/04 ,  G10L21/0216 ,  G10L25/78

Abstract: A plurality of microphone signals can be captured with a plurality of microphones of the device. One or more echo dominant audio signals can be determined based on a pick-up beam directed towards one or more speakers of a playback device. Sound that is emitted from the one or more speakers and sensed by the plurality of microphones can be removed from plurality of microphone signals, by using the one or more echo dominant audio signals as a reference, resulting in clean audio.

公开(公告)号：US20210329381A1

公开(公告)日：2021-10-21

申请号：US17360825

申请日：2021-06-28

Applicant: Apple Inc.

Inventor： Tomlinson Holman ,  Christopher T. Eubank ,  Joshua D. Atkins ,  Soenke Pelzer ,  Dirk Schroeder

IPC: H04R5/027 ,  H04R5/033 ,  H04R5/04 ,  H04R3/00 ,  H04R3/04 ,  G10L19/16 ,  G10L21/0216

Abstract: An audio device can sense sound in a physical environment using a plurality of microphones to generate a plurality of microphone signals. Clean speech can be extracted from microphone signals. Ambience can be extracted from the microphone signals. The clean speech can be encoded at a first compression level. The ambience can be encoded at a second compression level that is higher than the first compression level. Other aspects are also described and claimed.

公开(公告)号：US10978086B2

公开(公告)日：2021-04-13

申请号：US16517400

申请日：2019-07-19

Applicant: Apple Inc.

Inventor： Jason Wung ,  Sarmad Aziz Malik ,  Ashrith Deshpande ,  Ante Jukic ,  Joshua D. Atkins

IPC: G10L21/0208 ,  G10K11/178 ,  G10L21/0216

Abstract: An echo canceller is disclosed in which audio signals of the playback content received by one or more of the microphones from a loudspeaker of the device may be used as the playback reference signals to estimate the echo signals of the playback content received by a target microphone for echo cancellation. The echo canceller may estimate the transfer function between a reference microphone and the target microphone based on the playback reference signal of the reference microphone and the signal of the target microphone. To mitigate near-end speech cancellation at the target microphone, the echo canceller may compute a mask to distinguish between target microphone audio signals that are echo-signal dominant and near-end speech dominant. The echo canceller may use the mask to adaptively update the transfer function or to modify the playback reference signal used by the transfer function to estimate the echo signals of the playback content.

公开(公告)号：US20210020188A1

公开(公告)日：2021-01-21

申请号：US16517400

申请日：2019-07-19

Applicant: Apple Inc.

Inventor： Jason Wung ,  Sarmad Aziz Malik ,  Ashrith Deshpande ,  Ante Jukic ,  Joshua D. Atkins

IPC: G10L21/0208 ,  G10K11/178

Abstract: An echo canceller is disclosed in which audio signals of the playback content received by one or more of the microphones from a loudspeaker of the device may be used as the playback reference signals to estimate the echo signals of the playback content received by a target microphone for echo cancellation. The echo canceller may estimate the transfer function between a reference microphone and the target microphone based on the playback reference signal of the reference microphone and the signal of the target microphone. To mitigate near-end speech cancellation at the target microphone, the echo canceller may compute a mask to distinguish between target microphone audio signals that are echo-signal dominant and near-end speech dominant. The echo canceller may use the mask to adaptively update the transfer function or to modify the playback reference signal used by the transfer function to estimate the echo signals of the playback content.

公开(公告)号：US10798511B1

公开(公告)日：2020-10-06

申请号：US16378438

申请日：2019-04-08

Applicant: Apple Inc.

Inventor： Jonathan D. Sheaffer ,  Juha O. Merimaa ,  Jason Wung ,  Martin E. Johnson ,  Peter A. Raffensperger ,  Joshua D. Atkins ,  Symeon Delikaris Manias ,  Mehrez Souden

IPC: H04S5/00 ,  G10K11/178 ,  H04R1/40

Abstract: Processing input audio channels for generating spatial audio can include receiving a plurality of microphone signals that capture a sound field. Each microphone signal can be transformed into a frequency domain signal. From each frequency domain signal, a direct component and a diffuse component can be extracted. The direct component can be processed with a parametric renderer. The diffuse component can be processed with a linear renderer. The components can be combined, resulting in a spatial audio output. The levels of the components can be adjusted to match a direct to diffuse ratio (DDR) of the output with the DDR of the captured sound field. Other aspects are also described and claimed.