公开(公告)号：US11109173B2

公开(公告)日：2021-08-31

申请号：US16778634

申请日：2020-01-31

Applicant: Apple Inc.

Inventor： Bruce C. Po ,  Richard M. Powell ,  Aram M. Lindahl ,  Baptiste P. Paquier ,  Phillip A. Kamp

IPC: H04S7/00 ,  G06F3/16 ,  H04R1/40 ,  H04R3/04 ,  H04R3/12 ,  H04R5/04 ,  H04R29/00

Abstract: A system and method is described for determining whether a loudspeaker device has relocated, tilted, rotated, or changed environment such that one or more parameters for driving the loudspeaker may be modified and/or a complete reconfiguration of the loudspeaker system may be performed. In one embodiment, the system may include a set of sensors. The sensors provide readings that are analyzed to determine 1) whether the loudspeaker has moved since a previous analysis and/or 2) a distance of movement and/or a degree change in orientation of the loudspeaker since the previous analysis. Upon determining the level of movement is below a threshold value, the system adjusts previous parameters used to drive one or more of the loudspeakers. By adjusting previous parameters instead of performing a complete recalibration, the system provides a more efficient technique for ensuring that the loudspeakers continue to produce accurate sound for the listener.

公开(公告)号：US10764670B2

公开(公告)日：2020-09-01

申请号：US16395714

申请日：2019-04-26

Applicant: Apple Inc.

Inventor： Aram M. Lindahl

IPC: H04R1/10 ,  G10L19/00 ,  H04R1/40 ,  H04R3/00 ,  H04R3/12 ,  G06F3/01

Abstract: A system having a head-mounted display (HMD) mount and a mobile device, are described. A processor of the system can determine whether the mobile device is mounted on the HMD mount and handle an audio signal communicated from the mobile device to a wireless headphone based on whether the mobile device is mounted on the HMD mount. When the mobile device is not mounted on the HMD mount, the mobile device or the wireless headphone may operate in a first audio mode. When the mobile device is mounted on the HMD mount, the mobile device or the wireless headphone may operate in a second audio mode. The second audio mode can reduce audio signal latency between the mobile device and the wireless headphone and increase motion-to-sound quality. Other embodiments are also described and claimed.

公开(公告)号：US20190251974A1

公开(公告)日：2019-08-15

申请号：US16389697

申请日：2019-04-19

Applicant: Apple Inc.

Inventor： Sean A. Ramprashad ,  Harvey D. Thornburg ,  Arvindh Krishnaswamy ,  Aram M. Lindahl

IPC: G10L15/32 ,  G10L15/20

CPC classification number: G10L15/32 ,  G10L15/20

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

公开(公告)号：US10013981B2

公开(公告)日：2018-07-03

申请号：US14732711

申请日：2015-06-06

Applicant: Apple Inc.

Inventor： Sean A. Ramprashad ,  Harvey D. Thornburg ,  Arvindh Krishnaswamy ,  Aram M. Lindahl

IPC: G10L15/26 ,  G10L15/06 ,  G10L15/32 ,  G10L15/20

CPC classification number: G10L15/32 ,  G10L15/20

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

公开(公告)号：US09913022B2

公开(公告)日：2018-03-06

申请号：US15353308

申请日：2016-11-16

Applicant: Apple Inc.

Inventor： Sorin V. Dusan ,  Baptiste P. Paquier ,  Aram M. Lindahl

IPC: H04R1/10 ,  G10K11/178 ,  H04R3/00 ,  G10L21/0208 ,  G10L25/78 ,  G10L25/90

CPC classification number: H04R1/1083 ,  G10K11/178 ,  G10L21/0208 ,  G10L25/78 ,  G10L25/90 ,  G10L2021/02161 ,  H04R3/005 ,  H04R5/033 ,  H04R2420/07 ,  H04R2460/13

Abstract: Method of improving voice quality using a wireless headset with untethered earbuds starts by receiving first acoustic signal from first microphone included in first untethered earbud and receiving second acoustic signal from second microphone included in second untethered earbud. First inertial sensor output is received from first inertial sensor included in first earbud and second inertial sensor output is received from second inertial sensor included in second earbud. First earbud processes first noise/wind level captured by first microphone, first acoustic signal and first inertial sensor output and second earbud processes second noise/wind level captured by second microphone, second acoustic signal, and second inertial sensor output. First and second noise/wind levels and first and second inertial sensor outputs are communicated between the earbuds. First earbud transmits first acoustic signal and first inertial sensor output when first noise and wind level is lower than second noise/wind level. Other embodiments are described.

公开(公告)号：US09865265B2

公开(公告)日：2018-01-09

申请号：US14732715

申请日：2015-06-06

Applicant: Apple Inc.

Inventor： Sean A. Ramprashad ,  Harvey D. Thornburg ,  Arvindh Krishnaswamy ,  Aram M. Lindahl

IPC: G10L21/00 ,  G10L15/34 ,  G10L15/20 ,  G10L15/16 ,  G10L15/02 ,  G10L21/0216

CPC classification number: G10L15/34 ,  G10L15/16 ,  G10L15/20 ,  G10L2015/022 ,  G10L2021/02166

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

公开(公告)号：US20170127172A1

公开(公告)日：2017-05-04

申请号：US15353308

申请日：2016-11-16

Applicant: Apple Inc.

Inventor： Sorin V. Dusan ,  Baptiste P. Paquier ,  Aram M. Lindahl

IPC: H04R1/10 ,  G10L25/90 ,  G10L21/0208 ,  G10L25/78 ,  G10K11/178 ,  H04R3/00

CPC classification number: H04R1/1083 ,  G10K11/178 ,  G10L21/0208 ,  G10L25/78 ,  G10L25/90 ,  G10L2021/02161 ,  H04R3/005 ,  H04R5/033 ,  H04R2420/07 ,  H04R2460/13

Abstract: Method of improving voice quality using a wireless headset with untethered earbuds starts by receiving first acoustic signal from first microphone included in first untethered earbud and receiving second acoustic signal from second microphone included in second untethered earbud. First inertial sensor output is received from first inertial sensor included in first earbud and second inertial sensor output is received from second inertial sensor included in second earbud. First earbud processes first noise/wind level captured by first microphone, first acoustic signal and first inertial sensor output and second earbud processes second noise/wind level captured by second microphone, second acoustic signal, and second inertial sensor output. First and second noise/wind levels and first and second inertial sensor outputs are communicated between the earbuds. First earbud transmits first acoustic signal and first inertial sensor output when first noise and wind level is lower than second noise/wind level. Other embodiments are described.

公开(公告)号：US09524735B2

公开(公告)日：2016-12-20

申请号：US14170136

申请日：2014-01-31

Applicant: Apple Inc.

Inventor： Vasu Iyengar ,  Aram M. Lindahl

IPC: G10L25/84 ,  G10L25/78 ,  G10L21/0216

CPC classification number: G10L25/84 ,  G10L2021/02165 ,  G10L2025/786

Abstract: A method for adapting a threshold used in multi-channel audio voice activity detection. Strengths of primary and secondary sound pick up channels are computed. A separation, being a measure of difference between the strengths of the primary and secondary channels, is also computed. An analysis of the peaks in separation is performed, e.g. using a leaky peak capture function that captures a peak in the separation and then decays over time, or using a sliding window min-max detector. A threshold that is to be used in a voice activity detection (VAD) process is adjusted, in accordance with the analysis of the peaks. Other embodiments are also described and claimed.

Abstract translation: 一种用于调整在多声道音频语音活动检测中使用的阈值的方法。 计算一次和二次声音拾取通道的强度。 还计算出分离，作为主要和次要信道强度差异的量度。 进行分离峰的分析，例如 使用泄漏峰值捕获功能，捕获分离中的峰值，然后随时间衰减，或使用滑动窗口最小 - 最大检测器。 根据峰值的分析，调整在语音活动检测（VAD）过程中使用的阈值。 还描述和要求保护其他实施例。

公开(公告)号：US09467779B2

公开(公告)日：2016-10-11

申请号：US14276988

申请日：2014-05-13

Applicant: Apple Inc.

Inventor： Vasu Iyengar ,  Fatos Myftari ,  Sorin V. Dusan ,  Aram M. Lindahl

IPC: H04R3/04 ,  H04R3/00 ,  H04R1/08

CPC classification number: H04R3/04 ,  H04R1/08 ,  H04R3/002 ,  H04R3/005 ,  H04R2499/11

Abstract: Digital signal processing for microphone partial occlusion detection is described. In one embodiment, an electronic system for audio noise processing and for noise reduction, using a plurality of microphones, includes a first noise estimator to process a first audio signal from a first one of the microphones, and generate a first noise estimate. The electronic system also includes a second noise estimator to process the first audio signal, and a second audio signal from a second one of the microphones, in parallel with the first noise estimator, and generate a second noise estimate. A microphone partial occlusion detector determines a low frequency band separation of the first and second audio signals and a high frequency band separation of the first and second audio signals to generate a microphone partial occlusion function that indicates whether one of the microphones is partially occluded.

Abstract translation: 描述了用于麦克风部分遮挡检测的数字信号处理。 在一个实施例中，使用多个麦克风的用于音频噪声处理和降噪的电子系统包括第一噪声估计器，用于处理来自第一麦克风的第一音频信号，并产生第一噪声估计。 电子系统还包括第二噪声估计器，用于处理第一音频信号，以及来自第二麦克风的第二音频信号与第一噪声估计器并行并产生第二噪声估计。 麦克风部分遮挡检测器确定第一和第二音频信号的低频带分离以及第一和第二音频信号的高频带间隔，以产生指示麦克风中的一个是否被部分遮挡的麦克风部分闭塞功能。

公开(公告)号：US20160093316A1

公开(公告)日：2016-03-31

申请号：US14502622

申请日：2014-09-30

Applicant: APPLE INC.

Inventor： Baptiste P. Paquier ,  Anthony J. Guetta ,  Aram M. Lindahl ,  Eric A. Allamanche

IPC: G10L25/48 ,  H04L29/06

CPC classification number: G10L25/48 ,  H04L65/604 ,  H04L65/605

Abstract: Unwanted audio, such as explicit language, may be removed during audio playback. An audio player may identify and remove unwanted audio while playing an audio stream. Unwanted audio may be replaced with alternate audio, such as non-explicit lyrics, a “beep”, or silence. Metadata may be used to describe the location of unwanted audio within an audio stream to enable the removal or replacement of the unwanted audio with alternate audio. An audio player may switch between clean and explicit versions of a recording based on the locations described in the metadata. The metadata, as well as both the clean and explicit versions of the audio data, may be part of a single audio file, or the metadata may be separate from the audio data. Additionally, real-time recognition analysis may be used to identify unwanted audio during audio playback.

Abstract translation: 在音频播放期间，可能会删除不需要的音频，例如显式语言。 音频播放器可以在播放音频流时识别和去除不需要的音频。 不需要的音频可能会被替代音频替代，例如非明确的歌词，“哔”或沉默。 元数据可用于描述音频流中不需要的音频的位置，以便能够用备用音频去除或替换不需要的音频。 音频播放器可以基于元数据中描述的位置在干涉和显式版本的记录之间切换。 元数据以及音频数据的干净和显式版本可以是单个音频文件的一部分，或者元数据可以与音频数据分开。 此外，实时识别分析可用于在音频播放期间识别不需要的音频。