User voice activity detection
    1.
    发明授权

    公开(公告)号:US11614916B2

    公开(公告)日:2023-03-28

    申请号:US16730134

    申请日:2019-12-30

    Abstract: Many headsets include automatic noise cancellation (ANC) which dramatically reduces perceived background noise and improves user listening experience. Unfortunately, the voice microphones in these devices often capture ambient noise that the headsets output during phone calls or other communication sessions to other users. In response, many headsets and communication devices provide manual muting circuitry, but users frequently forget to turn the muting on and/or off creating further problems as they communicate. To address this, the present inventors devised, among other things, an exemplary headset that detects the absence or presence of user speech, automatically muting and unmuting the voice microphone without user intervention. Some embodiments leverage relationships between feedback and feedforward signals in ANC circuitry to detect user speech, avoiding the addition of extra hardware to the headset. Other embodiments also leverage the speech detection function to activate and deactivate keyword detectors, and/or sidetone circuits, thus extending battery.

    LOW-POWER, ALWAYS-LISTENING, VOICE COMMAND DETECTION AND CAPTURE

    公开(公告)号:US20180174583A1

    公开(公告)日:2018-06-21

    申请号:US15706178

    申请日:2017-09-15

    Abstract: A system for detecting and capturing voice commands, the system comprising a voice-activity detector (VAD) configured to receive a VAD-received digital-audio signal; determine the amplitude of the VAD-received digital-audio signal; compare the amplitude of the VAD-received digital-audio signal to a first threshold and to a second threshold; withhold a VAD interrupt signal when the amplitude of the VAD-received digital-audio signal does not exceed the first threshold or the second threshold; generate the VAD interrupt signal when the amplitude of the VAD-received digital-audio signal exceeds the first threshold and the second threshold; and perform spectral analysis of the VAD-received digital-audio signal when the amplitude of the VAD-received digital-audio signal is between the first threshold and the second threshold.

    Automatic playback time adjustment

    公开(公告)号:US11366633B2

    公开(公告)日:2022-06-21

    申请号:US16017800

    申请日:2018-06-25

    Abstract: An apparatus can include an audio playback device configured to provide an audio output to a user, and a controller configured to: receive an initial playback position within the audio output; determine that an off-ear event has occurred; identify a time corresponding to the off-ear event; instruct the audio playback device to pause the audio output at the identified time; and calculate a new playback position within the audio output based at least in part on the identified time.

    User voice activity detection methods, devices, assemblies, and components

    公开(公告)号:US10564925B2

    公开(公告)日:2020-02-18

    申请号:US15711793

    申请日:2017-09-21

    Abstract: Many headsets include automatic noise cancellation (ANC) which dramatically reduces perceived background noise and improves user listening experience. Unfortunately, the voice microphones in these devices often capture ambient noise that the headsets output during phone calls or other communication sessions to other users. In response, many headsets and communication devices provide manual muting circuitry, but users frequently forget to turn the muting on and/or off, creating further problems as they communicate. To address this, the present inventors devised, among other things, an exemplary headset that detects the absence or presence of user speech, automatically muting and unmuting the voice microphone without user intervention. Some embodiments leverage relationships between feedback and feedforward signals in ANC circuitry to detect user speech, avoiding the addition of extra hardware to the headset. Other embodiments also leverage the speech detection function to activate and deactivate keyword detectors, and/or sidetone circuits, thus extending battery.

    Low-power, always-listening, voice command detection and capture

    公开(公告)号:US10403279B2

    公开(公告)日:2019-09-03

    申请号:US15706178

    申请日:2017-09-15

    Abstract: A system for detecting and capturing voice commands, the system comprising a voice-activity detector (VAD) configured to receive a VAD-received digital-audio signal; determine the amplitude of the VAD-received digital-audio signal; compare the amplitude of the VAD-received digital-audio signal to a first threshold and to a second threshold; withhold a VAD interrupt signal when the amplitude of the VAD-received digital-audio signal does not exceed the first threshold or the second threshold; generate the VAD interrupt signal when the amplitude of the VAD-received digital-audio signal exceeds the first threshold and the second threshold; and perform spectral analysis of the VAD-received digital-audio signal when the amplitude of the VAD-received digital-audio signal is between the first threshold and the second threshold.

    User Voice Activity Detection Methods, Devices, Assemblies, and Components

    公开(公告)号:US20180225082A1

    公开(公告)日:2018-08-09

    申请号:US15711793

    申请日:2017-09-21

    Abstract: Many headsets include automatic noise cancellation (ANC) which dramatically reduces perceived background noise and improves user listening experience. Unfortunately, the voice microphones in these devices often capture ambient noise that the headsets output during phone calls or other communication sessions to other users. In response, many headsets and communication devices provide manual muting circuitry, but users frequently forget to turn the muting on and/or off, creating further problems as they communicate. To address this, the present inventors devised, among other things, an exemplary headset that detects the absence or presence of user speech, automatically muting and unmuting the voice microphone without user intervention. Some embodiments leverage relationships between feedback and feedforward signals in ANC circuitry to detect user speech, avoiding the addition of extra hardware to the headset. Other embodiments also leverage the speech detection function to activate and deactivate keyword detectors, and/or sidetone circuits, thus extending battery.

    GESTURE-CONTROLLED TABLETOP SPEAKER SYSTEM
    9.
    发明申请
    GESTURE-CONTROLLED TABLETOP SPEAKER SYSTEM 有权
    控制面板扬声器系统

    公开(公告)号:US20150193193A1

    公开(公告)日:2015-07-09

    申请号:US14249696

    申请日:2014-04-10

    Abstract: A tabletop speaker system includes an amplifier, proximity and acceleration detectors, and a processor. The processor is operatively coupled to receive signals from the proximity and accelerometer detectors, and in response to the proximity and acceleration signals, activate various functions local to the tabletop speaker system to operate and control various behaviors or features of the tabletop speaker system. In this way, the tabletop speaker system can respond to user gestures for a very natural control interface.

    Abstract translation: 台式扬声器系统包括放大器,接近和加速度检测器以及处理器。 处理器可操作地耦合以从接近和加速度计检测器接收信号,并且响应于接近和加速度信号,激活桌面扬声器系统的局部的各种功能来操作和控制台式扬声器系统的各种行为或特征。 以这种方式,桌面扬声器系统可以响应用户手势进行非常自然的控制界面。

    Gesture-controlled tabletop speaker system

    公开(公告)号:US10474420B2

    公开(公告)日:2019-11-12

    申请号:US16159333

    申请日:2018-10-12

    Abstract: A speaker system includes a case, an audio input, speakers, an accelerometer, and a computer processor. The audio input is structured to receive a program audio signal from an audio device. The speakers are configured to play an audio output based on the program audio signal, the audio output causing a vibration of the case. The accelerometer is configured to detect the vibration of the case as well as a user tap on the case. The computer processor is configured to identify a user gesture that includes the tap on the case, to identify the tap apart from the case vibration by processing the detected vibration of the case and the detected user tap on the case based on information from the program audio signal to separate the detected user tap from the detected vibration, and to commence a particular function associated with the user gesture.

Patent Agency Ranking