公开(公告)号：US20190342652A1

公开(公告)日：2019-11-07

申请号：US16509711

申请日：2019-07-12

Applicant: Cirrus Logic International Semiconductor Ltd.

Inventor： David Leigh WATTS ,  Brenton Robert STEELE ,  Thomas Ivan HARVEY ,  Vitaliy SAPOZHNYKOV

IPC: H04R1/10 ,  H04R1/46 ,  G10L21/0208 ,  G10L25/78

Abstract: Embodiments of the invention determine a speech estimate using a bone conduction sensor or accelerometer, without employing voice activity detection gating of speech estimation. Speech estimation is based either exclusively on the bone conduction signal, or is performed in combination with a microphone signal. The speech estimate is then used to condition an output signal of the microphone. There are multiple use cases for speech processing in audio devices.

公开(公告)号：US20180367882A1

公开(公告)日：2018-12-20

申请号：US16009524

申请日：2018-06-15

Applicant: Cirrus Logic International Semiconductor Ltd.

Inventor： David Leigh WATTS ,  Brenton Robert STEELE ,  Thomas Ivan HARVEY ,  Vitaliy SAPOZHNYKOV

IPC: H04R1/10 ,  G10L25/78

CPC classification number: H04R1/1041 ,  G10L21/0208 ,  G10L25/78 ,  G10L2021/02161 ,  H04R1/1016 ,  H04R1/1075 ,  H04R1/1083 ,  H04R1/46 ,  H04R3/005 ,  H04R2420/07 ,  H04R2460/13

Abstract: Embodiments of the invention determine a speech estimate using a bone conduction sensor or accelerometer, without employing voice activity detection gating of speech estimation. Speech estimation is based either exclusively on the bone conduction signal, or is performed in combination with a microphone signal. The speech estimate is then used to condition an output signal of the microphone. There are multiple use cases for speech processing in audio devices.

公开(公告)号：US20180294000A1

公开(公告)日：2018-10-11

申请号：US15946245

申请日：2018-04-05

Applicant: Cirrus Logic International Semiconductor Ltd.

Inventor： Brenton Robert STEELE ,  Hu CHEN ,  Ben HUTCHINS

IPC: G10L25/84 ,  G10K11/175 ,  G10L25/30

Abstract: A signal processing device for configurable voice activity detection. A plurality of inputs receive respective microphone signals. A microphone signal router configurably routes the microphone signals. At least one voice activity detection module receives a pair of microphone signals from the router, and produces a respective output indicating whether speech or noise has been detected by the voice activity detection module in the respective pair of microphone signals. A voice activity decision module receives the output of the voice activity detection module(s) and determines whether voice activity exists in the microphone signals. A spatial noise reduction module receives microphone signals from the microphone signal router, and performs adaptive beamforming based in part upon the output of the voice activity decision module, and outputs a spatial noise reduced output. The device permits simple configurability to deliver spatial noise reduction for one of a wide variety of headset form factors.