公开(公告)号：US20230379621A1

公开(公告)日：2023-11-23

申请号：US18130654

申请日：2023-04-04

申请人： Jawbone Innovations, LLC

发明人： Nicolas Petit ,  Gregory Burnett ,  Zhinian Jing

IPC分类号： H04R3/00 ,  G10L25/78 ,  G10L21/0216 ,  G10L25/93

CPC分类号： H04R3/005 ,  G10L25/78 ,  G10L2021/02165 ,  G10L2025/783 ,  G10L2025/937

摘要： Acoustic Voice Activity Detection (AVAD) methods and systems are described. The AVAD methods and systems, including corresponding algorithms or programs, use microphones to generate virtual directional microphones which have very similar noise responses and very dissimilar speech responses. The ratio of the energies of the virtual microphones is then calculated over a given window size and the ratio can then be used with a variety of methods to generate a VAD signal. The virtual microphones can be constructed using either an adaptive or a fixed filter.

公开(公告)号：US11627413B2

公开(公告)日：2023-04-11

申请号：US13669375

申请日：2012-11-05

申请人： Jawbone Innovations, LLC

发明人： Nicolas Petit ,  Gregory Burnett ,  Zhinian Jing

IPC分类号： H04R3/00 ,  G10L25/78 ,  G10L25/93 ,  G10L21/0216

摘要： Acoustic Voice Activity Detection (AVAD) methods and systems are described. The AVAD methods and systems, including corresponding algorithms or programs, use microphones to generate virtual directional microphones which have very similar noise responses and very dissimilar speech responses. The ratio of the energies of the virtual microphones is then calculated over a given window size and the ratio can then be used with a variety of methods to generate a VAD signal. The virtual microphones can be constructed using either an adaptive or a fixed filter.

公开(公告)号：US12063487B2

公开(公告)日：2024-08-13

申请号：US18130654

申请日：2023-04-04

申请人： Jawbone Innovations, LLC

发明人： Nicolas Petit ,  Gregory Burnett ,  Zhinian Jing

IPC分类号： H04R3/00 ,  G10L25/78 ,  G10L21/0216 ,  G10L25/93

CPC分类号： H04R3/005 ,  G10L25/78 ,  G10L2021/02165 ,  G10L2025/783 ,  G10L2025/937

摘要： Acoustic Voice Activity Detection (AVAD) methods and systems are described. The AVAD methods and systems, including corresponding algorithms or programs, use microphones to generate virtual directional microphones which have very similar noise responses and very dissimilar speech responses. The ratio of the energies of the virtual microphones is then calculated over a given window size and the ratio can then be used with a variety of methods to generate a VAD signal. The virtual microphones can be constructed using either an adaptive or a fixed filter.