公开(公告)号：US12119019B2

公开(公告)日：2024-10-15

申请号：US17578217

申请日：2022-01-18

Applicant: Google LLC

Inventor： Julian Maclaren ,  Karolis Misiunas ,  Vahe Tshitoyan ,  Brian Foo ,  Kelly Dobson

IPC: G10L25/51 ,  A61B5/024 ,  G10L15/22 ,  G10L21/028 ,  G10L25/78 ,  H04R1/04 ,  H04R1/40 ,  H04R3/00

CPC classification number: G10L25/51 ,  A61B5/02416 ,  G10L15/22 ,  G10L21/028 ,  G10L25/78 ,  H04R1/04 ,  H04R1/406 ,  H04R3/005 ,  A61B2503/12

Abstract: Various systems, devices, and methods for social interaction measurement that preserve privacy are presented. An audio signal can be captured using a microphone. The audio signal can be processed using an audio-based machine learning model that is trained to detect the presence of speech. The audio signal can be discarded such that content of the audio signal is not stored after the audio signal is processed using the machine learning model. An indication of whether speech is present within the audio signal can be output based at least in part on processing the audio signal using the audio-based machine learning model.

公开(公告)号：US20250014591A1

公开(公告)日：2025-01-09

申请号：US18886136

申请日：2024-09-16

Applicant: Google LLC

Inventor： Julian Maclaren ,  Karolis Misiunas ,  Vahe Tshitoyan ,  Brian Foo ,  Kelly Dobson

IPC: G10L25/51 ,  A61B5/024 ,  G10L15/22 ,  G10L21/028 ,  G10L25/78 ,  H04R1/04 ,  H04R1/40 ,  H04R3/00

Abstract: Various systems, devices, and methods for social interaction measurement that preserve privacy are presented. An audio signal can be captured using a microphone. The audio signal can be processed using an audio-based machine learning model that is trained to detect the presence of speech. The audio signal can be discarded such that content of the audio signal is not stored after the audio signal is processed using the machine learning model. An indication of whether speech is present within the audio signal can be output based at least in part on processing the audio signal using the audio-based machine learning model.

公开(公告)号：US20230230612A1

公开(公告)日：2023-07-20

申请号：US17578217

申请日：2022-01-18

Applicant: Google LLC

Inventor： Julian Maclaren ,  Karolis Misiunas ,  Vahe Tshitoyan ,  Brian Foo ,  Kelly Dobson

IPC: G10L25/51 ,  H04R1/40 ,  H04R1/04 ,  H04R3/00 ,  G10L21/028 ,  G10L25/78 ,  G10L15/22 ,  A61B5/024

CPC classification number: G10L25/51 ,  H04R1/406 ,  H04R1/04 ,  H04R3/005 ,  G10L21/028 ,  G10L25/78 ,  G10L15/22 ,  A61B5/02416 ,  A61B2503/12

Abstract: Various systems, devices, and methods for social interaction measurement that preserve privacy are presented. An audio signal can be captured using a microphone. The audio signal can be processed using an audio-based machine learning model that is trained to detect the presence of speech. The audio signal can be discarded such that content of the audio signal is not stored after the audio signal is processed using the machine learning model. An indication of whether speech is present within the audio signal can be output based at least in part on processing the audio signal using the audio-based machine learning model.