公开(公告)号：US20240013772A1

公开(公告)日：2024-01-11

申请号：US18471627

申请日：2023-09-21

Applicant: Google LLC

Inventor： Nolan Andrew Miller ,  Ramin Mehran

IPC: G10L15/02 ,  H04R3/00

CPC classification number: G10L15/02 ,  H04R3/005

Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process. The method also includes determining whether to accept or reject the multi-channel audio for processing by the particular application based on the first score generated as output from the application-specific classifier.

公开(公告)号：US12154547B2

公开(公告)日：2024-11-26

申请号：US18471627

申请日：2023-09-21

Applicant: Google LLC

Inventor： Nolan Andrew Miller ,  Ramin Mehran

IPC: G10L15/02 ,  H04R3/00

Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process. The method also includes determining whether to accept or reject the multi-channel audio for processing by the particular application based on the first score generated as output from the application-specific classifier.

公开(公告)号：US11380302B2

公开(公告)日：2022-07-05

申请号：US17077679

申请日：2020-10-22

Applicant: Google LLC

Inventor： Nolan Andrew Miller ,  Ramin Mehran

IPC: G10L15/02 ,  H04R3/00

Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process. The method also includes determining whether to accept or reject the multi-channel audio for processing by the particular application based on the first score generated as output from the application-specific classifier.

公开(公告)号：US11790888B2

公开(公告)日：2023-10-17

申请号：US17806198

申请日：2022-06-09

Applicant: Google LLC

Inventor： Nolan Andrew Miller ,  Ramin Mehran

IPC: G10L15/02 ,  H04R3/00

CPC classification number: G10L15/02 ,  H04R3/005

Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process. The method also includes determining whether to accept or reject the multi-channel audio for processing by the particular application based on the first score generated as output from the application-specific classifier.

公开(公告)号：US20220310060A1

公开(公告)日：2022-09-29

申请号：US17806198

申请日：2022-06-09

Applicant: Google LLC

Inventor： Nolan Andrew Miller ,  Ramin Mehran

IPC: G10L15/02 ,  H04R3/00

Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process. The method also includes determining whether to accept or reject the multi-channel audio for processing by the particular application based on the first score generated as output from the application-specific classifier.

公开(公告)号：US20220130375A1

公开(公告)日：2022-04-28

申请号：US17077679

申请日：2020-10-22

Applicant: Google LLC

Inventor： Nolan Andrew Miller ,  Ramin Mehran

IPC: G10L15/02 ,  H04R3/00

Abstract: A method for multi-channel voice activity detection includes receiving a sequence of input frames characterizing streaming multi-channel audio captured by an array of microphones. Each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. The method also includes determining, using a location fingerprint model, a location fingerprint indicating a location of a source of the multi-channel audio relative to the user device based on the respective audio features of each channel of the multi-channel audio. The method also includes generating an output from an application-specific classifier. The first score indicates a likelihood that the multi-channel audio corresponds to a particular audio type that the particular application is configured to process. The method also includes determining whether to accept or reject the multi-channel audio for processing by the particular application based on the first score generated as output from the application-specific classifier.