公开(公告)号：US11721354B2

公开(公告)日：2023-08-08

申请号：US17447619

申请日：2021-09-14

Applicant: Snap Inc.

Inventor： Changxi Zheng ,  Arun Asokan Nair ,  Austin Reiter ,  Shree K. Nayar

IPC: G10L21/0232 ,  G10L25/30 ,  G10L25/57 ,  H04R1/40 ,  G10L21/0216

CPC classification number: G10L21/0232 ,  G10L25/30 ,  G10L25/57 ,  H04R1/406 ,  G10L2021/02166

Abstract: Method of performing acoustic zooming starts with microphones capturing acoustic signals associated with video content. Beamformers generate beamformer signals using the acoustic signals. Beamformer signals correspond respectively to tiles of video content. Each of the beamformers is respectively directed to a center of each of the tiles. Target enhanced signal is generated using beamformer signals. Target enhanced signal is associated with a zoom area of video content. Target enhanced signal is generated by identifying the tiles respectively having at least portions that are included in the zoom area, selecting beamformer signals corresponding to identified tiles, and combining selected beamformer signals to generate target enhanced signal. Combining selected beamformer signals may include determining proportions for each of the identified tiles in relation to the zoom area and combining selected beamformer signals based on the proportions to generate the target enhanced signal. Other embodiments are described herein.

公开(公告)号：US20220108713A1

公开(公告)日：2022-04-07

申请号：US17447619

申请日：2021-09-14

Applicant: Snap Inc.

Inventor： Changxi Zheng ,  Arun Asokan Nair ,  Austin Reiter ,  Shree K. Nayar

IPC: G10L21/0232 ,  H04R1/40 ,  G10L25/57 ,  G10L25/30 ,  G10L21/0216

Abstract: Method of performing acoustic zooming starts with microphones capturing acoustic signals associated with video content. Beamformers generate beamformer signals using the acoustic signals. Beamformer signals correspond respectively to tiles of video content. Each of the beamformers is respectively directed to a center of each of the tiles. Target enhanced signal is generated using beamformer signals. Target enhanced signal is associated with a zoom area of video content. Target enhanced signal is generated by identifying the tiles respectively having at least portions that are included in the zoom area, selecting beamformer signals corresponding to identified tiles, and combining selected beamformer signals to generate target enhanced signal. Combining selected beamformer signals may include determining proportions for each of the identified tiles in relation to the zoom area and combining selected beamformer signals based on the proportions to generate the target enhanced signal. Other embodiments are described herein.

公开(公告)号：US11189298B2

公开(公告)日：2021-11-30

申请号：US17250763

申请日：2019-08-30

Applicant: Snap Inc.

Inventor： Changxi Zheng ,  Arun Asokan Nair ,  Austin Reiter ,  Shree K. Nayar

IPC: G10L21/0232 ,  G10L25/30 ,  H04R1/40 ,  G10L25/57 ,  G10L21/0216

Abstract: Method of performing acoustic zooming starts with microphones capturing acoustic signals associated with video content. Beamformers generate beamformer signals using the acoustic signals. Beamformer signals correspond respectively to tiles of video content. Each of the beamformers is respectively directed to a center of each of the tiles. Target enhanced signal is generated using beamformer signals. Target enhanced signal is associated with a zoom area of video content. Target enhanced signal is generated by identifying the tiles respectively having at least portions that are included in the zoom area, selecting beamformer signals corresponding to identified tiles, and combining selected beamformer signals to generate target enhanced signal. Combining selected beamformer signals may include determining proportions for each of the identified tiles in relation to the zoom area and combining selected beamformer signals based on the proportions to generate the target enhanced signal. Other embodiments are described herein.

公开(公告)号：US11152012B2

公开(公告)日：2021-10-19

申请号：US17250763

申请日：2019-08-30

Applicant: Snap Inc.

Inventor： Changxi Zheng ,  Arun Asokan Nair ,  Austin Reiter ,  Shree K. Nayar

IPC: G10L21/0232 ,  G10L25/30 ,  H04R1/40 ,  G10L25/57 ,  G10L21/0216

Abstract: Method of performing acoustic zooming starts with microphones capturing acoustic signals associated with video content. Beamformers generate beamformer signals using the acoustic signals. Beamformer signals correspond respectively to tiles of video content. Each of the beamformers is respectively directed to a center of each of the tiles. Target enhanced signal is generated using beamformer signals. Target enhanced signal is associated with a zoom area of video content. Target enhanced signal is generated by identifying the tiles respectively having at least portions that are included in the zoom area, selecting beamformer signals corresponding to identified tiles, and combining selected beamformer signals to generate target enhanced signal. Combining selected beamformer signals may include determining proportions for each of the identified tiles in relation to the zoom area and combining selected beamformer signals based on the proportions to generate the target enhanced signal. Other embodiments are described herein.