公开(公告)号：US12033654B2

公开(公告)日：2024-07-09

申请号：US17705687

申请日：2022-03-28

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Madoka Wada ,  Yoshifumi Hirose ,  Yusuke Adachi

IPC: G10L21/028 ,  G10L15/22 ,  G10L15/25 ,  G10L21/0216

CPC classification number: G10L21/028 ,  G10L15/22 ,  G10L15/25 ,  G10L21/0216 ,  G10L2021/02166

Abstract: A sound pickup device for picking up a target sound includes: a first input interface that inputs image data generated by a camera; a second input interface that inputs an audio signal output from a microphone array; a controller that determines a sound pickup direction in which the target sound is picked up, based on the image data and the audio signal; and an output interface that outputs information to be presented to the user. The controller determines whether an image indicated by the input image data and an audio sound indicated by the input audio signal are in a predetermined state. When determining that the image and the audio sound are in the predetermined state, the controller causes the output interface to output an instruction to the user, and inputs additional image data and an additional audio signal after the instruction is output, to determine the sound pickup direction.

公开(公告)号：US20220215852A1

公开(公告)日：2022-07-07

申请号：US17705687

申请日：2022-03-28

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Madoka Wada ,  Yoshifumi Hirose ,  Yusuke Adachi

IPC: G10L21/028 ,  G10L15/22 ,  G10L15/25 ,  G10L21/0216

Abstract: A sound pickup device for picking up a target sound includes: a first input interface that inputs image data generated by a camera; a second input interface that inputs an audio signal output from a microphone array; a controller that determines a sound pickup direction in which the target sound is picked up, based on the image data and the audio signal; and an output interface that outputs information to be presented to the user. The controller determines whether an image indicated by the input image data and an audio sound indicated by the input audio signal are in a predetermined state. When determining that the image and the audio sound are in the predetermined state, the controller causes the output interface to output an instruction to the user, and inputs additional image data and an additional audio signal after the instruction is output, to determine the sound pickup direction.