公开(公告)号：US11749285B2

公开(公告)日：2023-09-05

申请号：US17648067

申请日：2022-01-14

Applicant: Meta Platforms Technologies, LLC

Inventor： Vincent Charles Cheung ,  Chengxuan Bai ,  Yating Sheng

IPC: G10L17/00 ,  G06F3/01 ,  G06T19/00 ,  G10L25/63 ,  H04R1/40 ,  H04R3/00 ,  G06V40/16

CPC classification number: G10L17/00 ,  G06F3/011 ,  G06T19/006 ,  G06V40/161 ,  G10L25/63 ,  H04R1/406 ,  H04R3/005

Abstract: This disclosure describes transcribing speech using audio, image, and other data. A system is described that includes an audio capture system configured to capture audio data associated with a plurality of speakers, an image capture system configured to capture images of one or more of the plurality of speakers, and a speech processing engine. The speech processing engine may be configured to recognize a plurality of speech segments in the audio data, identify, for each speech segment of the plurality of speech segments and based on the images, a speaker associated with the speech segment, transcribe each of the plurality of speech segments to produce a transcription of the plurality of speech segments including, for each speech segment in the plurality of speech segments, an indication of the speaker associated with the speech segment, and analyze the transcription to produce additional data derived from the transcription.

公开(公告)号：US20240298084A9

公开(公告)日：2024-09-05

申请号：US17688662

申请日：2022-03-07

Applicant: META PLATFORMS TECHNOLOGIES, LLC

Inventor： Lisa Xiaoyi Huang ,  Eric Xiao ,  Nicholas Michael Andrew Benson ,  Yating Sheng ,  Zijian He

IPC: H04N5/232 ,  G06F9/451 ,  G06V40/16 ,  G06V40/18 ,  G06V40/20 ,  H04N5/76

CPC classification number: H04N23/611 ,  G06F9/453 ,  G06V20/30 ,  G06V20/52 ,  G06V40/172 ,  G06V40/174 ,  G06V40/18 ,  G06V40/20 ,  H04N5/76 ,  H04N23/617 ,  H04N23/64 ,  H04N23/66 ,  H04N23/69 ,  H04L67/306 ,  H04N1/00151 ,  H04N1/00159

Abstract: In one embodiment, a method includes accessing sensory data captured by cameras, identifying people in a field of view of the cameras based on facial recognition of the sensory data, detecting actions of one or more of the people based on the sensory data, generating media files with each being associated with one or more of a recording of at least one of the people or at least one of the determined actions, and sending instructions for presenting one or more of the media files to a client system.

公开(公告)号：US20230283878A1

公开(公告)日：2023-09-07

申请号：US17688662

申请日：2022-03-07

Applicant: META PLATFORMS TECHNOLOGIES, LLC

Inventor： Lisa Xiaoyi Huang ,  Eric Xiao ,  Nicholas Michael Andrew Benson ,  Yating Sheng ,  Zijian He

IPC: H04N5/232 ,  G06V40/16 ,  G06V40/20 ,  G06V40/18 ,  H04N5/76 ,  G06F9/451

CPC classification number: H04N5/23219 ,  G06V40/172 ,  G06V40/20 ,  G06V40/174 ,  G06V40/18 ,  H04N5/23296 ,  H04N5/23203 ,  H04N5/76 ,  H04N5/23222 ,  G06F9/453 ,  H04L67/306

Abstract: In one embodiment, a method includes accessing sensory data captured by cameras, identifying people in a field of view of the cameras based on facial recognition of the sensory data, detecting actions of one or more of the people based on the sensory data, generating media files with each being associated with one or more of a recording of at least one of the people or at least one of the determined actions, and sending instructions for presenting one or more of the media files to a client system.