公开(公告)号：US11610610B1

公开(公告)日：2023-03-21

申请号：US17643805

申请日：2021-12-10

Applicant: Amazon Technologies, Inc.

Inventor： Avijit Vajpayee ,  Hooman Mahyar ,  Vimal Bhat ,  Abhinav Jain ,  Zhikang Zhang

IPC: H04N9/88 ,  G11B27/10

Abstract: Systems and methods are provided for detecting and correcting synchronization errors in multimedia content comprising a video stream and a non-original audio stream. Techniques for directly detecting synchronization of video and audio streams may be inadequate to detect synchronize errors for non-original audio streams, particularly where such non-original audio streams contain audio not reflective of events within the video stream, such as speaking dialog in a different language than the speakers of the video stream. To overcome this problem, the present disclosure enables synchronization of a non-original audio stream to another audio stream, such as an original audio stream, that is synchronized to the video stream. By comparison of signatures, the non-original and other audio stream are aligned to determine an offset that can be used to synchronize the non-original audio stream to the video stream.

公开(公告)号：US11935170B1

公开(公告)日：2024-03-19

申请号：US17530070

申请日：2021-11-18

Applicant: Amazon Technologies, Inc.

Inventor： Abhinav Jain ,  Avijit Vajpayee ,  Vimal Bhat ,  Arjun Cholkar ,  Louis Kirk Barker

IPC: G06T13/40 ,  G06F40/20 ,  G06N3/08 ,  G06T17/00 ,  G06V20/40 ,  G06V40/16 ,  G06V40/20 ,  G09B21/00 ,  G10L25/63 ,  H04N5/272

CPC classification number: G06T13/40 ,  G06F40/20 ,  G06N3/08 ,  G06T17/00 ,  G06V20/46 ,  G06V40/174 ,  G06V40/28 ,  G09B21/009 ,  G10L25/63 ,  H04N5/272

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for automated generation and presentation of sign language avatars for video content. Example methods may include determining, by one or more computer processors coupled to memory, a first segment of video content, the first segment including a first set of frames, first audio content, and first subtitle data, where the first subtitle data comprises a first word and a second word. Methods may include determining, using a first machine learning model, a first sign gesture associated with the first word, determining first motion data associated with the first sign gesture, and determining first facial expression data. Methods may include generating an avatar configured to perform the first sign gesture using the first motion data, where a facial expression of the avatar while performing the first sign gesture is based on the first facial expression data.

公开(公告)号：US11659217B1

公开(公告)日：2023-05-23

申请号：US17301212

申请日：2021-03-29

Applicant: Amazon Technologies, Inc.

Inventor： Hooman Mahyar ,  Avijit Vajpayee ,  Abhinav Jain ,  Arjun Cholkar ,  Vimal Bhat

IPC: H04N21/242 ,  H04N21/234 ,  H04N21/233

CPC classification number: H04N21/242 ,  H04N21/233 ,  H04N21/234

Abstract: Techniques are described for detecting desynchronization between an audio component and a video component of a media presentation. Feature sets may be determined for portions of the audio component and portions of the video component, which may then be used to generate correlations between portions of the audio component and portions of the video component. Synchronization may then be assessed based on the correlations.

公开(公告)号：US20240242413A1

公开(公告)日：2024-07-18

申请号：US18432623

申请日：2024-02-05

Applicant: Amazon Technologies, Inc.

Inventor： Avijit Vajpayee ,  Vimal Bhat ,  Arjun Cholkar ,  Louis Kirk Barker ,  Abhinav Jain

IPC: G06T13/40 ,  G06F40/20 ,  G06N3/08 ,  G06T17/00 ,  G06V20/40 ,  G06V40/16 ,  G06V40/20 ,  G09B21/00 ,  G10L25/63 ,  H04N5/272

CPC classification number: G06T13/40 ,  G06F40/20 ,  G06N3/08 ,  G06T17/00 ,  G06V20/46 ,  G06V40/174 ,  G06V40/28 ,  G09B21/009 ,  G10L25/63 ,  H04N5/272

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for automated generation and presentation of sign language avatars for video content. Example methods may include determining, by one or more computer processors coupled to memory, a first segment of video content, the first segment including a first set of frames, first audio content, and first subtitle data, where the first subtitle data comprises a first word and a second word. Methods may include determining, using a first machine learning model, a first sign gesture associated with the first word, determining first motion data associated with the first sign gesture, and determining first facial expression data. Methods may include generating an avatar configured to perform the first sign gesture using the first motion data, where a facial expression of the avatar while performing the first sign gesture is based on the first facial expression data.