公开(公告)号：US11539919B1

公开(公告)日：2022-12-27

申请号：US17117948

申请日：2020-12-10

Applicant: Amazon Technologies, Inc.

Inventor： Siddhartha Shankara Rao ,  Tobias DiPasquale ,  John Joseph Dunne ,  Jennie Tietema ,  Ivan Marcin ,  Richard Newman ,  Giridhar Kalpathy Narayanan

IPC: H04N7/15 ,  H04N21/44 ,  H04N5/262 ,  H04N21/61 ,  H04N21/6405

Abstract: Implementations for combining at least two video streams received from devices of a plurality of participants of a video conference into a composite video stream are described. A video conference including the video streams received from the devices of the plurality of participants is established. A capability associated with consuming at least two of the video streams is received from at least one of the devices. The at least two video streams are then combined into a composite video stream based on the capability associated with consuming the at least two video streams. The composite video stream is transmitted to the at least one of the devices.

公开(公告)号：US12081602B1

公开(公告)日：2024-09-03

申请号：US17474503

申请日：2021-09-14

Applicant: Amazon Technologies, Inc.

Inventor： Gowthami Gudipati ,  Richard Newman

IPC: H04L65/403 ,  H04L65/611 ,  H04L65/612 ,  H04L65/65 ,  H04L65/70

CPC classification number: H04L65/403 ,  H04L65/611 ,  H04L65/612 ,  H04L65/65 ,  H04L65/70

Abstract: Implementations for metering features of media conferences on the client-side are described. Initially, a participant joins a media conference. An identifier of a feature and an allotment associated with the feature is then received by the participant. The feature is used during the media conference and the allotment associated with the feature is decremented based on the use of the feature. It is then determined that an allotment refresh is needed. In response, additional allotment associated with the feature is requested and received by the participant until the maximum number of additional allotment requests or the maximum allotment is reached.

公开(公告)号：US11196963B1

公开(公告)日：2021-12-07

申请号：US17118080

申请日：2020-12-10

Applicant: Amazon Technologies, Inc.

Inventor： Tobias DiPasquale ,  Siddhartha Shankara Rao ,  John Joseph Dunne ,  Ivan Marcin ,  Richard Newman ,  Eric D. Cox

IPC: H04N7/15 ,  G06F3/0484 ,  H04L29/06

Abstract: Implementations for combining a plurality of content based on instructions for a layout of a video conference are described. A video conference is established between a plurality of devices of participants of the video conference. First content is received from a device of the plurality of devices in the established video conference. Second content is also received. Instructions for a layout of the first content and the second content during the video conference is received. Based on the instructions for the layout, the first content and the second content are combined into a composite video stream. The composite video stream is saved or transmitted.

公开(公告)号：US11924367B1

公开(公告)日：2024-03-05

申请号：US17668297

申请日：2022-02-09

Applicant: Amazon Technologies, Inc.

Inventor： Jean-Marc Valin ,  Karim Helwani ,  Srikanth Venkata Tenneti ,  Erfan Soltanmohammadi ,  Mehmet Umut Isik ,  Richard Newman ,  Michael Mark Goodwin ,  Arvindh Krishnaswamy

IPC: H04M3/00 ,  G10L21/0232 ,  G10L21/034 ,  G10L25/18 ,  H04S3/00 ,  G10L21/0208

CPC classification number: H04M3/002 ,  G10L21/0232 ,  G10L21/034 ,  G10L25/18 ,  H04S3/008 ,  G10L2021/02082 ,  H04S2400/01 ,  H04S2400/03

Abstract: Joint noise and echo suppression may be performed for enhancing two-way audio communications. Audio data is captured at a communication device and audio data transmitted to the communication device from another communication device are used as input features to a trained machine learning model that uses the transmitted audio data as a reference signal to eliminate residual echo in the captured audio data when also suppressing noise in the captured audio data.