-
Patent Agency Ranking
1.发明授权公开(公告)号：US11838687B2
公开(公告)日：2023-12-05
申请号：US17675077
申请日：2022-02-18
Applicant: Pexip AS
Inventor： Eamonn Shaw
Abstract: A multi-point videoconferencing system includes video conferencing terminals in communication with a multipoint conferencing node (MCN). A method includes defining at least a first virtual studio and a second virtual studio, each of the at least first and second virtual studios having a policy for each of a set of the tags; initiating a first multi-point videoconferencing session according to the first virtual studio, such that each of the video conferencing terminals in the first multi-point videoconferencing session is connected to the MCN according to the first virtual studio policy of at least one tag of the video conferencing terminal; and reconfiguring, upon switching to the second virtual studio, the first multi-point videoconferencing session according to the second virtual studio, such that each of the videoconferencing terminals in the first multi-point videoconferencing session is connected to the MCN according to the second virtual studio policy for at least one tag.
-
公开(公告)号：US20230005469A1
公开(公告)日：2023-01-05
申请号：US17852548
申请日：2022-06-29
Applicant: PEXIP AS
Inventor： Anna Kim , Eamonn Shaw
IPC: G10L15/06 , G10L25/57 , G10L15/02 , G10L25/84 , G10L21/0232 , G10L21/0224
Abstract: A method of speech detection and speech enhancement in a speech detection and speech enhancement unit of Multipoint Conferencing Node (MCN) and a method of training the same. The method comprising receiving input audio segments, and determining an acoustic environment based on input audio auxiliary information, extracting T-F-domain features from the received input audio segments, determining if each of the received input audio segments is speech by inputting the T-F domain features into a speech detection classifier trained for the determined acoustic environment, determining, when one of the received input audio segments is speech, if the received audio segment is noisy speech by inputting the T-F domain features into a noise classifier using a statistical generative model representing the probability distributions of the T-F domain features of noisy speech trained for the determined acoustic environment, and applying a noise reduction mask on the received input audio segments according to the determination of the received audio segment is noisy speech
-
3.发明申请公开(公告)号：US20220272301A1
公开(公告)日：2022-08-25
申请号：US17675077
申请日：2022-02-18
Applicant: Pexip AS
Inventor： Eamonn Shaw
Abstract: A multi-point videoconferencing system includes video conferencing terminals in communication with a multipoint conferencing node (MCN). A method includes defining at least a first virtual studio and a second virtual studio, each of the at least first and second virtual studios having a policy for each of a set of the tags; initiating a first multi-point videoconferencing session according to the first virtual studio, such that each of the video conferencing terminals in the first multi-point videoconferencing session is connected to the MCN according to the first virtual studio policy of at least one tag of the video conferencing terminal; and reconfiguring, upon switching to the second virtual studio, the first multi-point videoconferencing session according to the second virtual studio, such that each of the videoconferencing terminals in the first multi-point videoconferencing session is connected to the MCN according to the second virtual studio policy for at least one tag.
-
公开(公告)号：US10972702B2
公开(公告)日：2021-04-06
申请号：US16898879
申请日：2020-06-11
Applicant: Pexip AS
Inventor： Eamonn Shaw
Abstract: The present invention creates compositions of pictures in multipoint conferences that emulate natural interaction and existing aesthetic sensibilities learned from visual media by a combination of correcting and adapting the composition of the picture content and the layout, preferably in the MCN of the conference, where real-time conference data is available, in addition to statistics and knowledge of historical conference data. Further, cross checking incoming imagery against a ruleset where compositional deltas are identified is done, and these corrective transformations are applied, and the resulting corrections and remixes are applied to the layout. More advanced transformations to the final composition based on presence and context define a layout. The ruleset could be both static and dynamic, or a combination, and the final recomposition of the layout may be a result of both corrective and adaptive transformations.
-
公开(公告)号：US20210029327A1
公开(公告)日：2021-01-28
申请号：US16898879
申请日：2020-06-11
Applicant: Pexip AS
Inventor： Eamonn Shaw
Abstract: The present invention creates compositions of pictures in multipoint conferences that emulate natural interaction and existing aesthetic sensibilities learned from visual media by a combination of correcting and adapting the composition of the picture content and the layout, preferably in the MCN of the conference, where real-time conference data is available, in addition to statistics and knowledge of historical conference data. Further, cross checking incoming imagery against a ruleset where compositional deltas are identified is done, and these corrective transformations are applied, and the resulting corrections and remixes are applied to the layout. More advanced transformations to the final composition based on presence and context define a layout. The ruleset could be both static and dynamic, or a combination, and the final recomposition of the layout may be a result of both corrective and adaptive transformations.
-
-
-
-
Search Results
5
records
(took 0.014 seconds)
