公开(公告)号：US20250159108A1

公开(公告)日：2025-05-15

申请号：US18509489

申请日：2023-11-15

Applicant: Cisco Technology, Inc.

Inventor： Bjørn Winsvold ,  Asbjørn Therkelsen

IPC: H04N7/15 ,  G06T3/40 ,  G06T5/00 ,  G06V40/16

Abstract: Video is obtained in a video conference session that includes one or more participants in a video conference room, wherein the video conference room includes a video display and a one video camera, and wherein a participant is remote with respect to the video conference room. During the video conference session, it is determined that video captured by the camera in the video conference room includes a face of a person not physically present in the video conference room and which face is displayed on the video display. Video of each participant in the video conference room is assigned to a respective video layout window except for video of the face of the person not physically present in the video conference room that is displayed on the video display.

公开(公告)号：US20200043509A1

公开(公告)日：2020-02-06

申请号：US16598059

申请日：2019-10-10

Applicant: Cisco Technology, Inc.

Inventor： Eric Chen ,  Asbjørn Therkelsen ,  Espen Moberg ,  Wei-Lien Hsu

IPC: G10L21/0216 ,  G10L25/30 ,  G06F17/18 ,  G06N7/00 ,  G06N20/00

Abstract: This disclosure relates to solutions for eliminating undesired audio artifacts, such as background noises, on an audio channel. A process for implementing the technology can include receiving a set of audio segments, analyzing the segments using a first ML model to identify a first probability of unwanted background noises in the segments, and if the first probability exceeds a threshold, analyzing the segments using a second ML model to determine a second probability that the one or more background features exist in the segments. In some aspects, the process can include attenuating audio artifacts in the segments, if the second probability exceeds a second threshold. In some implementations, dynamic time stretching and shrinking can be applied to the noise attenuation. Systems and machine-readable media are also provided.

公开(公告)号：US20220007129A1

公开(公告)日：2022-01-06

申请号：US17240380

申请日：2021-04-26

Applicant: Cisco Technology, Inc.

Inventor： Asbjørn Therkelsen ,  Marcus Widmer

IPC: H04S7/00 ,  H04L29/06

Abstract: In various embodiments, a collaboration endpoint transmits an ultrasonic signal into an area based on a frequency sweep. The collaboration endpoint receives a reflected signal that comprises the ultrasonic signal reflected off an object located in the area. The collaboration endpoint detects, based on the reflected signal, the object as being a potential user. The collaboration endpoint determines, based on the reflected signal, a distance from the collaboration endpoint to the potential user. The collaboration endpoint initiates, based on the distance from the collaboration endpoint to the potential user, a wake-up sequence of the collaboration endpoint to exit a standby mode.

公开(公告)号：US10992905B1

公开(公告)日：2021-04-27

申请号：US16919282

申请日：2020-07-02

Applicant: Cisco Technology, Inc.

Inventor： Asbjørn Therkelsen ,  Marcus Widmer

IPC: H04N7/15 ,  G01S15/66 ,  G01S15/04

Abstract: In various embodiments, a collaboration endpoint transmits an ultrasonic signal into an area. The collaboration endpoint receives a reflected signal that comprises the ultrasonic signal reflected off an object located in the area. The collaboration endpoint detects, based on the reflected signal, the object as being a potential user. The collaboration endpoint determines, based on the reflected signal, a distance from the collaboration endpoint to the potential user. The collaboration endpoint initiates, based on the distance from the collaboration endpoint to the potential user, a wake-up sequence of the collaboration endpoint to exit a standby mode.

公开(公告)号：US10446170B1

公开(公告)日：2019-10-15

申请号：US16012565

申请日：2018-06-19

Applicant: Cisco Technology, Inc.

Inventor： Eric Chen ,  Asbjørn Therkelsen ,  Espen Moberg ,  Wei-Lien Hsu

IPC: G10L21/0216 ,  G10L25/30 ,  G06F17/18 ,  G06N7/00 ,  G06N20/00

Abstract: This disclosure relates to solutions for eliminating undesired audio artifacts, such as background noises, on an audio channel. A process for implementing the technology can include receiving a set of audio segments, analyzing the segments using a first ML model to identify a first probability of unwanted background noises in the segments, and if the first probability exceeds a threshold, analyzing the segments using a second ML model to determine a second probability that the one or more background features exist in the segments. In some aspects, the process can include attenuating audio artifacts in the segments, if the second probability exceeds a second threshold. In some implementations, dynamic time stretching and shrinking can be applied to the noise attenuation. Systems and machine-readable media are also provided.