Audiovisual information processing in videoconferencing

Patent metadata

Field	Value
Publication number	US-9736430-B2
Application number	US-201615364429-A
Country	US
Kind code	B2
Filing date	Nov 30, 2016
Priority date	Oct 8, 2015
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

Embodiments of the present invention relate to audiovisual stream processing in videoconferences. For each audiovisual stream in a videoconference, a sound level of the audiovisual stream is detected. If the sound level exceeds a predefined threshold level, the audiovisual stream is processed with a first configuration. If the sound level is below the predefined threshold level, the audiovisual stream is processed with a second configuration. The second configuration is more resource-effective than the first configuration.

First claim

What is claimed is:

1. A computer program product for processing a plurality of audiovisual streams in a videoconference, the computer program product comprising:
one or more non-transitory computer readable storage media and program instructions stored on the one or more non-transitory computer readable storage media, the program instructions comprising:
program instructions to detect a sound level of an audiovisual stream in a videoconference based on determining an average sound level of the audiovisual stream over a predefined time period, decomposing the audiovisual stream into an audio component and a video component and analyzing the audio component to determine the sound level wherein analyzing the audio component is based on at least one of sound intensity, sound pressure, sound power, sound energy density and sound loudness;
in response to the sound level exceeding a first predefined threshold level, program instructions to process the audiovisual stream with a first configuration based on a first quality level wherein exceeding the first predefined threshold level comprises determining that the sound level of the audiovisual stream does not fall below the first predefined threshold level for a sequential time period greater than a predefined threshold time period;
in response to the sound level being below the first predefined threshold level and above a second predefined sound level, program instructions to process the audiovisual stream with a second configuration based on a second quality level, wherein the second configuration is more resource-effective than the first configuration and the second quality level is lower than the first quality level wherein the first quality level and the second quality level are based on signal-to-noise ratio and at least one of frequency response, stereo crosstalk or output power;
in response to the sound level being below the second predefined sound level, program instructions to discard the audiovisual stream;
program instructions to superimpose the audio component of the audiovisual stream with audio components of further audiovisual streams associated with the videoconference wherein the further audiovisual streams are processed with the first configuration;
program instructions to combine the video component of the audiovisual stream with video components of the further audiovisual streams; and
program instructions to render the audiovisual stream in a display area, wherein an appearance of the display area is determined based on the sound level of the audiovisual stream.

Assignees

• IBM

Inventors

• Pan Yang
• Su Wei
• Zhang Yi
• Zhang Yi Jian

Classifications

• H04N21/233

  Processing of audio elementary streams {(monitoring, identification or recognition of audio in broadcast systems H04H60/58)} · CPC title

• H04N7/152 Primary

  Multipoint control units therefor · CPC title

• H04N5/91

  Television signal processing therefor · CPC title

• G10L19/167

  Audio streaming, i.e. formatting and decoding of an encoded audio signal representation into a data stream for transmission or storage purposes · CPC title

• G10L19/22

  Mode decision, i.e. based on audio signal content versus external parameters · CPC title