Voice activation detecting system used for video conference system

A technology for voice activity detection and video conference system, which is applied in video conference system, voice analysis, two-way work system, etc., can solve the problem of inaccurate voice activity detection effect, and achieve good detection effect, easy implementation, and robust signal-to-noise ratio. great effect

Active Publication Date: 2020-01-14
西安合谱声学科技有限公司
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a voice activity detection system for a video conferencing

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice activation detecting system used for video conference system
  • Voice activation detecting system used for video conference system
  • Voice activation detecting system used for video conference system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0047] Example

[0048] In this embodiment, a voice activity detection system for a video conferencing system is disclosed, such as figure 1 and figure 2 shown. It should be noted that the voice activity detection method in the present invention can also be applied to other scenarios. For example, the application scenarios of the education recording and broadcasting system, the application scenarios of the interrogation system, etc. The application of the invention can effectively distinguish the voice signal and the noise signal in the audio signal.

[0049] A voice activity detection system for a video conferencing system, comprising a voice signal acquisition module, a transient impact noise detection module, a voiced sound unvoiced classification module, a signal-to-noise ratio detection module, a voice presence probability detection module, and a noisy voice signal energy detection module and the final judgment module;

[0050] The voice signal acquisition module is...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the field of voice signal processing, and discloses a voice activation detecting system used for a video conference system. According to the voice activation detecting system,transient impulse noise detection and voiced/unvoiced classification are respectively carried out on obtained noisy time-domain signals, and based on voice existence probabilistic detection, signal-to-noise ratio detection and energy detection of noisy voice signals, the final voice activation detection result can be obtained through judgment results of each module. The voice activation detectingsystem has good detection effect on transient impulse noises, non-transient impulse noises and quasi-stationary noises. Compared with the prior art, the voice activation detecting system has the advantages that the detection results are robust to typical conference room noises and to the signal-to-noise ratio, and the algorithm is low in computational complexity and easy to implement.

Description

technical field [0001] The invention belongs to the field of voice signal processing, and in particular relates to a voice activity detection system used in a video conference system. Background technique [0002] Usually, in a video conferencing system, the camera will rotate according to the angle given by the positioning algorithm to obtain the video of the current speaker. However, there are various sources of interference in a meeting room environment at any time. When the interference source exists, if the camera turns to the direction of the interference source, it will give participants a very bad experience. At this time, we need to perform voice activity detection on the current signal. If a voice signal is detected, the camera turns to the angle given by the positioning algorithm. If no voice signal is detected, the camera remains motionless. [0003] Typical interference sources in a conference room environment fall into two categories. The first category is ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G10L25/84G10L25/93G10L21/0216G10L21/0208H04N7/15
CPCG10L25/84G10L25/93G10L21/0216G10L21/0208H04N7/15G10L2025/783G10L2021/02166G10L2021/02082
Inventor 王向辉黄绍锋靳冠军张升辉刘晓霞
Owner 西安合谱声学科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products