Mute detection method based on speech characteristic to jude

A silent detection and voice feature technology, applied in voice analysis, instruments, etc., can solve the problems of low recognition rate of the detection system, poor system recognition rate effect, inability to adapt to different noises, etc., and achieve good classification effect and classification The effect of high accuracy and good robustness

A silent detection and voice feature technology, applied in voice analysis, instruments, etc., can solve the problems of low recognition rate of the detection system, poor system recognition rate effect, inability to adapt to different noises, etc., and achieve good classification effect and classification The effect of high accuracy and good robustness

CN1835073AInactive Publication Date: 2006-09-20NANJING UNIV
0 Cites 31 Cited by

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Mute detection method based on speech characteristic to jude
  • Mute detection method based on speech characteristic to jude
  • Mute detection method based on speech characteristic to jude

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0026] A kind of mute detection method based on speech feature discrimination of the present invention, see figure 1 , a sampling frequency of 8kHz is used in the specific detection process, and 80 points are used as a frame for detection, and each frame is 10 milliseconds. It consists of the following steps:

[0027] (1) Extract the multi-threshold zero-crossing rate of a frame of audio data, and sum them with preferred weighted values. In step (1), the total zero-crossing rate cut-off value Z is used 0 and the optimal weight vector (W 1 , W 2 , W 3 ), their values ​​must be set before silence detection. To determine their values, at least 2000 frames of audio data in different environments are collected, half of which are silence and half are speech. Taking the silent misjudgment rate generated by multi-threshold zero-crossing rate detection as the objective...

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 discloses a voice characteristic identification-based silence detecting method, firstly extracting multi-threshold overzero rate of an audio data frame; pre-identify silence by weighting the multi-threshold overzero rate to identify obvious silence; extracting composite characteristic of an audio data frame, where the composite characteristic comprises overzero rate, short-time energy value, and variable resolution frequency spectrum-based Mel scale revere spectrum coefficient; using dichotomy support vector machine to identify the composite character of the audio frequency, one class normal voice and the other class silence. And the invention can raise success rate of silence detection and can identify some special voices, able to be widely applied to network voice talking, especially voice chatting and video meeting.

Description

1. Technical field [0001] The invention relates to an audio processing method, in particular to a method for detecting silence based on speech feature discrimination for Internet voice calls. 2. Background technology [0002] In the process of human speaking, its voice can be divided into two parts: silence and voice, and 60% of the time is silence on average. And when many people are talking, basically only one person speaks at each moment, while the others are silent. Silence and noise (including airflow noise) introduced by voice collection equipment are transmitted in the network like voice data, causing voice quality to degrade. Using the mute suppression technology, the mute part can be eliminated, which can save more than 50% of the transmission bandwidth and reduce network congestion. [0003] Existing silence detection methods include extracting audio signal eigenvalues ​​and comparing them with preset thresholds to determine silence. The parameters used in tradit...

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
20 Sep 2006
Publication
CN1835073A
IPC
G10L11/02; G10L25/78
Inventors
都思丹; 薛卫