Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for distinguishing voice and apparatus

A technology for discriminating devices and human voices, applied in speech analysis, instruments, etc., can solve the problems of occupying too many software and hardware resources, complexity, and large amount of calculation, and achieve the effect of small amount of calculation and storage space

Active Publication Date: 2009-02-04
合肥炬芯智能科技有限公司
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1: Feature parameters such as energy value, zero-crossing rate, and autocorrelation coefficient cannot well reflect the difference between human voice and non-human voice, resulting in poor detection results;
[0006] 2: The method of calculating linear predictive cepstral coefficients or Mel frequency cepstral coefficients, and then using template matching technology to identify vocals is too complicated, the amount of calculation is too large, it needs to occupy too many software and hardware resources, and the feasibility is not good

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
  • Method for distinguishing voice and apparatus
  • Method for distinguishing voice and apparatus
  • Method for distinguishing voice and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Before describing the specific implementation of the present invention, the principle on which the solution of the present invention is based is firstly introduced. Figure 1 to Figure 3 An example of three time-domain waveform diagrams is given. The abscissa in the figure is the label of the sampling point of the audio signal, and the ordinate is the relative intensity of the sampling point, and the sampling rate is 44100. In the following diagrams, the sampling rate is 44100. in, figure 1 is the time-domain waveform diagram of pure human voice; figure 2 is the time-domain waveform diagram of pure music; image 3 It is the time-domain waveform diagram of popular music that people sing, which can be regarded as the superimposed effect of human voice and music.

[0031] Observed Figure 1 to Figure 3 It can be found that the time-domain diagram of the human voice is significantly different from the time-domain diagram of the non-human voice. The human voice is cade...

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 human voice distinguishing method which includes the steps: the slide maximum absolute value of the audio signal inputted from the exterior is computed; the maximum absolute value is judged if the maximum absolute value has the transition relative to the distinguishing threshold value; if so, the transition times in the unit time is further judged; the time interval between the twice transition is judged if the time interval satisfies the preset condition; if so, the audio signal is human voice. The invention also discloses a human voice distinguishing device. The technical proposal of the invention can accurately distinguish the human voice in the audio signal with small computation cost.

Description

technical field [0001] The invention relates to the technical field of audio processing, in particular to a method and device for human voice discrimination. Background technique [0002] Human voice discrimination, as the name suggests, is to determine whether there is a human voice in the audio signal. Human voice discrimination has its special application environment and requirements. On the one hand, there is no need to know what the speaker is saying, only whether someone is speaking; on the other hand, it is necessary to distinguish the human voice in real time. In addition, it is also necessary to consider the overhead of system software and hardware, and reduce the requirements of software and hardware as much as possible. [0003] The existing human voice discrimination technology mainly includes the following two methods: one is to start from the feature parameters of the extracted audio signal, and use the difference between the feature parameters when there 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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L11/02G10L25/78
CPCG10L25/78
Inventor 谢湘勇陈展
Owner 合肥炬芯智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com