Unlock instant, AI-driven research and patent intelligence for your innovation.

Voice detection method of noise robustness based on hidden semi-Markov model

A speech detection and noise technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as lack of robustness

Inactive Publication Date: 2010-08-18
BEIHANG UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention: traditional voice detection lacks robustness in noisy environments, and a noise-robust voice detection method based on a hidden semi-Markov model is provided under different signal-to-noise ratios and different noise environments

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 detection method of noise robustness based on hidden semi-Markov model
  • Voice detection method of noise robustness based on hidden semi-Markov model
  • Voice detection method of noise robustness based on hidden semi-Markov model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0051] First, the principle of the present invention will be described.

[0052]The mechanism of human vocalization is that the vocal cords are vibrated by a certain external force, and then coordinated and formed by a series of resonating organs. Therefore, the whole process of vocalization can be considered as a life cycle, and subject to the constraints of the characteristics of human organs, the life cycle of vocalization can be considered to have certain statistical laws. This statistical law is usually noise robust, that is, human voice can be considered not to be affected by the noise in the environment. Therefore, an accurate description of this statistical law will make the modeling of speech activities in a noisy environment more in line with the actual situation and improve Noise Robustness for Speech Detection. Birnbaum-Saunders distributio...

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 detection method of noise robustness based on a hidden semi-Markov model, which comprises the following steps: (1) building the hidden semi-Markov model lambda= (A, B, pi and tau); (2) initializing parameters of pi and tau in the hidden semi-Markov model lambda; (3) carrying out DCT transformation on non-empty input signals; (4) estimating the parameters of B and a likelihood ratio test threshold respectively by utilizing front multi-frame input signals and a likelihood ratio, carrying out likelihood ratio test and finishing the voice detection; and (5) regulating the parameters of B and the likelihood ratio test threshold dynamically. The method regulates the parameters and the test threshold of the model dynamically according to the time-delay feature of voice and noise and realizes the real-time voice detection of noise robustness by utilizing the likelihood ratio test to carry out the voice detection.

Description

field of invention [0001] The invention relates to a noise robust speech detection method based on a hidden semi-Markov model under the category of speech signal processing in a noisy environment. Background of the invention [0002] Speech detection is used to detect the speech part and the noise part in the signal, and has been widely used in the fields of speech coding, transmission, speech enhancement and speech recognition. The methods based on statistical models have also achieved good detection results, but the detection results of these methods fluctuate greatly under different noise types and different signal-to-noise ratio environments. In practical applications, the noise environment is diverse and unavoidable, so noise robustness has become a hot spot in speech detection. Proposing a robust speech detection algorithm that adapts to different noise environments is of great significance for speech coding, enhancement, recognition and other applications. Contents...

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): G10L15/14
Inventor 刘祥龙梁苑单宝松楼奕华李未
Owner BEIHANG UNIV