Voice de-noising method

A speech noise reduction and speech technology, which is applied in speech analysis, speech recognition, instruments, etc., can solve problems such as large errors and reduce the signal-to-noise ratio of input signals, and achieve the effect of improving the signal-to-noise ratio and reducing errors.

Inactive Publication Date: 2010-10-20
TIANJIN UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, if this method is simply used in practical applications, large errors will b

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 de-noising method
  • Voice de-noising method
  • Voice de-noising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0032] In order to obtain the voice signal more accurately and improve the signal-to-noise ratio of the output signal, an embodiment of the present invention provides a voice noise reduction method, see figure 1 , the content of the method is as follows:

[0033] The voice noise reduction method provided by the embodiment of the present invention is based on voice activity detection (Voice Activity Detection, VAD) technology and noise spectrum subtraction technology. VAD technology was first applied to the speech recognition system. By accurately judging the starting point and ending point of words and phrases, the parameter information in the speech can be better extracted and compared with the parameter information in the speech data...

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 de-noising method, which relates to the field of voice de-noising. The method comprises the following steps of: acquiring initial and final positions of a voice section by adopting voice endpoint detection, and tracking the change of noise in a mode of updating a noise spectrum in real time when the voice section does not exist. Because power spectrum subtraction is generally performed by adopting the latest updated noise spectrum at the voice section, the error caused by continuous slow change of the noise can be furthest reduced; and meanwhile, the shortest length limitation of the noise is set after the dynamic detection of the voice so as to furthest avoid the condition of error noise average power spectrum statistics caused by falsely detecting the voice as the noise at the continuous voice section, further acquire more accurate voice signals, improve the signal-to-noise ratio of the output signals and meet the requirement in practical application.

Description

technical field [0001] The invention relates to the field of voice noise reduction, in particular to a voice noise reduction method applied to the environment where the noise spectrum in the vehicle changes slowly. Background technique [0002] With the development of science and technology, the noise pollution in the cockpit of modern vehicles has become a topic of concern. How to minimize the noise pollution caused by engine operation, airflow and body friction, and air-conditioning fans in such a relatively closed environment, so as to obtain a satisfactory environment for rest and voice communication, has become a research hotspot at home and abroad. [0003] In response to this requirement, it is necessary to adopt a signal-to-noise separation technology aimed at improving the Signal to Noise Ratio (SNR) of in-vehicle speech. To this end, wavelet-based noise detection technology, microphone array-based noise reduction method, and noise-spectrum subtraction-based signal...

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): G10L21/02G10L11/02G10L15/05G10L21/0208
Inventor 张涛李海张雯赵亮冯砚儒
Owner TIANJIN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap