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

Music noise suppression method and device thereof

A music noise and voice technology, applied in the field of music noise suppression methods and devices, can solve the problems of VAD detection accuracy and affecting voice components, etc.

Active Publication Date: 2018-12-07
CHINA ACAD OF TELECOMM TECH
View PDF18 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a music noise suppression method and device to solve the problems of existing music noise suppression schemes, such as relying on SNR estimation, affecting speech components, and relying on VAD detection accuracy, etc.

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
  • Music noise suppression method and device thereof
  • Music noise suppression method and device thereof
  • Music noise suppression method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0095] The technology related to the present invention will be described in detail below.

[0096] In voice communication systems, background noise severely impairs speech quality and intelligibility, and increases listener fatigue. For this reason, many effective methods for the enhancement of noisy speech signals have been studied and proposed. Among many speech enhancement techniques, spectral subtraction is widely used because of its simplicity and ease of implementation. This method is based on the viewpoint that the short-term amplitude of the speech signal is more important than the short-term phase. The spectral amplitude of the enhanced speech is obtained by directly subtracting the spectral amplitude of the noise from the spectral amplitu...

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 provides a music noise suppression method and a device thereof, wherein the music noise suppression method and the device thereof relate to the field of voice signal processing technology. The music noise suppression method comprises the steps of acquiring a characteristic parameter which is associated with the voice activity degree of a digital voice input signal; according to the characteristic parameter, acquiring a smoothing factor which is used for performing smoothing processing on a cepstrum that corresponds with an initial gain function for enhancing the digital voice input signal; and performing smoothing processing on the cepstrum which corresponds with the initial gain function, and obtaining a final gain function which corresponds with the smoothing-processed cepstrum and is used for enhancing the digital voice input signal. The music noise suppression method and the device thereof can effectively suppress the music noise in an output signal after enhancing ofthe digital signal, thereby further improving a voice hearing perception effect after enhancing processing.

Description

technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a music noise suppression method and device. Background technique [0002] Many digital speech enhancement algorithms use adaptive spectral gain functions to modify the signal spectrum amplitude. These algorithms are prone to short-term singular spectral peaks. These short-term singular spectral peaks induce the appearance of musical noise in the enhanced digital speech signal. Thus affecting the quality of the voice communication system. [0003] Although the existing technical solutions have a certain suppression effect on music noise, their defects cannot be ignored. Although the soft gain spectrum weighting method can suppress music noise to a certain extent, it is very sensitive to the estimation error of noise power spectral density and signal-to-noise ratio (SNR), so it cannot achieve a good effect of suppressing music noise; in order to improve The soft...

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): G10L21/0208G10L25/24G10L25/03
CPCG10L21/0208G10L25/03G10L25/24
Inventor 李佳芮梁民
Owner CHINA ACAD OF TELECOMM TECH
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