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

Voice noise reduction method and device, equipment and storage medium

A voice noise reduction and voice technology, applied in voice analysis, instruments, etc., can solve the problems of weakened noise suppression ability, difficult MVDR coefficient, and inability to perform good suppression, achieving good noise reduction effect and accurate cross power spectral density Effect

Pending Publication Date: 2022-03-25
西安讯飞超脑信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, when the signal-to-noise ratio of the received signal of the dual microphones is relatively low, the calculation of the cross-power spectral density of the steering vector and noise is inaccurate, making it difficult to accurately calculate the MVDR coefficient, resulting in weakened noise suppression capabilities
In addition, beamforming adjusts the MVDR coefficients so that the beam can suppress noise in a different direction from the target speech (which can be understood as the standard speech in the received signal of the microphone, that is, speech that is not noise), but for the noise in the same direction as the target speech not well suppressed

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 noise reduction method and device, equipment and storage medium
  • Voice noise reduction method and device, equipment and storage medium
  • Voice noise reduction method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0050] Speech noise reduction technology is a technology for extracting target speech from noisy speech. Speech noise reduction technology is divided into single-channel algorithm and multi-channel algorithm according to whether the channel number of the signal received by the microphone is 1 or not. Among them, although the single-channel noise reduction algorithm has the characteristics of low cost and low structural design requirements, it generally only performs well under stati...

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 noise reduction method. The method comprises the following steps: acquiring multiple paths of noisy voices; the multiple paths of noisy voices are acquired synchronously; extracting feature data of the multiple paths of noisy voices; calling a network model to process the feature data of the noisy voice to obtain a masking value of the voice, and calculating the cross-power spectral density of a steering vector and the noise by using the masking value of the voice; and processing the noisy voice by using the steering vector and the cross-power spectral density of the noise to obtain a denoised voice, so as to improve the effect of denoising the noisy voice.

Description

technical field [0001] The present application relates to the technical field of speech noise reduction methods, and more specifically, relates to a speech noise reduction method, device, device and storage medium. Background technique [0002] At present, speech noise reduction technology is a technology for extracting target speech from noisy speech. [0003] MVDR is one of the most widely used beamforming techniques today, and its principle is to try to minimize the power of the beamformed signal while maintaining unity gain in the desired direction. For the dual-channel noise reduction algorithm, the cross-power spectral density of the steering vector and the noise is calculated through the received signals of the dual microphones, and the cross-power spectral density of the steering vector and the noise is processed according to the formula to calculate the MVDR coefficient (which can be understood as a weight coefficients or beam coefficients), and then apply the MVDR...

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): G10L21/0208G10L21/0216G10L25/30
CPCG10L21/0208G10L21/0216G10L25/30G10L2021/02166G10L2021/02165
Inventor 张姣万蕊付中华
Owner 西安讯飞超脑信息科技有限公司
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