Noise elimination method based on VAD and ANN

A noise removal and noise technology, applied in the field of signal processing, can solve the problem of insufficient performance of LMS algorithm

Active Publication Date: 2018-02-02
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the performance deficiency of the existing LMS algorithm in the field of noise elimination, and creatively proposes a method based on VAD and ANN that combines VAD and ANN technology to improve the convergence speed and convergence accuracy of the algorithm in the field of noise elimination. Noise Cancellation Method

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
  • Noise elimination method based on VAD and ANN
  • Noise elimination method based on VAD and ANN
  • Noise elimination method based on VAD and ANN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0058] The present invention mainly includes two parts, the first part is to use VAD technology to divide the noisy speech into speech frame and noise frame. The second part is to perform adaptive filtering with a linear neural network, perform batch training on the reference noise corresponding to the noise frame, and perform sequential training on the reference noise corresponding to the speech frame. Specific as attached figure 1 , 2 , 3 shown.

[0059] The first part of the present invention is to use the logarithmic spectrum distance method to realize VAD technology to divide the noisy speech into speech frame and noise frame. Divided into the following steps:

[0060] Step 1: Set an appropriate frame length according to the sampling frequency and noise characteristics, and perform windowing and frame processing on the noisy speech and...

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 noise elimination method based on VAD and ANN, and the method comprises the steps: firstly employing the VAD technology for dividing voice with noise into a voice frame and anoise frame; secondly carrying out the different noise reduction of the voice frame and the noise frame through ANN; thirdly employing a sequential training of the reference noise corresponding to the voice frame, and employing batch training for the reference noise corresponding to the noise frame. According to the invention, the voice with the noise is divided into the voice frame and the noiseframe through the VAD technology. Through the quick convergence and high convergence precision of the batch training of the neural networks, the method achieves the processing of the noise frame. Onethe one hand, the method enables adaptive filtering to be convergent in one piece of noise frame data; on the other hand, the method also improves the convergence precision.

Description

technical field [0001] The invention belongs to a noise elimination method, in particular to a noise elimination method based on VAD and ANN, and belongs to the technical field of signal processing. Background technique [0002] Noise elimination is a very important problem in the field of signal processing, and it is also a very difficult problem. The existence of noise has a huge impact on the normal operation of the system. Over the years, scholars have done extensive and in-depth research on noise cancellation. Noise cancellation can be generally divided into two categories: passive noise suppression and active noise cancellation. Passive noise suppression is to use physical methods to select new materials for sound absorption, sound insulation and noise reduction. This method has high cost, is not easy to maintain, and the effect is not ideal, especially the noise reduction ability for low-frequency noise is very poor. Active noise cancellation, based on the principl...

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): G10L21/0208G10L21/0216G10L25/30
CPCG10L21/0208G10L21/0216G10L25/30
Inventor 何志连韩大强李想
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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