Speech enhancement method and device based on neural network, terminal and medium

A neural network and voice enhancement technology, applied in the field of voice enhancement based on neural network, can solve problems such as voice distortion and poor user experience of voice-related products, achieve smooth quiet zone, improve voice quality, and good separation effect.

Pending Publication Date: 2021-03-26
LANZHOU JIAOTONG UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But if the oversubtraction factor is too large, it will cause speech distortion
[0010] In summary, none of the existing speech enhancement algorithms can adapt to various environments for good denoising, resulting in poor user experience for speech-related products

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
  • Speech enhancement method and device based on neural network, terminal and medium
  • Speech enhancement method and device based on neural network, terminal and medium
  • Speech enhancement method and device based on neural network, terminal and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them.

[0064] Such as image 3 As shown, in the first aspect, the application provides a neural network-based speech enhancement method, including:

[0065] S301: Obtain the multiple noisy voice signals collected by each array element of the microphone array;

[0066] There are many ways for the existing microphone array to collect voice signals. In general, an independent analog-to-digital conversion ADC is used for data collection. Control unit, clock generation unit, PC upper computer unit and storage unit. The clock generation unit provides a clock si...

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 speech enhancement method and device based on a neural network, a terminal and a medium. The method comprises the following steps: acquiring multiple paths of noisy speech signals acquired by each array element of a microphone array; unmixing the multiple paths of noisy speech signals by adopting a fast independent component analysis algorithm fastICA to obtain multiple paths of separation signals; predicting an optimal over-subtraction factor by adopting an error back propagation neural network BPNN; and according to the optimal over-subtraction factor predicted by the neural network, carrying out voice processing on the path of separation signal with the highest signal-to-noise ratio after unmixing by adopting a multi-window spectral subtraction method to obtaina voice enhancement signal. According to the invention, the BPNN is adopted to predict the optimal over-subtraction factor, so that the silence zone is smoother, and the speech quality is improved.

Description

technical field [0001] The present application belongs to the technical field of speech signal processing, and in particular relates to a neural network-based speech enhancement method, device, terminal and medium. Background technique [0002] Artificial Neural Network (ANN), referred to as neural network for short, has flourished since the end of the 20th century until today. It can simulate the connection work between neurons in the human brain and realize learning calculation. The neural network solves nonlinear problems in real life through the hierarchical connection between neurons, the hierarchical transmission and processing of data, the use of powerful mapping capabilities, and bottom-to-top learning and training. [0003] A neuron is the most basic unit in a neural network. It abstractly imitates the work of neurons in the human brain, which is equivalent to a multi-input and single-output component. The mathematical model of a neuron is as figure 1 As shown, x...

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): G10L21/0216G10L21/0264G10L21/0272G10L25/30G10L25/45
CPCG10L21/0216G10L21/0264G10L21/0272G10L25/30G10L25/45G10L2021/02166
Inventor 王春丽王园利王全宇
Owner LANZHOU JIAOTONG 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