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

Speech denoising method and device thereof

A voice denoising and voice signal technology, applied in voice analysis, instruments, etc., can solve problems such as difficulty in extracting voice signals and poor voice quality, and achieve the effects of improving quality, improving accuracy, and reducing leakage

Active Publication Date: 2020-06-09
GREE ELECTRIC APPLIANCES INC
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present application provides a voice denoising method and device to solve the technical problems in the prior art that the voice signal is difficult to extract and the quality of the extracted voice is poor

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 denoising method and device thereof
  • Speech denoising method and device thereof
  • Speech denoising method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] A method for voice denoising provided by the embodiment of the present application will be further described in detail below in conjunction with the accompanying drawings. The specific implementation of the method may include the following steps (the method flow is as follows: figure 1 shown):

[0057] Step 101 , the electronic device receives a set of noisy speech signals, and extracts Bark-frequency cepstral coefficients (Bark-frequency cepstral coefficients, BFCC) features of each noisy speech signal in the set of noisy speech signals.

[0058] There are a plurality of noisy speech signals in the set of noisy speech signals, wherein the plurality of noisy speech signals include speech signals with different noises and with different signal-to-noise ratios, for example, the different noises include pink noise, industrial noise , car noise, Gaussian noise and white noise etc. The electronic device receives a collection of noisy speech signals, and extracts BFCC featur...

Embodiment 2

[0088] This application provides a device for voice denoising, such as Image 6 shown, the device includes:

[0089] The extraction module 601 is used to receive a set of noisy speech signals, and extract the Barker frequency cepstral coefficient BFCC feature of each noisy speech signal in the collection of noisy speech signals;

[0090] Generation module 602, is used for inputting described BFCC feature in neural network GRU and trains and generates cyclic neural network RNN ​​model, wherein, described RNN model comprises the probability density function of each noise spectrum in the collection of described noisy speech signal, The probability density function of each noise spectrum and the gain compensation parameter of each speech signal;

[0091] The determination module 603 is configured to receive the speech signal to be denoised, and extract the BFCC feature of the speech signal to be denoised, and input the BFCC feature of the speech signal to be denoised into the RNN...

Embodiment 3

[0106] This application provides an electronic device, such as Figure 8 As shown, the electronic equipment, including:

[0107] memory 801, configured to store instructions executed by at least one processor;

[0108] The processor 802 is configured to execute instructions stored in the memory 801 to execute the method described in Embodiment 1.

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 speech denoising method and a device thereof. The method comprises the following steps: receiving a set of noisy speech signals; extracting BFCC features of each noisy speechsignal in the set; inputting the BFCC features into a neural network GRU for training to generate a recurrent neural network RNN model; receiving a speech signal to be denoised; extracting BFCC features of the speech signal to be denoised; inputting the BFCC features of the speech signal to be denoised into the RNN model; determining a noise spectrum in the speech signal to be denoised based on the RNN model; determining a gain compensation parameter of the speech signal in the speech signal to be denoised according to the noise spectrum in the speech signal to be denoised; and generating a denoised speech signal based on the gain compensation parameter of the speech signal and a fundamental tone signal in the speech signal to be denoised. The technical problem that in the prior art speech signals are difficult to extract, and the quality of extracted speech is poor are solved.

Description

technical field [0001] The present application relates to the technical field of speech recognition, in particular to a method and device for denoising speech. Background technique [0002] Due to the presence of a lot of noise in the urban environment, such as industrial production noise, construction noise, traffic noise, and social life noise, electronic devices, such as smart home devices or car audio devices, are affected by Due to the influence of environmental noise, the collected speech signal is not a pure speech signal, but a noisy speech signal polluted by noise. [0003] In order to recognize the speech signal from the noisy speech signal, it is necessary to denoise the speech. At present, in the environment of non-stationary noise and strong background noise, the power spectrum of the noise is estimated mainly by estimating the statistical characteristics of the noise, but when the noise power is large and the signal-to-noise ratio is low , it is easy to overe...

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): G10L21/0264G10L21/034G10L25/30G10L25/24
CPCG10L21/0264G10L21/034G10L25/30G10L25/24
Inventor 刘白皓
Owner GREE ELECTRIC APPLIANCES INC
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