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

Speech noise suppression method and device

A technology of noise suppression and voice, applied in the field of voice noise suppression methods and devices, can solve the problems of low voice noise reduction efficiency and poor noise suppression effect, and achieve the goal of improving speed and accuracy, improving effect, improving effect and efficiency Effect

Inactive Publication Date: 2018-11-06
台州智歌电子科技有限公司
View PDF9 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the embodiments of the present invention is to provide a speech noise suppression method and device to solve the problems of low speech noise reduction efficiency and poor noise suppression effect in the above-mentioned existing speech enhancement methods

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 noise suppression method and device
  • Speech noise suppression method and device
  • Speech noise suppression method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0030] According to the research of the applicant, it is found that the voice information will be interfered by various scene noises during voice recording in real life, while the traditional noise reduction scheme is usually based on a general noise reduction model, and is not based on the acoustics of actual voice recording. The scene adjusts the parameters of each algorithm in the general noise reduction model, the noise reduction effect is poor, and there may be a lot of noise left. In order to solve the above problems, the first embodiment of the present invention provides a speech noise suppression method.

[0031] Please refer to figure 1 , figure 1 It is a flow chart of a speech noise suppression method provided in the first embodiment of the present invention. The speech noise suppression method is applied to any type of electronic equipment capable of processing speech information, and the steps of the speech noise suppression method can be as follows:

[0032] St...

no. 2 example

[0071] In order to better implement the speech noise suppression method provided in the first embodiment of the present invention, the second embodiment of the present invention further provides a speech noise suppression apparatus 100 .

[0072] Please refer to Figure 4 , Figure 4 It is a block diagram of a speech noise suppression device provided by the second embodiment of the present invention.

[0073] The speech noise suppression device 100 includes an acoustic scene determination module 110 , a parameter adjustment module 120 , and a noise processing module 130 .

[0074] Optionally, the speech noise suppression device 100 further includes a speech activity detection module 101 , a noise analysis module 102 and a speech signal output module 140 .

[0075] The voice activity detection module 101 is configured to acquire a voice activity detection result of the frequency domain voice signal.

[0076] A noise analysis module 102, configured to calculate and obtain a n...

no. 3 example

[0083] Please refer to Figure 5 , Figure 5 The third embodiment of the present invention provides a structural block diagram of an electronic device applicable to the embodiments of the present application.

[0084] The electronic device 200 may include a speech noise suppression apparatus 100 , a memory 201 , a storage controller 202 , a processor 203 , a peripheral interface 204 , an input and output unit 205 , an audio unit 206 , and a display unit 207 .

[0085] The memory 201, storage controller 202, processor 203, peripheral interface 204, input and output unit 205, audio unit 206, and display unit 207 are electrically connected to each other directly or indirectly to realize data transmission or interact. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The speech noise suppression device 100 includes at least one software function module that can be stored in the memory 201 in the fo...

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 noise suppression method and device, and relates to the technical field of speech signal processing. The speech noise suppression method firstly determines an acousticscene corresponding to a frequency domain speech signal according to a noise estimation result and a signal to noise ratio of the frequency domain speech signal, performs parameter adjustment on a noise processing model according to the acoustic scene, and then performs speech enhancement on the frequency domain speech signal according to the adjusted noise processing model. The speech noise suppression method adjusts the noise processing model based on a plurality of acoustic scenes to perform speech enhancement, so that the noise suppression has scene specificity, and the noise processing speed and the speech enhancement effect are improved.

Description

technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a method and device for suppressing speech noise. Background technique [0002] With the popularization of electronic devices, more and more operations or inputs require the participation of voice functions, and the refined operations of many electronic devices require higher and higher accuracy of voice input. Since voice recording is usually performed in a noisy environment, in actual application scenarios, the target voice is often disturbed by noise environment and other factors, which greatly reduces the voice clarity, intelligibility and comfort, which seriously affects human performance. The auditory experience of the ear and the analysis and processing of speech by electronic equipment, so it is often necessary to perform noise reduction processing on the recorded speech signal with noise, speech enhancement, and then output or other operations. [0003]...

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): G10L21/02G10L21/0208G10L25/18
CPCG10L21/02G10L21/0208G10L25/18G10L2021/02082
Inventor 金如利
Owner 台州智歌电子科技有限公司
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