Speech enhancement method, electronic equipment and storage medium

A speech enhancement and audio technology, applied in speech analysis, instruments, etc., can solve problems such as unsatisfactory model effects and inability to reuse, achieve good speech enhancement effects, and speed up the research and development progress

Pending Publication Date: 2022-04-12
AISPEECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Furthermore, in the current speech enhancement algorithm, it is impossible to reuse the related technologies that the neural network has successfully achieved in the field of graphics processing, and the nature of the problem is considered from a single perspective, which makes the model effect unsatisfactory

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, electronic equipment and storage medium
  • Speech enhancement method, electronic equipment and storage medium
  • Speech enhancement method, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0016] Please refer to figure 1 , which shows a flowchart of an embodiment of the speech enhancement method of the present application.

[0017] Such as figure 1 As shown, in step 101, the audio signal to be enhanced is converted into a bitmap;

[0018] In step 102, the bitmap is processed using a neural network image processing technology, whe...

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 enhancement method, electronic equipment and a storage medium, and the speech enhancement method comprises the steps: converting a to-be-enhanced audio signal into a bitmap; and the bitmap is processed by using a neural network image processing technology, and the neural network image processing technology comprises a neural network based on image noise reduction. The to-be-enhanced audio signal is converted into the bitmap, and then the bitmap is processed by using the neural network image processing technology, so that the voice problem can be processed from the perspective of image processing, the research and development progress can be successfully accelerated by using deep learning in the field of image processing, and further, the development efficiency is improved. The neural network based on image noise reduction obtains a better speech enhancement effect.

Description

technical field [0001] The invention belongs to the technical field of voice data processing, and in particular relates to a voice enhancement method, electronic equipment and a storage medium. Background technique [0002] In addition to the traditional methods based on strict mathematical derivation, the use of neural networks is becoming more and more common in the current speech enhancement algorithms. [0003] The usual neural network method includes converting the time-domain signal into signal features of other domains (frequency domain, BARK domain, MEL domain, etc.), and then inputting it into the neural network, and finally combining the original input signal features with the estimated gain output by the neural network. Signals in other domains are converted to processed time domain signals. [0004] Furthermore, in the current speech enhancement algorithms, it is impossible to reuse the related technologies that the neural network has successfully achieved in th...

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): G10L21/02G10L21/10G10L25/30
Inventor 陈进
Owner AISPEECH 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