Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech data enhancement method and device

A voice data and enhancement device technology, applied in voice analysis, instruments, etc., can solve problems such as many parameters, many resources, and complex training, and save time and disk costs.

Active Publication Date: 2022-04-15
AISPEECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of implementing this application, the inventor found that the existing solutions have at least the following defects: the training is more complicated, the parameters are more, and the actual application requires more resources

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 data enhancement method and device
  • Speech data enhancement method and device
  • Speech data enhancement method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] 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.

[0019] Please refer to figure 1 , which shows a flow chart of an embodiment of the speech data enhancement method of the present application. The speech data enhancement method of this embodiment can be applied to enhance speech data, and the present application is not limited here.

[0020] Such as figure 1 As shown, in step 101, original clean...

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 present invention discloses a speech data enhancement method and device, wherein, a speech data enhancement method includes: a speech data enhancement method, including: inputting original clean audio and noisy audio into an embedding extractor, wherein the noisy audio Including the original clean audio and noise; obtaining the clean embedding and noise embedding output by the embedding extractor; calculating the difference between the clean embedding and the noise embedding; performing distribution estimation on the difference to obtain a noise distribution Fitted noise embedding. The embodiments of the present application can reliably estimate the proposed NDM by using only a small amount of training data. Compared with traditional enhancement methods, the NDM method can save time and disk cost. NDM training results can achieve comparable effects to traditional enhancement methods, and sometimes even surpass traditional methods.

Description

technical field [0001] The invention belongs to the field of voice data enhancement, in particular to a voice data enhancement method and device. Background technique [0002] In related technologies, the laboratory already has data enhancement technology based on GAN and VAE technology. [0003] Data augmentation (DA) is an effective strategy to help construct speaker recognition systems with good generalization ability. In speaker verification based on speaker features, data augmentation can be applied to front-end feature extractor or back-end PLDA scoring. Traditional back-end data enhancement is to generate relevant data through existing feature data and generative models such as GAN and VAE to enhance the robustness of PLDA. [0004] In the process of implementing the present application, the inventor found that the existing solution has at least the following defects: the training is relatively complicated, the parameters are many, and the actual application require...

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 Patents(China)
IPC IPC(8): G10L21/02G10L17/00G10L17/02G10L17/04
CPCG10L17/02G10L17/04
Inventor 钱彦旻龚勋陈正阳杨叶新王帅
Owner AISPEECH CO LTD