Speech enhancement method based on ensemble learning and noise sensing training

A speech enhancement and integrated learning technology, applied in speech analysis, instruments, etc., can solve the problem of inability to obtain noise estimation, and achieve the effect of accurate tracking

Active Publication Date: 2019-01-22
UNIV OF SCI & TECH OF CHINA
View PDF7 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the face of non-stationary and bursty noise, static noise-aware training cannot obtain accurate estimation of noise

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 based on ensemble learning and noise sensing training
  • Speech enhancement method based on ensemble learning and noise sensing training
  • Speech enhancement method based on ensemble learning and noise sensing training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0022] Embodiments of the present invention provide a speech enhancement method based on integrated learning and noise perception training, such as figure 1 As shown, it mainly includes:

[0023] 1. Training stage.

[0024] The training process is as follows figure 2 As shown, it mainly includes:

[0025] 1. Use the input noisy speech signal to train a gradient boosting decision tree model for dynamic noise perception.

[0026] In view of the ...

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 based on ensemble learning and noise sensing training. Compared with the static noise sensing training, the speech enhancement method provided by the invention has the advantage that non-stable noises can be accurately tracked, meanwhile, by utilizing the feature that a gradient boosted decision tree can spontaneously extract characteristics, noise scene coding for each time-frequency unit is obtained, then additional information of noises is provided for the deep neural network, while the traditional noise sensing training method only can obtain the amplitude information of noises. Seen from the experimental result, the method is superior to the speech enhancement method adopting static noise sensing training.

Description

technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a speech enhancement method based on integrated learning and noise perception training. Background technique [0002] Ensemble learning is the integration of multiple weak prediction models to finally obtain a model with strong prediction ability; it can be used for classification, regression, and feature selection. In general, ensemble learning models outperform individual models in both predictive accuracy and generalization ability, and are widely used in industry. Gradient Boosting Decision Tree (GBDT) is a commonly used ensemble learning model. Based on the boosting idea in ensemble learning, a series of decision trees are trained iteratively, and a new decision tree is established in the gradient direction of the residual error for each iteration. , the final prediction value is the sum of the decision tree prediction values ​​generated by all iterations. ...

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): G10L21/02G10L21/0216G10L21/0232G10L25/30
CPCG10L21/02G10L21/0216G10L21/0232G10L25/30
Inventor 王兮楼郭武
Owner UNIV OF SCI & TECH OF CHINA
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