Objective assessment method based on voice enhancement algorithm subjective assessment

An objective evaluation and speech enhancement technology, applied in speech analysis, instruments, etc., to achieve good performance

Inactive Publication Date: 2009-12-23
NANJING UNIV
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] At present, there is no objective evaluation method similar to the present invention, which adopts the combination of PESQ, LLR, CEP, fwSNRseg and fwSNRsegVar for the speech enhancement algorithm

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
  • Objective assessment method based on voice enhancement algorithm subjective assessment
  • Objective assessment method based on voice enhancement algorithm subjective assessment
  • Objective assessment method based on voice enhancement algorithm subjective assessment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In the following, the minimum mean square error short-term spectral amplitude estimation method (MMSE), spectral subtraction (Specsub), Wiener filter method based on prior SNR estimation (Wiener_as), subspace method (KLT), and minimum mean square error The logarithmic short-term spectral magnitude estimation method (logMMSE) and the minimum mean square error logarithmic short-term spectral magnitude method (logMMSE_ne) algorithm based on prior SNR estimation and the SNR in the standard speech library NOISEUS are 10dB and 5dB 60 groups of voices of car noise are taken as an example, and the implementation of the present invention is described in detail.

[0029]The 60 groups of voices in the standard voice library NOISEUS with signal-to-noise ratios of 10dB and 5dB car noise are respectively processed by MMSE, Specsub, Wiener_as, logMMSE, KLT, logMMSE_ne algorithms, and each group of noise-reduced voices and pure voices is processed according to the MATLAB program Calcul...

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 an objective assessment method based on voice enhancement algorithm subjective assessment. The method is a new objective combination method proposed by utilizing multi-linear regression analysis based on five voice enhancement objective assessment methods as follows: PESQ, LLR, CEP, fwSNRseg and fwSNRsegVar. An objective score for assessing the quality of a voice signal, an objective score for assessing the quality of background noise and an objective score for assessing overall quality are obtained by the combinations of different weighting coefficients and five objective methods. The subjective and objective correlation coefficients of the method are superior to a plurality of other traditional objective algorithms, the standard deviation of error is lower, and the assessment of performance of the voice enhancement algorithm is easier, therefore, the invention has great practical value.

Description

1. Technical field [0001] The invention relates to an objective evaluation method for measuring speech enhancement, in particular to an objective combination method proposed by multiple linear regression analysis. The method has a higher subjective-objective correlation coefficient and a lower error standard deviation, and can more accurately evaluate the performance of speech enhancement algorithms. 2. Background technology [0002] Speech enhancement is a technology that extracts useful speech signals from noise backgrounds and suppresses or reduces noise interference. Since people are the ultimate recipients of speech, subjective evaluation is the true reflection of speech quality and the most reliable method for evaluating speech enhancement effects. But in the case of low signal-to-noise ratio, the speech enhancement algorithm may degrade the speech signal in the process of suppressing the background noise. ITU-T P.835 guides the listeners to score the speech signal (...

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): G10L21/02
Inventor 周璐邱小军林志斌
Owner NANJING UNIV
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