Quasi-clean voice construction method for voice quality objective evaluation

A technology for clean speech and objective evaluation, applied in speech analysis, instruments, etc., can solve problems such as unfavorable real-time estimation, reduce algorithm efficiency, increase computational complexity, etc., to eliminate noise parts, improve accuracy, and accurately estimate noise power spectrum. Effect

Active Publication Date: 2015-01-07
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the minimum control recursive averaging algorithm uniformly estimates the distorted speech when estimating and updating the noise spectrum, and does not distinguish the speech segment from the non-speech segment of the distorted speech, so there is a certain gap between the estimation result and the actual noise power spectrum. , and the unified estimation of the distorted speech noise spectrum increases the computational complexity, reduces the efficiency of the algorithm, and is not conducive to real-time estimation

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
  • Quasi-clean voice construction method for voice quality objective evaluation
  • Quasi-clean voice construction method for voice quality objective evaluation
  • Quasi-clean voice construction method for voice quality objective evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] A quasi-clean speech construction method for objective evaluation of speech quality, comprising the steps of:

[0040] 1. Carry out framing and windowing on the distorted speech (frame length 30ms, frame shift 15ms, plus Hamming window), calculate the short-term energy and zero-crossing rate of each frame respectively; then calculate the average energy of the distorted speech, the energy upper threshold, Energy lower threshold, average zero-crossing number, and zero-crossing number threshold. The upper energy threshold is 0.05 times the average energy; the lower energy threshold is 0.25 times the upper energy threshold; the zero-crossing threshold is 0.3 times the average zero-crossing number.

[0041] 2. Adopt the double-threshold method based on energy and zero-crossing rate to determine the start frame and the end frame of the distorted voice segment; use the above-mentioned determined distorted voice segment as the input data of the sohn voice activity detection alg...

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 quasi-clean voice construction method for voice quality objective evaluation. An improved minimum value control recursion average algorithm and a multi-spectrum subtraction are adopted to obtain quasi-clean voice of distorsion voice. The method mainly comprises the steps of (1) distinguishing a voice segment and a non-voice segment of the distorsion voice; (2) respectively evaluating noise power spectrums of the voice segment and the non-voice segment according to the division of the voice segment and the non-voice segment; (3) calculating the quasi-clean voice power spectrum of the distorsion voice according to noise spectrum evaluation values of the non-voice segment and the voice segment. The quasi-clean voice construction method for voice quality objective evaluation has the advantages that the quasi-clean voice and the distorsion voice serve as input voice of a PESQ algorithm, and an objective evaluation value of the distorsion voice is obtained.

Description

technical field [0001] The invention relates to an objective speech quality evaluation technology, in particular to a quasi-clean speech construction method for the speech quality objective evaluation, and the speech construction method belongs to the field of non-intrusive speech quality objective evaluation. Background technique [0002] Voice quality is one of the important criteria for evaluating the quality of a voice communication system. Voice quality evaluation is generally divided into subjective evaluation methods and objective evaluation methods. The subjective evaluation method relies on the opinions of the listeners to make a judgment on the voice quality, which directly reflects the user's point of view on the quality of the system. Among them, the MOS (Mean Opinion Score) proposed by ITU-T Recommendation P.830 is a widely used subjective evaluation method. However, the subjective evaluation method has poor repeatability, is difficult to organize and implemen...

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): G10L25/60G10L21/0216
Inventor 贺前华周伟力李洪韬
Owner SOUTH CHINA UNIV OF TECH
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