Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Voice quality evaluation method and device

A voice quality, voice signal technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problem of low accuracy of voice quality assessment

Active Publication Date: 2014-04-16
HUAWEI TECH CO LTD
View PDF5 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the embodiment of the present invention provides a method and device for voice quality assessment to solve the problem of low accuracy of voice quality assessment

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
  • Voice quality evaluation method and device
  • Voice quality evaluation method and device
  • Voice quality evaluation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 3

[0087] Next, Embodiment 3 of the present invention will be described, wherein the sampling rate of the speech signal is 16KHz.

[0088] For a speech signal with a sampling rate of 16kHz, a filter bank with 30 subbands can be defined in step S72. Therefore, the input signal can be separated into 30 sub-band signals, and N=30 at this time. N can be changed according to needs, for example, to process the signal more finely without considering the complexity, or design a human ear filter bank with N being 60. Therefore, choosing N to be 30 here is only an example, and is a preferred value in the embodiment of the present invention.

[0089] For the subband signal s of the kth subband k (n), calculate its corresponding time-domain envelope, and obtain the corresponding first signal:

[0090] (Formula 1)

[0091] in, for s k Hilbert transform of (n).

[0092] Figure 9A to Figure 9B Respectively, a speech signal in the 8th sub-band signal and the waveform diagram of the c...

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 relates to a voice quality evaluation method which includes the steps of conducting human ear auditory sense modeling processing on voice signals to obtain first signals, conducting resolution-ratio-variable time-frequency analysis on the first signals to obtain second signals, and conducting feature extraction and analysis based on the second signals to obtain voice quality evaluation results for the voice signals. According to the technical scheme, the problem that the accuracy of the voice quality evaluation is not high is solved; human ear auditory sense modeling processing is carried out, the signals to be detected are converted into time-frequency signals capable of showing the variable resolution ratio, the time-frequency signals with the variable resolution ratio are further analyzed, features corresponding to the signals are extracted, further analysis is carried out, and therefore the high-accuracy voice quality evaluation results are finally obtained.

Description

technical field [0001] The present invention relates to the field of audio technology, more particularly to a method and device for voice quality assessment. Background technique [0002] In the field of audio technology research, subjective testing is an important link. In accordance with industry guidelines (for example: ITU-T P.800), a series of audio sequences are listened to by organizing several testers; finally, the average trend of the quality of the statistical testers is generally expressed as MOS (English is Mean Opinion Score), the high or low score reflects the good or bad of the relevant audio technology. [0003] However, the subjective test has the disadvantages of long experimental cycle and high economic cost; in the middle stage of an audio algorithm research, it is unrealistic to organize a large number of subjective tests. Therefore, the significance of studying objective testing tools becomes very obvious. From a methodological point of view, objecti...

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): G10L25/69G10L15/02G10L15/06G10L21/0224
CPCG10L25/69G10L25/60G10L17/04G10L21/02
Inventor 肖玮
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com