Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multi-channel audio quality evaluation method based on two layers of models

A technology of audio quality and evaluation method, which is applied in speech analysis, instruments, etc., can solve the problem of low correlation of subjective evaluation scores, and achieve the effect of good accuracy and high correlation

Inactive Publication Date: 2017-09-15
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the correlation between the existing multi-channel audio quality objective evaluation result and the subjective evaluation score is too low, to provide a multi-channel audio quality evaluation method based on a two-layer model, which improves the objective evaluation method the accuracy of

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
  • Multi-channel audio quality evaluation method based on two layers of models
  • Multi-channel audio quality evaluation method based on two layers of models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0027] In the following embodiments, for the convenience of description, 5.1-channel audio is selected for multi-channel audio. The method of the present invention is also applicable to the quality evaluation of other multi-channel audio, and can obtain the same beneficial technical effect. Specifically, since 5.1-channel audio is widely used in current practice, and is generally considered to be a surround sound system that requires the least number of speakers, the 5.1-channel audio file is used as the model training and testing sound source in the example. . Subjective quality scores obtained through subjective listening tests are used as training and test sets for the objective model.

[0028] The method steps of the present invention are as follows figure 1 shown, as follows:

[0029] (a) Input the audio to be tested and the reference a...

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 multi-channel audio quality evaluation method based on two layers of models, and belongs to the technical field of multi-channel audio quality evaluation. The method comprises the following steps: firstly, processing to-be-tested audio frequency and reference audio frequency by virtue of two objective models, namely an objective basic sound quality model and an objective spatial quality model, which are obtained by implementing training in accordance with a subjective listening test result, in the first layer, so as to calculate out objective basic sound quality scores and spatial quality scores; and then, inputting the scores, as independent variables, into an overall objective model which is obtained by implementing training in accordance with the subjective listening test result, so as to finally obtain overall objective scores of the to-be-tested audio frequency; therefore, evaluation of multi-channel audio quality is achieved. The method provided by the invention, in comparison with original single-layer models, is not only conducive to testers to understand quality information of the to-be-tested audio frequency in more detail but also better in accuracy.

Description

technical field [0001] The invention belongs to the technical field of multi-channel audio quality evaluation, and relates to a multi-channel audio quality evaluation method based on a two-layer model. Background technique [0002] In recent years, with the increasing development of multimedia technology, multi-channel audio has gradually entered people's daily life. Compared with traditional two-channel stereo, multi-channel audio can provide listeners with a better sound quality experience and a better immersive experience, so it is widely used in various scenarios, such as stereoscopic movies, 3D games, and real-time video conferences. and many more. This has led to a higher standard for multi-channel audio processing technology. In order to evaluate the effect of audio technology, the commonly used method is to evaluate the processed audio signal, and to obtain the effect evaluation of the corresponding technology by comparing the quality difference of the audio files ...

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): G10L25/69G10L25/60G10L25/27G10L19/008
Inventor 王晶谢湘刘继月刘敏费泽松
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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
Eureka Blog
Learn More
PatSnap group products