Objective Quality Measurement in Multi-channel Audio Systems by Multivariate Adaptive Regression Splines Model

DOI

10.2991/wcnme-19.2019.7How to use a DOI?

Keywords

multivariate adaptive regression spline; subjective quality; monaural feature; binaural feature

Abstract

Objective quality assessment methods have been used widely for evaluation of audio systems. This article introduces a new method to show the relationship between the input parameters and the prediction targets of the multivariate adaptive regression splines (MARS) model. In this proposed method, the relatively frequency of each input variables selected by the MARS model as useful predictors is calculated. The MARS model is trained and tested by the ITU DB4 database which is generated by ITU-R WP6C in order to evaluate the high-quality multichannel audio coding approaches. The under-test input parameters consist of one processed monaural feature and several unprocessed binaural features, the prediction target is the subjective quality score of test items. The proposed method indicates that the binaural features are also important, although the contribution made by them are relatively low.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huaping Liu
AU  - Yong Fang
PY  - 2019/06
DA  - 2019/06
TI  - Objective Quality Measurement in Multi-channel Audio Systems by Multivariate Adaptive Regression Splines Model
BT  - Proceedings of the 2019 International Conference on Wireless Communication, Network and Multimedia Engineering (WCNME 2019)
PB  - Atlantis Press
SP  - 27
EP  - 30
SN  - 2352-538X
UR  - https://doi.org/10.2991/wcnme-19.2019.7
DO  - 10.2991/wcnme-19.2019.7
ID  - Liu2019/06
ER  -