A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications
Due to the rising usage of various broadcasting systems and web-casting applications, a measurement of audio quality has become an essential task. This paper presents a benchmark of the parametric models for non-intrusive estimation of the audio quality perceived by the end user. The proposed soluti...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
VSB-Technical University of Ostrava
2021-01-01
|
Series: | Advances in Electrical and Electronic Engineering |
Subjects: | |
Online Access: | http://advances.utc.sk/index.php/AEEE/article/view/4207 |
_version_ | 1797826939317125120 |
---|---|
author | Martin Jakubik Peter Pocta |
author_facet | Martin Jakubik Peter Pocta |
author_sort | Martin Jakubik |
collection | DOAJ |
description | Due to the rising usage of various broadcasting systems and web-casting applications, a measurement of audio quality has become an essential task. This paper presents a benchmark of the parametric models for non-intrusive estimation of the audio quality perceived by the end user. The proposed solution is based on machine learning techniques for broadcasting systems and web-casting applications. The main goal of this study is to assess the performance of the non-intrusive parametric models as well as to evaluate a statistical significance of the performance differences between those models. The paper provides a comparison of several models based on the Support Vector Regression, Genetic Programming, Multigene Symbolic Regression, Neural Networks and Random Forest. The obtained results indicate that among the investigated models the most accurate, although not the fastest ones, are the model based on Random Forest (a broadcast scenario) and the SVR-based model (a web-cast scenario). These models represent promising candidates for non-intrusive parametric audio quality assessment in the context of broadcasting systems and web-casting applications. |
first_indexed | 2024-04-09T12:41:25Z |
format | Article |
id | doaj.art-f19c14f41df7493ca6ad9c98950af56c |
institution | Directory Open Access Journal |
issn | 1336-1376 1804-3119 |
language | English |
last_indexed | 2024-04-09T12:41:25Z |
publishDate | 2021-01-01 |
publisher | VSB-Technical University of Ostrava |
record_format | Article |
series | Advances in Electrical and Electronic Engineering |
spelling | doaj.art-f19c14f41df7493ca6ad9c98950af56c2023-05-14T20:50:13ZengVSB-Technical University of OstravaAdvances in Electrical and Electronic Engineering1336-13761804-31192021-01-0119430431210.15598/aeee.v19i4.42071131A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting ApplicationsMartin Jakubik0Peter Pocta1Department of Multimedia and Information and Communication Technology, Faculty of Electrical Engineering and Information Technology, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, Slovak RepublicDepartment of Multimedia and Information and Communication Technology, Faculty of Electrical Engineering and Information Technology, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, Slovak RepublicDue to the rising usage of various broadcasting systems and web-casting applications, a measurement of audio quality has become an essential task. This paper presents a benchmark of the parametric models for non-intrusive estimation of the audio quality perceived by the end user. The proposed solution is based on machine learning techniques for broadcasting systems and web-casting applications. The main goal of this study is to assess the performance of the non-intrusive parametric models as well as to evaluate a statistical significance of the performance differences between those models. The paper provides a comparison of several models based on the Support Vector Regression, Genetic Programming, Multigene Symbolic Regression, Neural Networks and Random Forest. The obtained results indicate that among the investigated models the most accurate, although not the fastest ones, are the model based on Random Forest (a broadcast scenario) and the SVR-based model (a web-cast scenario). These models represent promising candidates for non-intrusive parametric audio quality assessment in the context of broadcasting systems and web-casting applications.http://advances.utc.sk/index.php/AEEE/article/view/4207artificial neural networksaudio quality estimationbroadcastmachine learningstatistical significancesupport vector regressionweb-cast. |
spellingShingle | Martin Jakubik Peter Pocta A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications Advances in Electrical and Electronic Engineering artificial neural networks audio quality estimation broadcast machine learning statistical significance support vector regression web-cast. |
title | A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications |
title_full | A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications |
title_fullStr | A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications |
title_full_unstemmed | A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications |
title_short | A Benchmark of Non-intrusive Parametric Audio Quality Estimation Models for Broadcasting Systems and Web-casting Applications |
title_sort | benchmark of non intrusive parametric audio quality estimation models for broadcasting systems and web casting applications |
topic | artificial neural networks audio quality estimation broadcast machine learning statistical significance support vector regression web-cast. |
url | http://advances.utc.sk/index.php/AEEE/article/view/4207 |
work_keys_str_mv | AT martinjakubik abenchmarkofnonintrusiveparametricaudioqualityestimationmodelsforbroadcastingsystemsandwebcastingapplications AT peterpocta abenchmarkofnonintrusiveparametricaudioqualityestimationmodelsforbroadcastingsystemsandwebcastingapplications AT martinjakubik benchmarkofnonintrusiveparametricaudioqualityestimationmodelsforbroadcastingsystemsandwebcastingapplications AT peterpocta benchmarkofnonintrusiveparametricaudioqualityestimationmodelsforbroadcastingsystemsandwebcastingapplications |