Enhanced Temporal Feature Integration in Audio Semantics via Alpha-Stable Modeling
×
Cite This
Citation & Abstract
L. Vrysis, L. Hadjileontiadis, I. Thoidis, C. Dimoulas, and G. Papanikolaou, "Enhanced Temporal Feature Integration in Audio Semantics via Alpha-Stable Modeling," J. Audio Eng. Soc., vol. 69, no. 4, pp. 227-237, (2021 April.). doi: https://doi.org/10.17743/jaes.2021.0001
L. Vrysis, L. Hadjileontiadis, I. Thoidis, C. Dimoulas, and G. Papanikolaou, "Enhanced Temporal Feature Integration in Audio Semantics via Alpha-Stable Modeling," J. Audio Eng. Soc., vol. 69 Issue 4 pp. 227-237, (2021 April.). doi: https://doi.org/10.17743/jaes.2021.0001
Abstract: Modern feature-based methodologies in semantic audio applications attempt to capture the temporal dependency of successive feature observations, which form the so-called texture windows. This paper proposes an enhancement of this type of processing, known as temporal feature integration, by employing and testing alternative deployable strategies. Specifically, data are fitted through commonly used statistical principles, estimating the parameters of a given probability density function that maximize the log-likelihood of the samples inside each texture window. The main statistical model that is set under investigation is the alpha-stable distribution because it can successfully represent signals, which the commonly used Gaussian curves fail to capture. Within this framework, the enhanced feature integration method is also elaborated, introducing new measures for feature modeling. The main objective of this work is to introduce an efficient feature engineering protocol for temporal integration, specifying a compact and robust set of aggregated audio parameters that can address the needs of many audio information retrieval systems.
@article{vrysis2021enhanced,
author={vrysis, lazaros and hadjileontiadis, leontios and thoidis, iordanis and dimoulas, charalampos and papanikolaou, george},
journal={journal of the audio engineering society},
title={enhanced temporal feature integration in audio semantics via alpha-stable modeling},
year={2021},
volume={69},
number={4},
pages={227-237},
doi={https://doi.org/10.17743/jaes.2021.0001},
month={april},}
@article{vrysis2021enhanced,
author={vrysis, lazaros and hadjileontiadis, leontios and thoidis, iordanis and dimoulas, charalampos and papanikolaou, george},
journal={journal of the audio engineering society},
title={enhanced temporal feature integration in audio semantics via alpha-stable modeling},
year={2021},
volume={69},
number={4},
pages={227-237},
doi={https://doi.org/10.17743/jaes.2021.0001},
month={april},
abstract={modern feature-based methodologies in semantic audio applications attempt to capture the temporal dependency of successive feature observations, which form the so-called texture windows. this paper proposes an enhancement of this type of processing, known as temporal feature integration, by employing and testing alternative deployable strategies. specifically, data are fitted through commonly used statistical principles, estimating the parameters of a given probability density function that maximize the log-likelihood of the samples inside each texture window. the main statistical model that is set under investigation is the alpha-stable distribution because it can successfully represent signals, which the commonly used gaussian curves fail to capture. within this framework, the enhanced feature integration method is also elaborated, introducing new measures for feature modeling. the main objective of this work is to introduce an efficient feature engineering protocol for temporal integration, specifying a compact and robust set of aggregated audio parameters that can address the needs of many audio information retrieval systems.},}
TY - paper
TI - Enhanced Temporal Feature Integration in Audio Semantics via Alpha-Stable Modeling
SP - 227
EP - 237
AU - Vrysis, Lazaros
AU - Hadjileontiadis, Leontios
AU - Thoidis, Iordanis
AU - Dimoulas, Charalampos
AU - Papanikolaou, George
PY - 2021
JO - Journal of the Audio Engineering Society
IS - 4
VO - 69
VL - 69
Y1 - April 2021
TY - paper
TI - Enhanced Temporal Feature Integration in Audio Semantics via Alpha-Stable Modeling
SP - 227
EP - 237
AU - Vrysis, Lazaros
AU - Hadjileontiadis, Leontios
AU - Thoidis, Iordanis
AU - Dimoulas, Charalampos
AU - Papanikolaou, George
PY - 2021
JO - Journal of the Audio Engineering Society
IS - 4
VO - 69
VL - 69
Y1 - April 2021
AB - Modern feature-based methodologies in semantic audio applications attempt to capture the temporal dependency of successive feature observations, which form the so-called texture windows. This paper proposes an enhancement of this type of processing, known as temporal feature integration, by employing and testing alternative deployable strategies. Specifically, data are fitted through commonly used statistical principles, estimating the parameters of a given probability density function that maximize the log-likelihood of the samples inside each texture window. The main statistical model that is set under investigation is the alpha-stable distribution because it can successfully represent signals, which the commonly used Gaussian curves fail to capture. Within this framework, the enhanced feature integration method is also elaborated, introducing new measures for feature modeling. The main objective of this work is to introduce an efficient feature engineering protocol for temporal integration, specifying a compact and robust set of aggregated audio parameters that can address the needs of many audio information retrieval systems.
Modern feature-based methodologies in semantic audio applications attempt to capture the temporal dependency of successive feature observations, which form the so-called texture windows. This paper proposes an enhancement of this type of processing, known as temporal feature integration, by employing and testing alternative deployable strategies. Specifically, data are fitted through commonly used statistical principles, estimating the parameters of a given probability density function that maximize the log-likelihood of the samples inside each texture window. The main statistical model that is set under investigation is the alpha-stable distribution because it can successfully represent signals, which the commonly used Gaussian curves fail to capture. Within this framework, the enhanced feature integration method is also elaborated, introducing new measures for feature modeling. The main objective of this work is to introduce an efficient feature engineering protocol for temporal integration, specifying a compact and robust set of aggregated audio parameters that can address the needs of many audio information retrieval systems.
Authors:
Vrysis, Lazaros; Hadjileontiadis, Leontios; Thoidis, Iordanis; Dimoulas, Charalampos; Papanikolaou, George
Affiliations:
Aristotle University of Thessaloniki, Thessaloniki, Greece; Khalifa University of Science and Technology, Abu Dhabi, UAE; Aristotle University of Thessaloniki, Thessaloniki, Greece; Aristotle University of Thessaloniki, Thessaloniki, Greece; Aristotle University of Thessaloniki, Thessaloniki, Greece(See document for exact affiliation information.) JAES Volume 69 Issue 4 pp. 227-237; April 2021
Publication Date:
April 8, 2021Import into BibTeX
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=21031