Session: | A04-11: Artificial intelligence and environmental noise - Part II |
Date: | Tuesday 12 September 2023 |
Time: | 14:00 - 14:20 |
Title: | FuSA: Application of a machine learning system for noise mitigation action plans in urban environments |
Author(s): |
J.P. Arenas, Institute of Acoustics, University Austral of Chile, P.O. Box 567, 5090000 Valdivia, Chile
E. Suarez, Institute of Acoustics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
P. Huijse, Institute of Informatics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
V. Poblete, Institute of Acoustics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
M. Vernier, Institute of Informatics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
R. Viveros-Muñoz, Institute of Acoustics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
D. Espejo, Institute of Informatics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
V. Vargas, Institute of Informatics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
D. Vergara, Institute of Acoustics, University Austral of Chile, P.O. Box 567, Campus Miraflores, 5090000 Valdivia, Chile
|
Pages: | 1573-1578 |
DOI: | https://www.doi.org/10.61782/fa.2023.1274 |
PDF: | https://dael.euracoustics.org/confs/fa2023/data/articles/001274.pdf |
|
Conference proceedings
|
|
Abstract
The urban noise environment comprises many sources, some of which are regulated by
local legislation setting maximum permitted noise levels, which are vital in
implementing the noise action plans. A multidisciplinary project funded by the
Chilean R+D Agency has resulted in a machine learning-based system called FuSA that
automatically recognizes sound sources in audio files recorded in the urban
environment to assist in their analysis. FuSA (Integrated System for the Analysis of
Environmental Sound Sources) incorporates a deep neural model transferred to a
dataset of urban sound events compiled from public sources and recordings. The
target dataset follows a customized taxonomy of urban sounds. The system also uses a
public API so potential users can post audio files to determine the overall presence
of noise sources contributing to environmental noise pollution. This work provides
examples of how stakeholders can use FuSA to address urban noise problems and
contribute to city noise abatement policies.
|