Study of the Non-negative Matrix Factorization behavior to estimate the urban traffic sound levels

Résumé : The advent of low-cost acoustic sensor networks in cities raises new interesting approaches for improving the monitoring of the acoustic quality of cities. Many innovative approaches are developed to improve knowledge on sound environments: sound environment recognition, sound source detection, etc. In order to improve the road traffic noise mapping, the use of a specific version of the Non-negative Matrix Factorization (NMF), named thresholded initialized NMF, as a source separation method to estimate the sound level of road traffic from measurements, has proved to be a successful approach. This paper proposes to further detail the functioning of the thresholded initialized NMF on a corpus composed of urban sound scenes mixing traffic and specific interfering components with calibrated sound levels in order to better understand its behavior according to the different sources encountered. The study reveals the different performances of this approach depending on the noise levels of the interfering sources and their proximity to the urban traffic spectrum.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02285320
Contributor : Ifsttar Cadic <>
Submitted on : Thursday, September 12, 2019 - 4:06:37 PM
Last modification on : Saturday, September 14, 2019 - 1:25:01 AM

File

doc00030795.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02285320, version 1

Collections

Citation

Jean-Rémy Gloaguen, Mathieu Lagrange, Arnaud Can, Jean-François Petiot. Study of the Non-negative Matrix Factorization behavior to estimate the urban traffic sound levels. ICSV'26 ; 26ème International Congress on Sound and Vibration, Jul 2019, MONTREAL, Canada. ⟨hal-02285320⟩

Share

Metrics

Record views

14

Files downloads

10