Estimation of the Perceived Time of Presence of Sources in Urban Acoustic Environments Using Deep Learning Techniques

Abstract

The impact of urban sound on human beings has often been studied from a negative point of view (noise pollution). In the two last decades, the interest of studying its positive impact has been revealed with the soundscape approach (resourcing spaces). The literature shows that the recognition of sources plays a great role in the way humans are affected by sound environments. There is thus a need for characterizing urban acoustic environments not only with sound pressure measurements but also with source-specific attributes such as their perceived time of presence, dominance or volume. This paper demonstrates, on a controlled dataset, that machine learning techniques based on state of the art neural architectures can predict the perceived time of presence of several sound sources at a sufficient accuracy. To validate this assertion, a corpus of simulated sound scenes is first designed. Perceptual attributes corresponding to those stimuli are gathered through a listening experiment. From the contributions of the individual sound sources available for the simulated corpus, a physical indicator approximating the perceived time of presence of sources is computed and used to train and evaluate a multi-label source detection model. This model predicts the presence of simultaneously active sources from fast third octave spectra, allowing the estimation of perceptual attributes such as pleasantness in urban sound environments at a sufficient degree of precision.

Ecosystem services enhanced through soundscape management link people and wildlife

“…A study of consumer‐grade recording devices found that these units are able to obtain accurate sound pressure level readings when integrating across time and spectrum (Mennitt & Fristrup, 2012). Additionally, L50 is considered one of the most well‐correlated physical indicators to pleasantness and perceived loudness in soundscape assessments (Aumond et al., 2017; Gontier, Aumond, et al., 2019; Gontier, Lavandier, et al., 2019).…”

A Taxonomy Proposal for the Assessment of the Changes in Soundscape Resulting from the COVID-19 Lockdown

“…The following indicators should be calculated on an hourly basis. [11,26] Good for discriminating presence of biophonic sounds and anthropogenic sounds in urban sound…”

Investigating urban soundscapes of the COVID-19 lockdown: A predictive soundscape modeling approach

“…Keeping in mind the remote nature of the study and ensuring a minimum level of robustness for reliable sound source recognition, an initial exercise was performed, consisting of a headphone screening test ( Woods et al , 2017 ) and a headphone reproduction level adjustment test ( Gontier et al , 2019 ). The level adjustment was performed using an 11-s-long pink noise sample matched to the lowest and highest values from the experimental set.…”