Sons al Balcó: A Comparative Analysis of WASN-Based LAeq Measured Values with Perceptual Questionnaires in Barcelona during the COVID-19 Lockdown.

The mobility and activity restrictions imposed in Spain due to the COVID-19 pandemic caused a significant improvement in the urban noise pollution that could be objectively measured in those cities with acoustic sensor networks deployed. This significant change in the urban soundscapes was also perceived by citizens who positively appraised this new acoustic scenario. In this work, authors present a comparative analysis between different noise indices provided by 70 sound sensors deployed in Barcelona, both during and before the lockdown, and the results of a perceptual test conducted in the framework of the project Sons al Balcó during the lockdown, which received more than one hundred contributions in Barcelona alone. The analysis has been performed by clustering the objective and subjective data according to the predominant noise sources in the location of the sensors and differentiating road traffic in heavy, moderate and low-traffic areas. The study brings out strong alignments between a decline in noise indices, acoustic satisfaction improvement and changes in the predominant noise sources, supporting the idea that objective calibrated data can be useful to make a qualitative approximation to the subjective perception of urban soundscapes when further information is not available.

Analysis and Acoustic Event Classification of Environmental Data Collected in a Citizen Science Project.

Citizen science can serve as a tool to obtain information about changes in the soundscape. One of the challenges of citizen science projects is the processing of data gathered by the citizens, to obtain conclusions. As part of the project Sons al Balcó, authors aim to study the soundscape in Catalonia during the lockdown due to the COVID-19 pandemic and afterwards and design a tool to automatically detect sound events as a first step to assess the quality of the soundscape. This paper details and compares the acoustic samples of the two collecting campaigns of the Sons al Balcó project. While the 2020 campaign obtained 365 videos, the 2021 campaign obtained 237. Later, a convolutional neural network is trained to automatically detect and classify acoustic events even if they occur simultaneously. Event based macro F1-score tops 50% for both campaigns for the most prevalent noise sources. However, results suggest that not all the categories are equally detected: the percentage of prevalence of an event in the dataset and its foregound-to-background ratio play a decisive role.

The Soundscape of the COVID-19 Lockdown: Barcelona Noise Monitoring Network Case Study.

The lockdown social measures in Spain due to COVID-19 caused a significant decrease in urban noise levels, which was observed in most of the large cities. This paper presents an analysis of the noise levels in Barcelona, Spain, by means of an accurate analysis of the most relevant sensors deployed in the Barcelona Noise Monitoring Network. In this work, we present the LAeq levels in eight different locations from January 2020 to June 2020-from Superblocks to industrial zones-including and detailing all stages of the lockdown. Several comparisons were conducted with the monitoring data available from the former years (2019 and 2018-when available). The results of the analysis in Barcelona show a drastic LAeq reduction (-9 dBA), especially in nightlife areas of the city, moderate to high LAeq change (-7 dBA) in commercial and restaurants areas and a small decrease in LAeq (-5 dBA) in dense traffic areas.

A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments.

Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (k-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.