Analysis and acoustic event classification of environmental data collected in sons al balco project
One of the challenges of citizen science projects is the processing of data gathered by the citizens, to obtain conclusions. In the project Sons al Balcó, we aim to study the effect of lockdown due to the COVID-19 pandemic on the perception of noise in Catalonia. In one of the activities of the proj...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2023 |
| País: | España |
| Institución: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositorio: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:20.500.14342/5692 |
| Acceso en línea: | http://hdl.handle.net/20.500.14342/5692 https://www.doi.org/10.61782/fa.2023.0422 |
| Access Level: | acceso abierto |
| Palabra clave: | Noise annoyance Acoustic event detection Citizen science Convolutional neural networks 502 531/534 62 |
| Sumario: | One of the challenges of citizen science projects is the processing of data gathered by the citizens, to obtain conclusions. In the project Sons al Balcó, we aim to study the effect of lockdown due to the COVID-19 pandemic on the perception of noise in Catalonia. In one of the activities of the project, citizens collaborated by sending short videos recorded with a mobile phone, together with a subjective questionnaire about the recorded soundscape on their home balcony. Following this purpose, the samples coming from citizens should be automatically analyzed in terms of acoustic event detection, in order to compare the objective data in the videos with the subjective impressions collected in the questionnaires. As a first step towards automatic acoustic event classification, this paper details and compares the acoustic samples of the two collecting campaigns of the 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. 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. |
|---|