Abstract
We investigated whether the use of technological tools can effectively help in manipulating the increasing volume of audio data available through the use of long field recordings. We also explored whether we can address, by using these recordings and tools, audio data analysis, feature extraction and determine predominant patterns in the data. Similarly, we explored whether we can visualize feature clusters in the data and automatically detect sonic events. Our focus was primarily on enhancing the importance of natural-urban hybrid habitats within cities, which benefit communities in various ways, specifically through the natural soundscapes of these habitats that evoke memories and reinforce a sense of belonging for inhabitants. The loss of sonic heritage can be a precursor to the extinction of biodiversity within these habitats. By quantifying changes in the soundscape of these habitats over long periods of time, we can collect relevant information linked to this eventual loss. In this respect, we developed two approaches. The first was the comparison among habitats that progressively changed from natural to urban. The second was the optimization of the field recordings’ labeling process. This was performed with labels corresponding to the annotations of classes of sonic events and their respective start and end times, including events temporarily superimposed on one another. We compared three habitats over time by using their sonic characteristics collected in field conditions. Comparisons of sonic similarity or dissimilarity among patches were made based on the Jaccard coefficient and uniform manifold approximation and projection (UMAP). Our SEDnet model achieves a F1-score of 0.79 with error rate 0.377 and with the area under PSD-ROC curve of 71.0. In terms of computational efficiency, the model is able to detect sound events from an audio file in a time of 14.49 s. With these results, we confirm the usefulness of the methods used in this work for the process of labeling field recordings.
Highlights
Natural-urban hybrid habitats are defined as natural landscapes that are close to an urban context, and they capture the interest of this work
It is clear from recent research that urban wetlands are under threat as a consequence of the intensification of anthropogenic activities associated with increases in population [17]
When we disaggregated the data of the global temporal evolution of classes at the level of wetlands, as observed in Figure 8, we found, through the single-event analysis at the early morning period, that the Miraflores wetland had a greater number of sonic events of amphibians (62%) compared with the El Bosque wetland (20%), as explained above, as well as in comparison to the Angachilla wetland (18%)
Summary
Natural-urban hybrid habitats are defined as natural landscapes that are close to an urban context, and they capture the interest of this work. While urban wetlands provide the above mentioned benefits, concerns about their degradation have increased in recent years [13]. Bradfer-Lawrence et al (2019) [33] explored various ecoacoustic practices, such as the use of various acoustic indices that reflect different attributes of the soundscape and recording collection methods. Gan et al (2020) [34] explored the problem of acoustic recognition of two frog species by using long-term field recordings and machine-learning methods. Acoustic data were extracted from 48 h of field recordings under different weather conditions. These data were used to conduct experiments and to assess recognition performance. The labeling task of frog chorusing was performed manually by trained ecologists who proposed, as features, spectral acoustic indices extracted from the recordings’ spectrograms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
