Identifying bird species by their calls in Soundscapes Maclean, Kyle Triguero, Isaac Multi-label classification Signal processing Domain mismatch Convolutional neural networks This work is partly supported by projects A-TIC-434-UGR20 and PID2020-119478GB-I00 I. Triguero’s work is supported by projects A-TIC-434-UGR20 and PID2020-119478GB-I00. I. Triguero is currently enjoying a Maria Zambrano fellowship at the University of Granada. Funding for open access charge: Universidad de Granada / CBUA In many real data science problems, it is common to encounter a domain mismatch between the training and testing datasets, which means that solutions designed for one may not transfer well to the other due to their differences. An example of such was in the BirdCLEF2021 Kaggle competition, where participants had to identify all bird species that could be heard in audio recordings. Thus, multi-label classifiers, capable of coping with domain mismatch, were required. In addition, classifiers needed to be resilient to a long-tailed (imbalanced) class distribution and weak labels. Throughout the competition, a diverse range of solutions based on convolutional neural networks were proposed. However, it is unclear how different solution components contribute to overall performance. In this work, we contextualise the problem with respect to the previously existing literature, analysing and discussing the choices made by the different participants. We also propose a modular solution architecture to empirically quantify the effects of different architectures. The results of this study provide insights into which components worked well for this challenge. 2023-05-11T10:11:51Z 2023-05-11T10:11:51Z 2023-03-20 info:eu-repo/semantics/article K. Maclean and I. Triguero. Identifying bird species by their calls in Soundscapes. Applied Intelligence. [https://doi.org/10.1007/s10489-023-04486-8] https://hdl.handle.net/10481/81466 10.1007/s10489-023-04486-8 eng http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess Atribución 4.0 Internacional Springer Nature