Improving Primate Sounds Classification Using Binary Presorting for Deep Learning

Kölle, Michael; Illium, Steffen; Zorn, Maximilian ; Nüßlein, Jonas ; Suchostawski, Patrick und Linnhoff-Popien, Claudia (2023): Improving Primate Sounds Classification Using Binary Presorting for Deep Learning. DeLTA 2023: 4th International Conference on Deep Learning Theory and Applications, Rome, Italy, 13. - 14. Juli 2023. Conte, Donatello; Fred, Ana; Gusikhin, Oleg und Sansone, Carlo (Hrsg.): In: Deep Learning Theory and Applications: 4th International Conference, DeLTA 2023, Rome, Italy, July 13–14, 2023, Proceedings, Cham: Springer. S. 19-34

Abstract

In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available datasets from this field of research are often not optimal learning material; Samples can be weakly labeled, of different lengths or come with a poor signal-to-noise ratio. In this work, we introduce a generalized approach that first relabels subsegments of MEL spectrogram representations, to achieve higher performances on the actual multi-class classification tasks. For both the binary pre-sorting and the classification, we make use of convolutional neural networks (CNN) and various data-augmentation techniques. We showcase the results of this approach on the challenging ComparE 2021 dataset, with the task of classifying between different primate species sounds, and report significantly higher Accuracy and UAR scores in contrast to comparatively equipped model baselines.

• Dokumententyp: Konferenzbeitrag (Paper)
• Keywords: audio classification ; binary presorting ; relabelling ; background noise ; CNN
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 978-3-031-39059-3
• Ort: Cham