Auto deep learning for bioacoustic signals
This work addresses the problem of improving accuracy and efficiency in bioacoustics research for ecologists and researchers, though it is incremental as it applies existing automated methods to a specific domain.
The study tackled multi-class classification of bird vocalizations using automated deep learning, finding that an AutoKeras-derived model consistently outperformed traditional models like MobileNet, ResNet50, and VGG16 on the Western Mediterranean Wetland Birds dataset.
This study investigates the potential of automated deep learning to enhance the accuracy and efficiency of multi-class classification of bird vocalizations, compared against traditional manually-designed deep learning models. Using the Western Mediterranean Wetland Birds dataset, we investigated the use of AutoKeras, an automated machine learning framework, to automate neural architecture search and hyperparameter tuning. Comparative analysis validates our hypothesis that the AutoKeras-derived model consistently outperforms traditional models like MobileNet, ResNet50 and VGG16. Our approach and findings underscore the transformative potential of automated deep learning for advancing bioacoustics research and models. In fact, the automated techniques eliminate the need for manual feature engineering and model design while improving performance. This study illuminates best practices in sampling, evaluation and reporting to enhance reproducibility in this nascent field. All the code used is available at https: //github.com/giuliotosato/AutoKeras-bioacustic Keywords: AutoKeras; automated deep learning; audio classification; Wetlands Bird dataset; comparative analysis; bioacoustics; validation dataset; multi-class classification; spectrograms.