Development of a machine learning detector for North Atlantic humpback whale song

• Published in: The Journal of the Acoustical Society of America
• Main Authors: Kather, Vincent, Seipel, Fabian, Berges, Benoit, Davis, Genevieve, Gibson, Catherine, Harvey, Matt, Henry, Lea-Anne, Stevenson, Andrew, Risch, Denise
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2024
• Subjects: Life Science; Humpback Whale; North Atlantic
• Online Access: https://research.wur.nl/en/publications/development-of-a-machine-learning-detector-for-north-atlantic-hum; https://doi.org/10.1121/10.0025275

The study of humpback whale song using passive acoustic monitoring devices requires bioacousticians to manually review hours of audio recordings to annotate the signals. To vastly reduce the time of manual annotation throughautomation, a machine learning model was developed. Convolutional neural networks have made major advances in the previous decade, leading to a wide range of applications, including the detection of frequency modulatedvocalizations by cetaceans. A large dataset of over 60 000 audio segments of 4 s length is collected from the North Atlantic and used to fine-tune an existing model for humpback whale song detection in the North Pacific (see Allen,Harvey, Harrell, Jansen, Merkens, Wall, Cattiau, and Oleson (2021). Front. Mar. Sci. 8, 607321). Furthermore, different data augmentation techniques (time-shift, noise augmentation, and masking) are used to artificially increasethe variability within the training set. Retraining and augmentation yield F-score values of 0.88 on context window basis and 0.89 on hourly basis with false positive rates of 0.05 on context window basis and 0.01 on hourly basis. Ifnecessary, usage and retraining of the existing model is made convenient by a framework (AcoDet, acoustic detector) built during this project. Combining the tools provided by this framework could save researchers hours of manualannotation time and, thus, accelerate their research.