Few-shot bioacoustic event detection at the DCASE 2023 challenge
This work addresses the problem of detecting animal sounds in varied environments with few examples, which is incremental as it builds on previous challenge editions.
The paper describes the DCASE 2023 challenge for few-shot bioacoustic event detection, where systems detect sound events with limited examples, achieving an F-score of 63% on the evaluation set.
Few-shot bioacoustic event detection consists in detecting sound events of specified types, in varying soundscapes, while having access to only a few examples of the class of interest. This task ran as part of the DCASE challenge for the third time this year with an evaluation set expanded to include new animal species, and a new rule: ensemble models were no longer allowed. The 2023 few shot task received submissions from 6 different teams with F-scores reaching as high as 63% on the evaluation set. Here we describe the task, focusing on describing the elements that differed from previous years. We also take a look back at past editions to describe how the task has evolved. Not only have the F-score results steadily improved (40% to 60% to 63%), but the type of systems proposed have also become more complex. Sound event detection systems are no longer simple variations of the baselines provided: multiple few-shot learning methodologies are still strong contenders for the task.