Multitask frame-level learning for few-shot sound event detection
This work improves few-shot sound event detection for applications like bioacoustics, but it is incremental as it builds on existing frame-level strategies.
The paper tackles the problem of few-shot sound event detection by addressing prediction truncation issues in frame-level methods, introducing a multitask framework and TimeFilterAug data augmentation, achieving a F-score of 63.8% and ranking first in the DCASE 2023 challenge.
This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on segment-level predictions, which often providing detailed, fine-grained predictions, particularly for events of brief duration. Although frame-level prediction strategies have been proposed to overcome these limitations, these strategies commonly face difficulties with prediction truncation caused by background noise. To alleviate this issue, we introduces an innovative multitask frame-level SED framework. In addition, we introduce TimeFilterAug, a linear timing mask for data augmentation, to increase the model's robustness and adaptability to diverse acoustic environments. The proposed method achieves a F-score of 63.8%, securing the 1st rank in the few-shot bioacoustic event detection category of the Detection and Classification of Acoustic Scenes and Events Challenge 2023.