Few-shot acoustic event detection via meta-learning
This work addresses the under-studied problem of few-shot learning for audio recognition, enabling detection of new acoustic events with very limited data, though it appears incremental in applying existing meta-learning methods to this domain.
The paper tackles few-shot acoustic event detection by exploring meta-learning approaches, which achieve superior performance compared to supervised baselines, demonstrating effectiveness in generalizing to new audio events with limited labeled data.
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition has been under-studied. We formulate few-shot AED problem and explore different ways of utilizing traditional supervised methods for this setting as well as a variety of meta-learning approaches, which are conventionally used to solve few-shot classification problem. Compared to supervised baselines, meta-learning models achieve superior performance, thus showing its effectiveness on generalization to new audio events. Our analysis including impact of initialization and domain discrepancy further validate the advantage of meta-learning approaches in few-shot AED.