Multi-Scale Time-Frequency Attention for Acoustic Event Detection
This work addresses acoustic event detection for audio processing applications, but it is incremental as it builds on existing attention methods by adding frequency and multi-scale components.
The paper tackled the problem of acoustic event detection by addressing the insufficiency of time-only attention and the multi-scale nature of events, proposing a multi-scale time-frequency attention module that achieved competitive results on the DCASE 2017 Challenge datasets.
Most attention-based methods only concentrate along the time axis, which is insufficient for Acoustic Event Detection (AED). Meanwhile, previous methods for AED rarely considered that target events possess distinct temporal and frequential scales. In this work, we propose a Multi-Scale Time-Frequency Attention (MTFA) module for AED. MTFA gathers information at multiple resolutions to generate a time-frequency attention mask which tells the model where to focus along both time and frequency axis. With MTFA, the model could capture the characteristics of target events with different scales. We demonstrate the proposed method on Task 2 of Detection and Classification of Acoustic Scenes and Events (DCASE) 2017 Challenge. Our method achieves competitive results on both development dataset and evaluation dataset.