Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection

Weakly Labelled learning has garnered lot of attention in recent years due to its potential to scale Sound Event Detection (SED). The paper proposes a Multi-Task Learning (MTL) framework for learning from Weakly Labelled Audio data which encompasses the traditional Multiple Instance Learning (MIL) setup. The MTL framework uses two-step attention mechanism and reconstructs Time Frequency (T-F) representation of audio as the auxiliary task. By breaking the attention into two steps, the network retains better time level information without compromising classification performance. The auxiliary task uses an auto-encoder structure to encourage the network for retaining source specific information. This indirectly de-noises internal T- F representation and improves classification performance under noisy recordings. For evaluation of proposed methodology, we remix the DCASE 2019 task 1 acoustic scene data with DCASE 2018 Task 2 sounds event data under 0, 10 and 20 db SNR. The proposed network outperforms existing benchmark models over all SNRs, specifically 22.3 %, 12.8 %, 5.9 % improvement over benchmark model on 0, 10 and 20 dB SNR respectively. The results and ablation study performed demonstrates the usefulness of auto-encoder for auxiliary task and verifies that the output of decoder portion provides a cleaned Time Frequency (T-F) representation of audio/sources which can be further used for source separation. The code is publicly released.