DCASE 2024 Task 4: Sound Event Detection with Heterogeneous Data and Missing Labels

TL;DR

The paper addresses sound event detection under missing labels and heterogeneous data by organizing DCASE 2024 Task 4 around combining DESED and MAESTRO datasets and leveraging soft labels. It proposes an updated CRNN baseline that fuses BEATs-derived features with a CNN encoder, employing Mixup and mean-teacher training, along with cross-dataset label mapping and targeted masking to handle partially labeled data. Key contributions include cross-mapping of classes, masked attention-pooling, dataset-aware loss, and a dual-phase hyperparameter optimization strategy, all showing improved performance when training on multiple datasets. The findings suggest that leveraging diverse data sources with incomplete/soft annotations can outperform single-dataset training, advancing practical robustness for real-world SED systems in domestic environments.

Abstract

The Detection and Classification of Acoustic Scenes and Events Challenge Task 4 aims to advance sound event detection (SED) systems in domestic environments by leveraging training data with different supervision uncertainty. Participants are challenged in exploring how to best use training data from different domains and with varying annotation granularity (strong/weak temporal resolution, soft/hard labels), to obtain a robust SED system that can generalize across different scenarios. Crucially, annotation across available training datasets can be inconsistent and hence sound labels of one dataset may be present but not annotated in the other one and vice-versa. As such, systems will have to cope with potentially missing target labels during training. Moreover, as an additional novelty, systems will also be evaluated on labels with different granularity in order to assess their robustness for different applications. To lower the entry barrier for participants, we developed an updated baseline system with several caveats to address these aforementioned problems. Results with our baseline system indicate that this research direction is promising and is possible to obtain a stronger SED system by using diverse domain training data with missing labels compared to training a SED system for each domain separately.