Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations to improve the localization ability. Synthetic data is an alternative, but it suffers from a great domain gap with real recordings. Inspired by the great success of UP-DETR in object detection, we propose to self-supervisedly pre-train SEDT (SP-SEDT) by detecting random patches (only cropped along the time axis). Experiments on the DCASE2019 task4 dataset show the proposed SP-SEDT can outperform fine-tuned frame-based model. The ablation study is also conducted to investigate the impact of different loss functions and patch size.
翻译:最近,提出了一个事件端对端模型(SEDT),用于对事件进行健全的检测,并实现竞争性性能;然而,与基于框架的模式相比,它需要更多的培训数据,并附有时间说明,以提高本地化能力;合成数据是一种替代办法,但因真实记录而存在巨大的领域差距;由于UP-DETR在物体探测方面的巨大成功,我们提议通过探测随机补丁(仅按时间轴裁剪);DCASE2019任务4数据集的实验显示,拟议的SP-SEDT可以超越经过微调的基于框架的模式;还进行了反差研究,以调查不同损失功能和补缺大小的影响。