MAT-SED：一种用于声音事件检测的带掩码重构预训练的掩码音频Transformer
MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection
AI总结：
针对现有声音事件检测方法依赖RNN上下文网络、标注数据不足的问题，提出带掩码重构预训练的纯Transformer模型MAT-SED，结合全局-局部特征融合策略，在DCASE2023任务4上取得SOTA性能。
摘要：
近年来，在DCASE挑战赛中，利用大型预训练Transformer编码器网络的声音事件检测（SED）方法展现出了可观的性能。但由于标注数据稀缺，这类方法仍依赖基于RNN的上下文网络来建模时序依赖关系。本文提出了一种采用掩码重构预训练的纯Transformer架构SED模型，命名为MAT-SED。具体而言，首先设计了带有相对位置编码的Transformer作为上下文网络，以自监督方式在所有可用目标数据上通过掩码重构任务进行预训练；编码器与上下文网络以半监督方式联合微调。此外，还提出了一种全局-局部特征融合策略以提升定位能力。在DCASE2023任务4上的评估显示，MAT-SED超越了当前最优性能，PSDS1/PSDS2分别达到0.587/0.896。
英文摘要：
Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still rely on an RNN-based context network to model temporal dependencies, largely due to the scarcity of labeled data. In this work, we propose a pure Transformer-based SED model with masked-reconstruction based pre-training, termed MAT-SED. Specifically, a Transformer with relative positional encoding is first designed as the context network, pre-trained by the masked-reconstruction task on all available target data in a self-supervised way. Both the encoder and the context network are jointly fine-tuned in a semi-supervised manner. Furthermore, a global-local feature fusion strategy is proposed to enhance the localization capability. Evaluation of MAT-SED on DCASE2023 task4 surpasses state-of-the-art performance, achieving 0.587/0.896 PSDS1/PSDS2 respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
