基于置信均值教师的多维频率动态卷积声音事件检测
Multi-dimensional frequency dynamic convolution with confident mean teacher for sound event detection
摘要：
最近，卷积神经网络（CNN）已被广泛用于声音事件检测（SED）。然而，传统的卷积在学习不同声音事件的时频域表示方面存在不足。为了解决这个问题，我们提出了多维频率动态卷积（MFDConv），这是一种新的设计，它赋予卷积核沿多维的频率自适应动态特性。MFDConv利用一种新的多维注意力机制和并行策略来学习互补的频率自适应注意力，这大大增强了卷积核的特征提取能力。此外，为了提高平均教师的绩效，我们提出了自信的平均教师，以提高教师的伪标签的准确性和训练学生与高置信度的标签。实验结果表明，在DESED真实验证数据集上，所提方法的PSDS1和PSDS2分别达到0.470和0.692。
英文摘要：
Recently, convolutional neural networks (CNNs) have been widely used in sound event detection (SED). However, traditional convolution is deficient in learning time-frequency domain representation of different sound events. To address this issue, we propose multi-dimensional frequency dynamic convolution (MFDConv), a new design that endows convolutional kernels with frequency-adaptive dynamic properties along multiple dimensions. MFDConv utilizes a novel multi-dimensional attention mechanism with a parallel strategy to learn complementary frequency-adaptive attentions, which substantially strengthen the feature extraction ability of convolutional kernels. Moreover, in order to promote the performance of mean teacher, we propose the confident mean teacher to increase the accuracy of pseudo-labels from the teacher and train the student with high confidence labels. Experimental results show that the proposed methods achieve 0.470 and 0.692 of PSDS1 and PSDS2 on the DESED real validation dataset.
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。
