Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic convolution is used to model the frequency dependency of sound events. In this paper, we proposed the first full-dynamic method named full-frequency dynamic convolution (FFDConv). FFDConv generates frequency kernels for every frequency band, which is designed directly in the structure for frequency-dependent modeling. It physically furnished 2D convolution with the capability of frequency-dependent modeling. FFDConv outperforms not only the baseline by 6.6% in DESED real validation dataset in terms of PSDS1, but outperforms the other full-dynamic methods. In addition, by visualizing features of sound events, we observed that FFDConv could effectively extract coherent features in specific frequency bands, consistent with the vocal continuity of sound events. This proves that FFDConv has great frequency-dependent perception ability.

翻译：近年来，二维卷积在声音事件检测（SED）中被发现存在不足。它在频率轴上对声音事件强制施加了平移等变性，而频率轴并非一个平移不变的维度。为解决此问题，动态卷积被用于建模声音事件的频率依赖性。本文中，我们提出了首个全动态方法，称为全频动态卷积（FFDConv）。FFDConv为每个频带生成频率核，其结构直接设计用于频率相关建模。它在物理上赋予二维卷积以频率相关建模的能力。FFDConv不仅在DESED真实验证数据集上以PSDS1指标优于基线6.6%，而且性能优于其他全动态方法。此外，通过可视化声音事件的特征，我们观察到FFDConv能够有效提取特定频带中的连贯特征，这与声音事件的发声连续性一致。这证明FFDConv具有出色的频率相关感知能力。