Exporing Inter-Node Relations in CNNs for Environmental Sound Classicatin
Exporing Inter-Node Relations in CNNs for Environmental Sound Classicatin
复制标题
揭示 CNN 中的节点间关系以实现环境无害分类
DOI：
10.1109/lsp.2021.3130502
复制
发表时间：
2021
影响因子：
3.9
通讯作者：
Han Jiqing
中科院分区：
文献类型：
--
作者：
Hongwei Song;Deng Shiwen;Han Jiqing
对于环境声音分类，CNN已成为最成功的架构。通过将CNN特征视为排列在2D时频网格上的节点集合，典型的CNN层处理有限局部区域内的节点。然而，节点之间丰富的关系信息，特别是非局部关系，大多被忽视。对于环境声音，这些节点间的关系携带丰富的信息，重复的声音事件模式的存在和声学场景中不同的声音事件之间的复杂的相互作用，这是有价值的分类环境声音。在这封信中，我们提出了一个关系模块，命名为R-块，探索关系信息的明确和全面的方式。R-Block不仅可以捕获和利用节点间的关系，还可以探索学习到的关系的结构，从而实现更具表达力的表示。实验结果表明，通过使用R-Block增强强大的ResNeXt主干，我们的模型能够在ESC-50和US 8 K声音事件分类数据集上实现具有竞争力的性能，并在DCASE 2018声学场景分类数据集上实现最先进的结果。
For environmental sound classification, CNNs have become the most successful architecture. By regarding the CNN features as a collection of nodes arranged on a 2D time-frequency grid, typical CNN layers process nodes within a limited local region. However, the rich relation information between nodes, especially the non-local relations, is mostly ignored. For environmental sound, these inter-node relations carry rich information about the existence of repetitive sound event patterns and the complex interactions between different sound events in acoustic scenes, which are valuable for categorizing environmental sound. In this letter, we propose a relation module, named the R-Block, to explore the relation information in an explicit and comprehensive way. The R-Block is designed to not only capture and utilize the inter-node relations, but also explore the structure of the learned relations, which leads to a more expressive representation. Experimental results reveal that, by augmenting a powerful ResNeXt backbone with the R-Block, our model is able to achieve competitive performance on ESC-50 and US8K sound event classification dataset and state-of-the-art result on DCASE2018 acoustics scene classification dataset.