返回
Exploring Inter-Node Relations in CNNs for Environmental Sound Classification
DOI:10.1109/LSP.2021.3130502.png)
摘要
En 中文
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.
Keyword:
Time-frequency analysis
Spectrogram
Psychoacoustic models
Task analysis
Neural networks
Indexes
Correlation
Acoustic scene classification
CNN
relation modeling
sound event classification
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
Regulation by sucrose of storage compounds breakdown in germinating seeds of yellow lupine (Lupinus luteus L.), white lupine (Lupinus albus L.) and Andean lupine (Lupinus mutabilis Sweet): I. Mobilization of storage protein蔗糖对黄羽扇豆(Lupinus luteus L.)、白羽扇豆(Lupinus albus L.)和安第斯羽扇豆(Lupinus mutabilis Sweet)萌发种子中贮藏物质分解的调控:I. 贮藏蛋白的动员

