Slow-Fast Auditory Streams for Audio Recognition
Slow-Fast Auditory Streams for Audio Recognition
复制标题
DOI：
10.1109/icassp39728.2021.9413376
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
E. Kazakos;Arsha Nagrani;Andrew Zisserman;D. Damen
中科院分区：
文献类型：
--
作者：
E. Kazakos;Arsha Nagrani;Andrew Zisserman;D. Damen
我们提出了一种用于音频识别的双流卷积网络，该网络对时频谱图输入进行操作。在视觉识别方面取得类似的成功之后，我们学习了具有可分离卷积和多级横向连接的慢-快听觉流。慢路径具有高通道容量，而快路径以细粒度的时间分辨率操作。我们在两个不同的数据集上展示了我们的双流提案的重要性：VGG-Sound和EPIC-KITCHENS-100，并在两者上实现了最先进的结果。
We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state- of-the-art results on both.