Slow-Fast Auditory Streams for Audio Recognition
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 855-859
Abstract
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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition2019
- Environment Sound Classification Using a Two-Stream CNN Based on Decision-Level FusionSensors, 2019
- Acoustic features fusion using attentive multi-channel deep architecture2018
- A Closer Look at Spatiotemporal Convolutions for Action Recognition2018
- Timbre analysis of music audio signals with convolutional neural networks2017
- CNN architectures for large-scale audio classification2017
- Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound ClassificationIEEE Signal Processing Letters, 2017
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- Deep Residual Learning for Image Recognition2016
- Encoding of Natural Sounds at Multiple Spectral and Temporal Resolutions in the Human Auditory CortexPLOS Computational Biology, 2014