Slow-Fast Auditory Streams For Audio Recognition

03/05/2021
by   Evangelos Kazakos, et al.
4

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset