DeepAI
Log In Sign Up

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

page 2

page 7

09/18/2021

V-SlowFast Network for Efficient Visual Sound Separation

The objective of this paper is to perform visual sound separation: i) we...
04/27/2021

Three-stream network for enriched Action Recognition

Understanding accurate information on human behaviours is one of the mos...
01/24/2019

Multi-stream Network With Temporal Attention For Environmental Sound Classification

Environmental sound classification systems often do not perform robustly...
12/10/2018

SlowFast Networks for Video Recognition

We present SlowFast networks for video recognition. Our model involves (...
10/20/2022

Play It Back: Iterative Attention for Audio Recognition

A key function of auditory cognition is the association of characteristi...
05/30/2022

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning

Recurrent neural networks have a strong inductive bias towards learning ...
06/28/2022

A Hierarchical Speaker Representation Framework for One-shot Singing Voice Conversion

Typically, singing voice conversion (SVC) depends on an embedding vector...

Code Repositories

auditory-slow-fast

Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch


view repo