DeepAI AI Chat
Log In Sign Up

Towards Learning Universal Audio Representations

by   Luyu Wang, et al.

The ability to learn universal audio representations that can solve diverse speech, music, and environment tasks can spur many applications that require general sound content understanding. In this work, we introduce a holistic audio representation evaluation suite (HARES) spanning 12 downstream tasks across audio domains and provide a thorough empirical study of recent sound representation learning systems on that benchmark. We discover that previous sound event classification or speech models do not generalize outside of their domains. We observe that more robust audio representations can be learned with the SimCLR objective; however, the model's transferability depends heavily on the model architecture. We find the Slowfast architecture is good at learning rich representations required by different domains, but its performance is affected by the normalization scheme. Based on these findings, we propose a novel normalizer-free Slowfast NFNet and achieve state-of-the-art performance across all domains.


page 1

page 2

page 3

page 4


HEAR 2021: Holistic Evaluation of Audio Representations

What audio embedding approach generalizes best to a wide range of downst...

An empirical study of weakly supervised audio tagging embeddings for general audio representations

We study the usability of pre-trained weakly supervised audio tagging (A...

A Study on Robustness to Perturbations for Representations of Environmental Sound

Audio applications involving environmental sound analysis increasingly u...

DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning

Inspired by the recent progress in self-supervised learning for computer...

Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags

Self-supervised audio representation learning offers an attractive alter...

Supervised and Unsupervised Learning of Audio Representations for Music Understanding

In this work, we provide a broad comparative analysis of strategies for ...

BYOL for Audio: Exploring Pre-trained General-purpose Audio Representations

Pre-trained models are essential as feature extractors in modern machine...