DeepAI AI Chat
Log In Sign Up

HEAR 2021: Holistic Evaluation of Audio Representations

03/06/2022
by   Joseph Turian, et al.
Google
adobe
University of Victoria
Princeton University
IRCAM
Universitat Pompeu Fabra
Queen Mary University of London
IEEE
Carnegie Mellon University
Imperial College London
Stanford University
McGill University
17

What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR 2021 NeurIPS challenge is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. HEAR 2021 evaluates audio representations using a benchmark suite across a variety of domains, including speech, environmental sound, and music. In the spirit of shared exchange, each participant submitted an audio embedding model following a common API that is general-purpose, open-source, and freely available to use. Twenty-nine models by thirteen external teams were evaluated on nineteen diverse downstream tasks derived from sixteen datasets. Open evaluation code, submitted models and datasets are key contributions, enabling comprehensive and reproducible evaluation, as well as previously impossible longitudinal studies. It still remains an open question whether one single general-purpose audio representation can perform as holistically as the human ear.

READ FULL TEXT

page 10

page 27

page 28

11/23/2021

Towards Learning Universal Audio Representations

The ability to learn universal audio representations that can solve dive...
03/20/2022

A Study on Robustness to Perturbations for Representations of Environmental Sound

Audio applications involving environmental sound analysis increasingly u...
11/04/2022

Integrated Parameter-Efficient Tuning for General-Purpose Audio Models

The advent of hyper-scale and general-purpose pre-trained models is shif...
11/25/2022

Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers

The success of supervised deep learning methods is largely due to their ...
11/28/2022

Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation

Current computer vision models, unlike the human visual system, cannot y...
03/03/2023

Low-Complexity Audio Embedding Extractors

Solving tasks such as speaker recognition, music classification, or sema...