HeAR -- Health Acoustic Representations

Health acoustic sounds such as coughs and breaths are known to contain useful health signals with significant potential for monitoring health and disease, yet are underexplored in the medical machine learning community. The existing deep learning systems for health acoustics are often narrowly train...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Baur, Sebastien, Nabulsi, Zaid, Wei-Hung, Weng, Garrison, Jake, Blankemeier, Louis, Fishman, Sam, Chen, Christina, Kakarmath, Sujay, Minyoi Maimbolwa, Sanjase, Nsala, Shuma, Brian, Matias, Yossi, Corrado, Greg S, Patel, Shwetak, Shetty, Shravya, Shruthi Prabhakara, Muyoyeta, Monde, Ardila, Diego
Format: Article
Language:English
Subjects:
Acoustics
Datasets
Deep learning
Machine learning
Self-supervised learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Health acoustic sounds such as coughs and breaths are known to contain useful health signals with significant potential for monitoring health and disease, yet are underexplored in the medical machine learning community. The existing deep learning systems for health acoustics are often narrowly trained and evaluated on a single task, which is limited by data and may hinder generalization to other tasks. To mitigate these gaps, we develop HeAR, a scalable self-supervised learning-based deep learning system using masked autoencoders trained on a large dataset of 313 million two-second long audio clips. Through linear probes, we establish HeAR as a state-of-the-art health audio embedding model on a benchmark of 33 health acoustic tasks across 6 datasets. By introducing this work, we hope to enable and accelerate further health acoustics research.
ISSN:2331-8422