HeAR -- Health Acoustic Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909127748354048 |
|---|---|
| author | Baur, Sebastien Nabulsi, Zaid Weng, Wei-Hung Garrison, Jake Blankemeier, Louis Fishman, Sam Chen, Christina Kakarmath, Sujay Maimbolwa, Minyoi Sanjase, Nsala Shuma, Brian Matias, Yossi Corrado, Greg S. Patel, Shwetak Shetty, Shravya Prabhakara, Shruthi Muyoyeta, Monde Ardila, Diego |
| author_facet | Baur, Sebastien Nabulsi, Zaid Weng, Wei-Hung Garrison, Jake Blankemeier, Louis Fishman, Sam Chen, Christina Kakarmath, Sujay Maimbolwa, Minyoi Sanjase, Nsala Shuma, Brian Matias, Yossi Corrado, Greg S. Patel, Shwetak Shetty, Shravya Prabhakara, Shruthi Muyoyeta, Monde Ardila, Diego |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02522 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HeAR -- Health Acoustic Representations Baur, Sebastien Nabulsi, Zaid Weng, Wei-Hung Garrison, Jake Blankemeier, Louis Fishman, Sam Chen, Christina Kakarmath, Sujay Maimbolwa, Minyoi Sanjase, Nsala Shuma, Brian Matias, Yossi Corrado, Greg S. Patel, Shwetak Shetty, Shravya Prabhakara, Shruthi Muyoyeta, Monde Ardila, Diego Machine Learning Artificial Intelligence 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. |
| title | HeAR -- Health Acoustic Representations |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.02522 |