Summary of Hear — Health Acoustic Representations, by Sebastien Baur et al.
HeAR – Health Acoustic Representations
by Sebastien Baur, Zaid Nabulsi, Wei-Hung Weng, Jake Garrison, Louis Blankemeier, Sam Fishman, Christina Chen, Sujay Kakarmath, Minyoi Maimbolwa, Nsala Sanjase, Brian Shuma, Yossi Matias, Greg S. Corrado, Shwetak Patel, Shravya Shetty, Shruthi Prabhakara, Monde Muyoyeta, Diego Ardila
First submitted to arxiv on: 4 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper introduces HeAR, a scalable self-supervised learning-based deep learning system for processing health acoustic sounds like coughs and breaths. The existing deep learning models in the field are often narrowly trained on single tasks, which limits their generalizability to other tasks. To address this issue, the authors develop HeAR using masked autoencoders trained on a large dataset of 313 million two-second long audio clips. The model is evaluated through linear probes and established as a state-of-the-art health audio embedding model on a benchmark of 33 health acoustic tasks across 6 datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary HeAR is a new deep learning system that can process sounds like coughs and breaths to help monitor health and detect diseases. Right now, most systems are only good at one specific task, which limits their ability to help with other tasks. The authors developed HeAR by training it on a huge dataset of audio clips. They tested it and found that it’s really good at processing sounds related to health. |
Keywords
* Artificial intelligence * Deep learning * Embedding * Self supervised
