EarCough: Enabling Continuous Subject Cough Event Detection on Hearables
This enables continuous cough monitoring for individual pulmonary health applications using hearables, representing an incremental improvement by adapting existing methods to a new platform.
The paper tackled the problem of continuous subject cough event detection for pulmonary health monitoring by proposing EarCough, a lightweight neural network model that leverages active noise cancellation microphones on hearables, achieving 95.4% accuracy and 92.9% F1-score with 385 kB space.
Cough monitoring can enable new individual pulmonary health applications. Subject cough event detection is the foundation for continuous cough monitoring. Recently, the rapid growth in smart hearables has opened new opportunities for such needs. This paper proposes EarCough, which enables continuous subject cough event detection on edge computing hearables by leveraging the always-on active noise cancellation (ANC) microphones. Specifically, we proposed a lightweight end-to-end neural network model -- EarCoughNet. To evaluate the effectiveness of our method, we constructed a synchronous motion and audio dataset through a user study. Results show that EarCough achieved an accuracy of 95.4% and an F1-score of 92.9% with a space requirement of only 385 kB. We envision EarCough as a low-cost add-on for future hearables to enable continuous subject cough event detection.