Listen2Cough: Leveraging End-to-End Deep Learning Cough Detection Model to Enhance Lung Health ...
summary
An end-to-end raw-audio model takes uncropped recordings, combining 1D CNN + pre-trained MobileNet and heavy augmentation, trained on multiple public datasets plus two clinical datasets (a controlled quiet study and an uncontrolled clinic visit study). Precision improves significantly over prior cough detectors. A multi-instance attention branch reuses learned features for three diagnostic tasks (healthy vs unhealthy, obstructive vs non-obstructive, COPD vs asthma), consistently outperforming baselines and isolating a few cough snippets that drive each prediction.
AI-written summary · about
chapters (6)
related talks
01h 14mExploring the hidden potential of sound data
45mAuditory Intelligence : beyond speech recognition
43mWhy you can't afford to ignore deep learning
21mDeveloping Machine Learning Based Speech Enhancement Models for Teams and Skype
20mExploring the hidden potential of sound data
28mHow to use Deep Learning to process audio data and classify sounds.
27mThe Story of End to End Models in Deep Learning
26mTraining a TensorFlow model to detect lung nodules on CT scans