Mahbubur Rahman

TL;DR: In this paper, an end-to-end deep learning architecture using public cough sound datasets was proposed to detect coughs within raw audio recordings. But due to limited lung health data, the authors have difficulty in collecting both cough sounds and lung health condition ground truth.

TL;DR: An exploration of the feasibility of using speech features from natural speech to detect pulmonary disease is presented and patients and healthy subjects were differentiable with 68% accuracy; moreover, the subset of patients with the highest disease severity were detected with 89% accuracy.

TL;DR: Two algorithms are proposed for passive assessment of pulmonary condition: one for detection of obstructive pulmonary disease and the other for estimation of the pulmonary function in terms of FEV1/FVC ratio, which is an established clinical metric.

TL;DR: Wang et al. as mentioned in this paper developed a novel variant of the teacher-student training method for transferring knowledge from an inertial sensor to an acoustic sensor, eliminating the need for manual breathing sound annotation by fusing signal processing with deep learning techniques.