Audio-based cough counting using independent subspace analysis

TL;DR

This paper introduces an audio analysis algorithm that automatically detects cough events in recordings using independent subspace analysis, reducing manual counting time and providing reliable event summaries.

Contribution

The paper presents a novel application of independent subspace analysis for automatic cough detection in audio recordings, improving efficiency and accuracy over manual methods.

Findings

True positive rate of 76%

Average of 2.85 false positives per minute

Effective in synthesized ambulatory audio scenarios

Abstract

In this paper, an algorithm designed to detect characteristic cough events in audio recordings is presented, significantly reducing the time required for manual counting. Using time-frequency representations and independent subspace analysis (ISA), sound events that exhibit characteristics of coughs are automatically detected, producing a summary of the events detected. Using a dataset created from publicly available audio recordings, this algorithm has been tested on a variety of synthesized audio scenarios representative of those likely to be encountered by subjects undergoing an ambulatory cough recording, achieving a true positive rate of 76% with an average of 2.85 false positives per minute.