Assessment of Audio Features for Automatic Cough Detection
This work addresses the problem of quantifying and qualifying pathology for patients with respiratory diseases like mucoviscidosis, but it is incremental as it builds on existing methods for feature assessment and classification.
The paper tackled automatic cough detection from audio recordings by proposing a large set of audio features and evaluating them using mutual information measures and three classifiers, achieving results that confirmed the features' efficiency, though no specific performance numbers were provided.
This paper addresses the issue of cough detection using only audio recordings, with the ultimate goal of quantifying and qualifying the degree of pathology for patients suffering from respiratory diseases, notably mucoviscidosis. A large set of audio features describing various aspects of the audio signal is proposed. These features are assessed in two steps. First, their intrisic potential and redundancy are evaluated using mutual information-based measures. Secondly, their efficiency is confirmed relying on three classifiers: Artificial Neural Network, Gaussian Mixture Model and Support Vector Machine. The influence of both the feature dimension and the classifier complexity are also investigated.