Optimising MFCC parameters for the automatic detection of respiratory diseases
Yuyang Yan, Sami O. Simons, Loes van Bemmel, Lauren Reinders, Frits M. E. Franssen, Visara Urovi
TL;DR
The paper tackles automatic detection of respiratory diseases from voice and shows that MFCC extraction parameters critically influence diagnostic accuracy. It systematically sweeps the coefficient count $L$, frame length $N$, and hop length $M$ across four datasets (Cambridge COVID-19 Sound, Coswara, Saarbrücken SVD, and TACTICAS) using a binary SVM with an RBF kernel, with LSTM validation and external testing. The key finding is that an optimized configuration ($L \approx 30$, $N=25$ ms, $M=5$ ms) yields substantial accuracy gains—up to about 19–21 percentage points over the worst parameter settings—and generalizes across datasets and languages. Overall, the work demonstrates that MFCC parameter optimization can meaningfully improve remote, acoustic-based screening of respiratory diseases and provides practical guidance for parameter selection in deployment scenarios.
Abstract
Voice signals originating from the respiratory tract are utilized as valuable acoustic biomarkers for the diagnosis and assessment of respiratory diseases. Among the employed acoustic features, Mel Frequency Cepstral Coefficients (MFCC) is widely used for automatic analysis, with MFCC extraction commonly relying on default parameters. However, no comprehensive study has systematically investigated the impact of MFCC extraction parameters on respiratory disease diagnosis. In this study, we address this gap by examining the effects of key parameters, namely the number of coefficients, frame length, and hop length between frames, on respiratory condition examination. Our investigation uses four datasets: the Cambridge COVID-19 Sound database, the Coswara dataset, the Saarbrucken Voice Disorders (SVD) database, and a TACTICAS dataset. The Support Vector Machine (SVM) is employed as the classifier, given its widespread adoption and efficacy. Our findings indicate that the accuracy of MFCC decreases as hop length increases, and the optimal number of coefficients is observed to be approximately 30. The performance of MFCC varies with frame length across the datasets: for the COVID-19 datasets (Cambridge COVID-19 Sound database and Coswara dataset), performance declines with longer frame lengths, while for the SVD dataset, performance improves with increasing frame length (from 50 ms to 500 ms). Furthermore, we investigate the optimized combination of these parameters and observe substantial enhancements in accuracy. Compared to the worst combination, the SVM model achieves an accuracy of 81.1%, 80.6%, and 71.7%, with improvements of 19.6%, 16.10%, and 14.90% for the Cambridge COVID-19 Sound database, the Coswara dataset, and the SVD dataset respectively.