Ritwik, K.V.S.Kalluri, S.B.Vijayasenan, D.2026-02-062021Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2021, Vol.6, , p. 4266-42702308457Xhttps://doi.org/10.21437/Interspeech.2021-1031https://idr.nitk.ac.in/handle/123456789/30313In this paper we investigate the cues of COVID-19 on sustained phonation of Vowel-/i/, deep breathing and number counting data of the DiCOVA dataset. We use an ensemble of classifiers trained on different features, namely, super-vectors, formants, harmonics and MFCC features. We fit a two-class Weighted SVM classifier to separate the COVID-19 audio from Non-COVID-19 audio. Weighted penalties help mitigate the challenge of class imbalance in the dataset. The results are reported on the stationary (breathing, Vowel-/i/) and nonstationary( counting data) data using individual and combination of features on each type of utterance. We find that the Formant information plays a crucial role in classification. The proposed system resulted in an AUC score of 0.734 for cross validation, and 0.717 for evaluation dataset. © © 2021 ISCA.AcousticsCOVID-19HealthcareMachine learningRespiratory diagnosis