InterSpeech 2021

COVID-19 Detection from Spectral features on the DiCOVA Dataset
(Oral presentation)

Kotra Venkata Sai Ritwik (NITK Surathkal, India), Shareef Babu Kalluri (NITK Surathkal, India), Deepu Vijayasenan (NITK Surathkal, India)
In 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 non-stationary (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.