Skip to main content
. 2023 Jan 30;89:101754. doi: 10.1016/j.pmcj.2023.101754

Fig. 1.

Fig. 1

COVID-19 detection approaches: (1) extraction of handcrafted acoustic features from the audio waveform, which are then classified by a shallow ML model; (2) usage of a pre-trained deep learning model as features extractor, in series with a shallow model to classify the deep audio embeddings; and (3) fine-tuning of the pre-trained deep model for both features extraction and classification.