Skip to main content
. 2021 Dec 17;141:105153. doi: 10.1016/j.compbiomed.2021.105153

Fig. 2.

Fig. 2

Pre-processed speech (counting from 1 to 20 at a normal pace) from both COVID-19 positive and COVID-19 negative subjects in the Coswara dataset. In contrast to breath (Fig. 1), the spectral energy in this speech is concentrated below 1 kHz.