Continue reading below for the Scientific Data or Click Here for an RTVA Overview.
There are two patents filed that protect the Real Time Voice Analyzer –The first is for the science of detecting respiratory illness voice biomarkers using neural networks and the second is for the technology that processes and securely delivers screening results.
INTERPRETING GLOTTAL FLOW DYNAMICS FOR DETECTING COVID-19 FROM VOICE
The experiment is conducted using a 5-fold Cross validation setup. The partitioning ensured that all recordings from a selected speaker remained in the same fold — i.e. partitioning was based on speaker ids. We obtained an ROC AUC score of 0.946 with a Random Forest classifier trained by automatically filtering out some instances that exhibited lower confidence in classifying COVID vs non COVID. A threshold of 0.7 classifier confidence was used in the filtering step.