“How are you?” Estimation of anxiety, sleep quality, and mood using computational voice analysis

Abstract: We developed a method of estimating impactors of cognitive function (ICF) – such as anxiety, sleep quality, and mood – using computational voice analysis. Clinically validated questionnaires (VQs) were used to score anxiety, sleep and mood while salient voice features were extracted to train regression models with deep neural networks. Experiments with 203 subjects showed promising results with significant concordance correlation coefficients (CCC) between actual VQ scores and the predicted scores (0.46 = anxiety, 0.50 = sleep quality, 0.45 = mood).

S. Kim, N. Kwon, H. O’Connell, N. Fisk, S. Ferguson and M. Bartlett, “”How are you?” Estimation of anxiety, sleep quality, and mood using computational voice analysis,” 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 2020, pp. 5369-5373, doi: 10.1109/EMBC44109.2020.9175788.