Our paper titled ‘Depression recognition using a proposed speech chain model fusing speech production and perception features’ has been accepted for publication in Journal of Affective Disorders. Our research introduces an innovative approach to depression diagnosis using a novel machine speech chain model (MSCDR). By combining speech generation and perception features, the MSCDR captures comprehensive depressive speech representations, resulting in significantly improved recognition performance.
Our method demonstrated exceptional accuracy (0.77 and 0.86) and average F1 scores (0.75 and 0.86) on diverse datasets, outperforming existing methods.
License
Copyright 2017-2000 Tao Wang
