Decoupled Multi-perspective Fusion for Speech Depression Detection

• Published in: IEEE transactions on affective computing pp. 1 - 15
• Main Authors: Zhao, Minghui, Gao, Hongxiang, Zhao, Lulu, Wang, Zhongyu, Wang, Fei, Zheng, Wenming, Li, Jianqing, Liu, Chengyu
• Format: Journal Article
• Language: English
• Published: IEEE 04.02.2025
• Subjects: Acoustics; Affective computing; Brain modeling; decoupled feature fusion; Depression; Electronic mail; Feature extraction; Long short term memory; Medical diagnostic imaging; Mel frequency cepstral coefficient; multi-perspective; Spectrogram; Speech depression; voiceprint contrastive learning

S peech D epression D etection (SDD) has garnered attention from researchers due to its low cost and convenience. However, current algorithms lack methods for extracting interpretable acoustic features based on clinical manifestations. In addition, effectively fusing these features to overcome indiv...