zhou25f@interspeech_2025@ISCA

Total: 1

#1 Emotion-Guided Graph Attention Networks for Speech-Based Depression Detection under Emotion-Inducting Tasks [PDF1] [Copy] [Kimi1] [REL]

Authors: Yuqiu Zhou, Yongjie Zhou, Yudong Yang, Yang Liu, Jun Huang, Shuzhi Zhao, Rongfeng Su, Lan Wang, Nan Yan

Depression affects emotional expression and perception. As a non-invasive and privacy-preserving method, speech is widely used for automatic depression detection. However, existing models often focus only on depressive features in speech, ignoring the differential emotion expression patterns across different emotion-inducing tasks. To address this, we propose an emotion-guided graph attention network (emoGAT) for depression detection. By collecting speech-text data from depressed individuals and healthy controls during emotion-inducing tasks, we construct graph embeddings using sentiment cues from both speech and text. Experimental results show our method reduces the standard deviation by 1.8% and improves accuracy by 4.36%. Graph attention visualization also reveals depression-specific characteristics, such as flattened prosody in neutral picture description tasks and cognitive biases toward negative information, offering deeper insights into emotional relational expressions.

Subject: INTERSPEECH.2025 - Speech Detection