Clinically Inspired Symptom-Guided Depression Detection from Emotion-Aware Speech Representations
Preprint
Abstract
Depression manifests through a diverse set of symptoms such as sleep disturbance, loss of interest, and concentration difficulties. However, most existing works treat depression prediction either as a binary label or an overall severity score without explicitly modeling symptom-specific information. This limits their ability to provide symptom-level analysis relevant to clinical screening. To address this, we propose a symptom-specific and clinically inspired framework for depression severity estimation from speech. Our approach uses a symptom-guided cross-attention mechanism that aligns PHQ-8 questionnaire items with emotion-aware speech representations to identify which segments of a participant's speech are more important to each symptom. To account for differences in how symptoms are expressed over time, we introduce a learnable symptom-specific parameter that adaptively controls the sharpness of attention distributions. Our results on EDAIC, a standard clinical-style dataset, demonstrate improved performance outperforming prior works. Further, analyzing the attention distributions showed that higher attention is assigned to utterances containing cues related to multiple depressive symptoms, highlighting the interpretability of our approach. These findings outline the importance of symptom-guided and emotion-aware modeling for speech-based depression screening.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Self-Supervised Embeddings for Detecting Individual Symptoms of Depression2024
- IIFDD: Intra and inter-modal fusion for depression detection with multi-modal information from Internet of Medical ThingsInformation Fusion, 2023
- Spatial–Temporal Feature Network for Speech-Based Depression RecognitionIEEE Transactions on Cognitive and Developmental Systems, 2023
- Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence GapIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- MFCC-based Recurrent Neural Network for automatic clinical depression recognition and assessment from speechBiomedical Signal Processing and Control, 2022
- Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training2021
- Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast RecordingsIEEE Transactions on Affective Computing, 2017
- The PHQ-8 as a measure of current depression in the general populationJournal of Affective Disorders, 2009
- Acoustic analysis of speech variables during depression and after improvementActa Psychiatrica Scandinavica, 1987