arXiv cs.CL· Chuanbo Zhu, Run Luo, Weibo Zhao, Yue Li, Kun Qian, Qiang Qu, Yike Guo, Minghuan Tan, Wei Xue·· 12 小时前AI 评分31
AudiPsy：基于证据的多模态推理用于语音心理咨询对话中的抑郁评估
AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment
AI 导读
研究提出 AudiPsy，一个基于证据的全模态 LLM，用于语音心理咨询对话中的抑郁评估。它采用 Observation-Assessment-Summary（OAS）范式，将对话转录、文本与声学情绪及两者不一致性整合为结构化推理，并构建了合成语料 AudiPsy-Counsel 与三阶段课程。
正文 · 原文
Abstract:Depression assessment from counseling speech requires integrating textual and acoustic psychological evidence across turns, yet existing end-to-end classification approaches lack explicit multimodal evidence interpretation and context-aware reasoning. We propose AudiPsy, an evidence-grounded omni-LLM for depression assessment over spoken counseling conversations. AudiPsy employs an Observation-Assessment-Summary (OAS) paradigm to integrate dialogue transcripts, textual and acoustic emotions, and textual-acoustic emotion incongruence into structured reasoning. OAS incrementally organizes multimodal observations, performs contextualized assessment, and maintains an evolving dialogue summary for subsequent turns. To support this framework, we construct AudiPsy-Counsel, a synthetic spoken counseling conversation corpus with multimodal context augmentation, and develop a unified three-stage curriculum for depression-oriented reasoning. Experiments on DAIC-WOZ demonstrate superior depression assessment performance over specialized depression detection methods and general-purpose speech/omni-LLMs, along with improved reasoning quality, while supplementary evaluation on EATD-Corpus supports AudiPsy's applicability to naturalistic conversations.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27567 [cs.CL] |
| (or arXiv:2610.27567v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27567 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chuanbo Zhu [view email]
[v1]
Tue, 20 Oct 2026 03:31:15 UTC (1,113 KB)
来源：arXiv cs.CL · arxiv.org