针对临床访谈中的 AD 与抑郁症语音自动检测，本文提出用动态 Dirichlet 先验建模二阶概率的贝叶斯置信度估计方法，并在 ADReSS 和 DAIC-WOZ 上取得优于基线的分类与置信度估计效果。
摘要：
基于语音的阿尔茨海默病（AD）和抑郁症自动检测已受到越来越多的关注。置信度估计对于可信的自动诊断系统至关重要，它可向临床医生告知模型预测的置信度，并帮助降低误诊风险。本文研究基于临床访谈的 AD 与抑郁症自动检测的置信度估计。文中提出一种新颖的贝叶斯方法，该方法使用动态 Dirichlet 先验分布来建模预测分布的二阶概率。在公开可用的 ADReSS 和 DAIC-WOZ 数据集上的实验结果表明，所提方法在分类准确率和置信度估计方面均优于一系列基线方法。
英文摘要：
Speech-based automatic detection of Alzheimer's disease (AD) and depression has attracted increased attention. Confidence estimation is crucial for a trust-worthy automatic diagnostic system which informs the clinician about the confidence of model predictions and helps reduce the risk of misdiagnosis. This paper investigates confidence estimation for automatic detection of AD and depression based on clinical interviews. A novel Bayesian approach is proposed which uses a dynamic Dirichlet prior distribution to model the second-order probability of the predictive distribution. Experimental results on the publicly available ADReSS and DAIC-WOZ datasets demonstrate that the proposed method outperforms a range of baselines for both classification accuracy and confidence estimation.
A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks
College of Computing, Georgia Institute of Technology（佐治亚理工学院计算机学院）；Georgia Tech Research Institute, Georgia Institute of Technology（佐治亚理工学院研究 institute）
Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data
Winterlight Labs（Winterlight实验室）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（Vector人工智能研究所）；Li Ka Shing Knowledge Institute（李嘉诚知识研究院）；St Michael’s Hospital（圣迈克尔医院）；Surgical Safety Technologies Inc.（手术安全技术公司）
Probabilistic Textual Time Series Depression Detection
Department of Computer Science, KTH Royal Institute of Technology（计算机科学系，皇家理工学院）；Department of Information Technology, Uppsala University（信息科技系，乌普萨拉大学）
DAIC-WOZ: On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interviews
Idiap Research Institute（伊迪亚普研究所）；Mathematics Research Center (CIMAT)（数学研究中心（CIMAT））；Consejo Nacional de Humanidades, Ciencias y Tecnologías (CONAHCYT)（国家人文科学与技术委员会（CONAHCYT））；Brno University of Technology（布尔诺理工大学）
Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches
Computer Science University of Colorado Boulder Boulder, CO, USA；Inst. Cognitive Science \& Computer Science University of Colorado Boulder Boulder, CO, USA
Evaluating Lexicon Incorporation for Depression Symptom Estimation
Normandie Univ, UNICAEN, ENSICAEN, CNRS, GREYC（诺曼底大学、卡昂大学、卡昂高等工程师学院、法国国家科学研究中心、格雷西研究所）；Institute of Computer Science, University of Tartu（塔尔图大学计算机科学研究所）
MAGI: Multi-Agent Guided Interview for Psychiatric Assessment
Tsinghua University（清华大学）；Central South University（中南大学）；Beijing Institute of Technology（北京理工大学）；Sichuan University（四川大学）；Lingxin AI（灵心人工智能公司）；University of International Relations（国际关系学院）；Central University of Finance and Economics（中央财经大学）
Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China（哈尔滨工业大学（深圳）计算机科学与技术学院）；School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China（江南大学人工智能与计算机学院）；Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）；Pengcheng Laboratory（鹏城实验室）；Chinese People’s Liberation Army General Hospital, Beijing, China（中国人民解放军总医院）
Enhancing Depression-Diagnosis-Oriented Chat with Psychological State Tracking
School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）；Shanghai Institute of Al for Education, East China Normal University（东华大学上海人工智能教育研究所）；School of Psychology and Cognitive Science, East China Normal University（东华大学心理学与认知科学学院）
MMFformer: Multimodal Fusion Transformer Network for Depression Detection
Centre for Pattern Analysis and Machine Intelligence, Department of Electrical and Computer Engineering, University of Waterloo（模式分析与机器智能中心，电气与计算机工程系，滑铁卢大学）；School of Engineering and Computing, Department of Computer Science and Engineering, American University of Ras Al Khaimah（工程与计算学院，计算机科学与工程系，阿联酋拉线哈姆斯美国大学）
DECT: Harnessing LLM-assisted Fine-Grained Linguistic Knowledge and Label-Switched and Label-Preserved Data Generation for Diagnosis of Alzheimer's Disease
The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）
