arXiv 2409.003912024-08-31cs.SDcs.AIeess.AS

密度自适应注意力语音网络：增强心理健康障碍的特征理解

Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders

James Silberrad Brown Center for Artificial Intelligence（詹姆斯·西尔伯拉德·布朗人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）；Amazon GenAI（亚马逊生成式人工智能）

Georgios Ioannides, Adrian Kieback, Aman Chadha, Aaron Elkins

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出DAAMAudioCNNLSTM和DAAMAudioTransformer两种参数高效且可解释的语音抑郁症检测模型，通过多头密度自适应注意力机制动态聚焦关键语音片段，在DAIC-WOZ数据集上取得领先性能，且无需额外补充信息。

摘要：

基于语音的抑郁症检测由于其在个体间表现独特且数据稀缺，对自动化检测构成重大挑战。为应对这些挑战，我们提出了DAAMAudioCNNLSTM和DAAMAudioTransformer，这两种参数高效且可解释的模型用于音频特征提取和抑郁症检测。DAAMAudioCNNLSTM采用新颖的CNN-LSTM框架，并配备多头密度自适应注意力机制（DAAM），动态聚焦于信息丰富的语音片段。DAAMAudioTransformer利用Transformer编码器替代CNN-LSTM架构，并集成相同的DAAM模块以增强注意力和可解释性。这些方法不仅提高了检测的鲁棒性和可解释性，还取得了最先进的性能：在DAIC-WOZ数据集上，DAAMAudioCNNLSTM的F1宏平均得分为0.702，DAAMAudioTransformer的F1宏平均得分为0.72，且在训练/验证过程中不依赖元音位置和说话人信息等补充信息，而此前的方法则依赖这些信息。两个模型在利用语音信号进行抑郁症检测方面展现出显著的可解释性和效率，标志着向更可靠、更具临床实用性的诊断工具迈出了一步，有望推动语音和心理健康护理的进步。为促进该领域的进一步研究，我们公开了代码。

英文摘要：

Speech-based depression detection poses significant challenges for automated detection due to its unique manifestation across individuals and data scarcity. Addressing these challenges, we introduce DAAMAudioCNNLSTM and DAAMAudioTransformer, two parameter efficient and explainable models for audio feature extraction and depression detection. DAAMAudioCNNLSTM features a novel CNN-LSTM framework with multi-head Density Adaptive Attention Mechanism (DAAM), focusing dynamically on informative speech segments. DAAMAudioTransformer, leveraging a transformer encoder in place of the CNN-LSTM architecture, incorporates the same DAAM module for enhanced attention and interpretability. These approaches not only enhance detection robustness and interpretability but also achieve state-of-the-art performance: DAAMAudioCNNLSTM with an F1 macro score of 0.702 and DAAMAudioTransformer with an F1 macro score of 0.72 on the DAIC-WOZ dataset, without reliance on supplementary information such as vowel positions and speaker information during training/validation as in previous approaches. Both models' significant explainability and efficiency in leveraging speech signals for depression detection represent a leap towards more reliable, clinically useful diagnostic tools, promising advancements in speech and mental health care. To foster further research in this domain, we make our code publicly available.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。