研究语音表征与认知评估层级的关系，发现任务约束影响诊断效果。
Beyond Binary: Speech Representations Across the Cognitive Score Hierarchy
- 比较手工特征与自监督嵌入在不同层级的表现
- 低层级中自监督优于手工特征，但痴呆分类时反超
- 自由度高的任务表现随层级上升下降，结构化任务则相反
本研究探讨轻度认知障碍中语音表征与认知评估层级结构之间的关系。基于5,754段德语神经心理学评估录音，评估六项认知任务在任务、领域和全局三个评分层级上的表现。对比了手工声学特征与自监督学习（SSL）嵌入的性能。结果表明，尽管在较低层级上SSL表示普遍优于手工特征，但在轻度认知障碍分类任务中这一趋势反转。此外，任务特异性约束影响表现：响应自由度较高的任务在层级升高时性能下降，暗示其具有“专业型”表征；而高度结构化任务的性能随层级提升而增强，提示其具备“通用型”表征。这些发现揭示了任务约束与评估层级在自动化临床语音分析中的关联。
原文摘要 · Abstract (English)
This study examines the relationship between speech representations and the hierarchical structure of cognitive assessment in mild cognitive impairment. Utilizing 5,754 German neuropsychological assessment recordings, we evaluate six cognitive tasks across three score levels: task, domain, and global levels. We compare hand-crafted acoustic features with self-supervised learning (SSL) embeddings. Results show that although SSL representations generally outperform hand-crafted features at lower levels, this trend reverses for MCI classification. Furthermore, task-specific constraints influence performance: tasks with greater response freedom exhibit performance dilution as hierarchical levels increase, suggesting ``specialist'' representations, whereas the performance of highly structured tasks increases toward higher levels, suggesting ``generalist'' representations. These findings show links between task constraints and assessment hierarchy in automated clinical speech analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。