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.

翻译：本研究探讨了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。利用5,754份德语神经心理学评估录音，我们评估了涵盖任务、领域和全局三个评分层级的六项认知任务的表现。我们比较了手工特征与自监督学习嵌入的效果。结果表明，尽管自监督学习表征在较低层级普遍优于手工特征，但这种趋势在轻度认知障碍分类中发生逆转。此外，任务特异性约束影响表现：具有较大回答自由度的任务随层级提升出现性能稀释现象，暗示“专才型”表征；而高度结构化任务的表现则随层级提升而增强，暗示“通才型”表征。这些发现揭示了任务约束与自动化临床语音分析中评估层级间的关联。