Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and to delay further progression. Speech based automatic AD screening systems provide a non-intrusive and more scalable alternative to other clinical screening techniques. Textual embedding features produced by pre-trained language models (PLMs) such as BERT are widely used in such systems. However, PLM domain fine-tuning is commonly based on the masked word or sentence prediction costs that are inconsistent with the back-end AD detection task. To this end, this paper investigates the use of prompt-based fine-tuning of PLMs that consistently uses AD classification errors as the training objective function. Disfluency features based on hesitation or pause filler token frequencies are further incorporated into prompt phrases during PLM fine-tuning. The decision voting based combination among systems using different PLMs (BERT and RoBERTa) or systems with different fine-tuning paradigms (conventional masked-language modelling fine-tuning and prompt-based fine-tuning) is further applied. Mean, standard deviation and the maximum among accuracy scores over 15 experiment runs are adopted as performance measurements for the AD detection system. Mean detection accuracy of 84.20% (with std 2.09%, best 87.5%) and 82.64% (with std 4.0%, best 89.58%) were obtained using manual and ASR speech transcripts respectively on the ADReSS20 test set consisting of 48 elderly speakers.

翻译：阿尔茨海默病（AD）的早期诊断对于促进预防性护理和延缓病情进展至关重要。基于语音的自动AD筛查系统相比其他临床筛查技术，提供了一种非侵入性且更具可扩展性的替代方案。预训练语言模型（PLM，如BERT）生成的文本嵌入特征广泛应用于此类系统中。然而，PLM领域微调通常基于掩码词或句子预测代价，这与后端AD检测任务不一致。为此，本文研究了基于提示的PLM微调方法，该方法一致地使用AD分类错误作为训练目标函数。进一步将基于犹豫或停顿填充词词频的不流畅特征融入PLM微调过程中的提示短语中。进一步应用了基于决策投票的组合方法，该组合可来自使用不同PLM（BERT和RoBERTa）的系统，或采用不同微调范式（传统掩码语言建模微调和基于提示的微调）的系统。采用15次实验运行中准确率的平均值、标准差和最大值作为AD检测系统的性能指标。在由48名老年说话者组成的ADReSS20测试集上，使用人工转录和ASR语音转录本分别获得了84.20%（标准差2.09%，最佳值87.5%）和82.64%（标准差4.0%，最佳值89.58%）的平均检测准确率。