Robust strategies for Alzheimer's disease (AD) detection are important, given the high prevalence of AD. In this paper, we study the performance and generalizability of three approaches for AD detection from speech on the recent ADReSSo challenge dataset: 1) using conventional acoustic features 2) using novel pre-trained acoustic embeddings 3) combining acoustic features and embeddings. We find that while feature-based approaches have a higher precision, classification approaches relying on pre-trained embeddings prove to have a higher, and more balanced cross-validated performance across multiple metrics of performance. Further, embedding-only approaches are more generalizable. Our best model outperforms the acoustic baseline in the challenge by 2.8%.
翻译:鉴于阿尔茨海默氏病(AD)检测的高度流行,因此强有力的战略非常重要。 在本文中,我们从最近ADRESSo挑战数据集的演讲中研究了三种AD检测方法的性能和通用性:1)使用传统的声学特征2)使用新颖的预先训练的声学嵌入3)结合声学特征和嵌入。我们发现,虽然基于地物的方法具有更高的精确度,但依赖预先训练的嵌入的分类方法证明,在多种性能衡量标准中,ADRESSo测试的三种方法的性能和通用性比较高。此外,只嵌入式方法比较普遍。我们最好的模型比2.8%的声学基准要强。