Cross-Lingual Alzheimer’s Disease Detection Based on Paralinguistic and Pre-Trained Features

We present our submission to the ICASSP-SPGC-2023 ADReSS-M Challenge Task, which aims to investigate which acoustic features can be generalized and transferred across languages for Alzheimer’s Disease (AD) prediction. The challenge consists of two tasks: one is to classify the speech of AD patients and healthy individuals, and the other is to infer Mini Mental State Examination (MMSE) score based on speech only. The difficulty is mainly embodied in the mismatch of the dataset, in which the training set is in English while the test set is in Greek. We extract paralinguistic features using openSmile toolkit and acoustic features using XLSR-53. In addition, we extract linguistic features after transcribing the speech into text. These features are used as indicators for AD detection in our method. Our method achieves an accuracy of 69.6% on the classification task and a root mean squared error (RMSE) of 4.788 on the regression task. The results show that our proposed method is expected to achieve automatic multilingual Alzheimer’s Disease detection through spontaneous speech.

1. INTRODUCTION

Alzheimer’s Disease (AD) is a neurodegenerative disease. When suffering from AD, pathological changes occur in patients’ brain, resulting in cognitive decline, expression degradation and other phenomena. Patients in different countries have similar symptoms. Clinical research shows that early treatment can delay the deterioration of AD. Therefore, the development of AD detection approach is crucial for the treatment of this disease. Although some researchers have carried out AD detection tasks on a single language [1], there are relatively few studies on cross-lingual AD detection. The academia still lacks a unified understanding of which speech features can be used for cross-lingual AD detection. The ICASSP-SPGC-2023 ADReSS-M challenge task aims to investigate how to extract generic acoustic features from speech for multilingual AD detection [2].