Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification

Yifan Gao; Long Guo; Hong Liu

ICASSP 2025accepted0 citations

Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification

Abstract

Cognitive impairment detection through spontaneous speech is a promising avenue for early diagnosis of Alzheimer’s disease (AD) and mild cognitive impairment (MCI), where timely intervention can significantly improve patient outcomes. The PROCESS Grand Challenge at ICASSP 2025 addresses these tasks by promoting innovative classification and regression methods for detecting cognitive decline. In this paper, we propose a multimodal fusion strategy that combines interpretable linguistic features with temporal embeddings extracted from pretrained models. Our approach achieves an F1-score of 0.649 for the classification task (predicting healthy, MCI, dementia) and an RMSE of 2.628 for the regression task (MMSE score prediction), securing the top overall ranking in the competition.

BibTeX

@inproceedings{icassp2025_leveragingmultim,
  title = {Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification},
  author = {Yifan Gao and Long Guo and Hong Liu},
  booktitle = {ICASSP 2025},
  year = {2025}
}