Leveraging Cascaded Binary Classification and Multimodal Fusion for Dementia Detection through Spontaneous Speech

TL;DR

This paper introduces a cascaded binary classification framework with multimodal fusion for early dementia detection using spontaneous speech, improving accuracy and robustness over baseline methods.

Contribution

It proposes a novel cascaded binary classification approach with pause encoding and an enhanced multimodal fusion system for dementia detection from speech.

Findings

Outperforms baseline models in dementia classification accuracy.

Effective handling of class imbalance through decision restructuring.

Robust regression of MMSE scores using ensemble of multimodal features.

Abstract

This paper presents our submission to the PROCESS Challenge 2025, focusing on spontaneous speech analysis for early dementia detection. For the three-class classification task (Healthy Control, Mild Cognitive Impairment, and Dementia), we propose a cascaded binary classification framework that fine-tunes pre-trained language models and incorporates pause encoding to better capture disfluencies. This design streamlines multi-class classification and addresses class imbalance by restructuring the decision process. For the Mini-Mental State Examination score regression task, we develop an enhanced multimodal fusion system that combines diverse acoustic and linguistic features. Separate regression models are trained on individual feature sets, with ensemble learning applied through score averaging. Experimental results on the test set outperform the baselines provided by the organizers in both tasks, demonstrating the robustness and effectiveness of our approach.