CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech

TL;DR

CogniVoice is a novel multimodal and multilingual framework that effectively detects Mild Cognitive Impairment and estimates MMSE scores from speech data, outperforming baseline models across languages.

Contribution

Introduces CogniVoice, a new ensemble multimodal and multilingual network based on 'Product of Experts' for MCI detection and MMSE estimation from speech.

Findings

Outperforms baseline models in MCI classification and MMSE regression.

Reduces performance gap across different languages.

Achieves 2.8 F1 points improvement in classification.

Abstract

Mild Cognitive Impairment (MCI) is a medical condition characterized by noticeable declines in memory and cognitive abilities, potentially affecting individual's daily activities. In this paper, we introduce CogniVoice, a novel multilingual and multimodal framework to detect MCI and estimate Mini-Mental State Examination (MMSE) scores by analyzing speech data and its textual transcriptions. The key component of CogniVoice is an ensemble multimodal and multilingual network based on ``Product of Experts'' that mitigates reliance on shortcut solutions. Using a comprehensive dataset containing both English and Chinese languages from TAUKADIAL challenge, CogniVoice outperforms the best performing baseline model on MCI classification and MMSE regression tasks by 2.8 and 4.1 points in F1 and RMSE respectively, and can effectively reduce the performance gap across different language groups by 0.7 points in F1.