Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Nana, Zhu, Youxiang, Liang, Xiaohui, Batsis, John A., Summerour, Caroline
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909379661398016
author Lin, Nana
Zhu, Youxiang
Liang, Xiaohui
Batsis, John A.
Summerour, Caroline
author_facet Lin, Nana
Zhu, Youxiang
Liang, Xiaohui
Batsis, John A.
Summerour, Caroline
contents Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with spontaneous voice assistant (VA) commands from 35 older adults in a controlled setting. Specifically, a command-generation task is designed with pre-defined intents for participants to freely generate commands that are more associated with cognitive ability than read commands. We develop MCI classification and regression models with audio, textual, intent, and multimodal fusion features. We find the command-generation task outperforms the command-reading task with an average classification accuracy of 82%, achieved by leveraging multimodal fusion features. In addition, generated commands correlate more strongly with memory and attention subdomains than read commands. Our results confirm the effectiveness of the command-generation task and imply the promise of using longitudinal in-home commands for MCI detection.
format Preprint
id arxiv_https___arxiv_org_abs_2411_04158
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection
Lin, Nana
Zhu, Youxiang
Liang, Xiaohui
Batsis, John A.
Summerour, Caroline
Audio and Speech Processing
Computation and Language
Machine Learning
Sound
Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with spontaneous voice assistant (VA) commands from 35 older adults in a controlled setting. Specifically, a command-generation task is designed with pre-defined intents for participants to freely generate commands that are more associated with cognitive ability than read commands. We develop MCI classification and regression models with audio, textual, intent, and multimodal fusion features. We find the command-generation task outperforms the command-reading task with an average classification accuracy of 82%, achieved by leveraging multimodal fusion features. In addition, generated commands correlate more strongly with memory and attention subdomains than read commands. Our results confirm the effectiveness of the command-generation task and imply the promise of using longitudinal in-home commands for MCI detection.
title Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection
topic Audio and Speech Processing
Computation and Language
Machine Learning
Sound
url https://arxiv.org/abs/2411.04158