Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910833898946560 |
|---|---|
| author | Gao, Yifan Guo, Long Liu, Hong |
| author_facet | Gao, Yifan Guo, Long Liu, Hong |
| contents | 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 pre-trained 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09928 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification Gao, Yifan Guo, Long Liu, Hong Sound Audio and Speech Processing 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 pre-trained 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. |
| title | Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identification |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2412.09928 |