Dementia classification from speech using machine learning

Researchers have developed a new method for classifying dementia using spontaneous speech, analyzing acoustic features from entire recordings rather than just speech-active segments. This approach, utilizing the openSMILE toolkit and wrapper-based feature selection, identifies diagnostically relevant characteristics. The extreme minimal learning machine classifier proved to be the most computationally efficient, offering competitive accuracy and serving as a supportive tool for dementia assessment. AI

IMPACT This research could lead to more accessible and efficient tools for early dementia detection, aiding clinical assessment.

RANK_REASON Academic paper detailing a novel methodology for dementia classification using machine learning on speech data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• ADReSS dataset
• Alzheimer's disease
• Dementia
• Marko Niemelä
• openSMILE toolkit
• Pitt Corpus

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →