Researchers have introduced PROCESS-2, a new benchmark speech corpus aimed at advancing the detection of early cognitive impairment. This large-scale dataset includes over 21 hours of audio recordings from 400 participants, categorized into healthy controls, mild cognitive impairment, and dementia diagnoses. The corpus is designed for use with spontaneous and task-oriented speech, featuring manually verified transcripts and participant metadata to support reproducible baseline modeling and clinically meaningful group separation. PROCESS-2 is available under controlled access via Hugging Face to ensure responsible data reuse while safeguarding participant privacy. AI
IMPACT Provides a new, large-scale dataset to advance AI-driven research in early cognitive impairment detection.
RANK_REASON The cluster describes the release of a new benchmark dataset for research purposes, detailed in an arXiv paper.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
