Reproduce “NUVA: A Naming Utterance Verifier for Aphasia Treatment” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
David Sabate Barbera, Mark Huckvale, Victoria Fleming, Emily Upton, Henry Coley-Fisher, Catherine Doogan, Ian Shaw, William Latham and 2 more
NUVA checks aphasic picture-naming attempts against healthy-speaker recordings of target words. It compares phone-probability sequences using dynamic time warping and a distance threshold. Among eight British-English participants, adapted NUVA reached 0.913 accuracy versus 0.882 for Google’s speech-to-text service. This small study did not test treatment outcomes or establish performance across broader patient populations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.