UPDF AI

Universal Speech Disorder Recognition: Towards a Foundation Model for Cross-Pathology Generalisation

G. Sanguedolce,D. Gruia,2 著者,F. Geranmayeh

3 件の引用

TLDR

This work addresses the critical challenge of limited training data in healthcare ASR demonstrating that the stroke-specific model generalises effectively across diverse speech pathologies, demonstrating improved recognition accuracy on SONIVA unseen patients, as well as AphasiaBank and DementiaBank.