Evaluating Model Interpretability in Speech-Based Clinical Artificial Intelligence Systems.

Purpose: Model interpretability is a critical requirement for deploying artificial intelligence (AI) applications in clinical speech settings, yet existing evaluation methods often overlook this aspect. The complex nature of speech features and the opaque decision-making processes of AI models under...

Descripción completa

Detalles Bibliográficos
Publicado en:Perspectives of the ASHA Special Interest Groups Vol. 10; no. 5; pp. 1637 - 1649
Autores principales: Xu, Lingfeng, Berisha, Visar, Utianski, Rene L., Liss, Julie
Formato: tables/charts Journal Article
Publicado: American Speech-Language-Hearing Association Oct2025
Acceso en línea:Ver este registro en EBSCOhost