works on
data-driven acoustics 1impulse response fingerprinting 1machine learning evaluation 1room acoustic parameter prediction 1validation protocols 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

eess.AS2026

What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters

Akın Oktav

The paper investigates how evaluation protocols and input availability affect the reported accuracy of machine‑learning models that predict ISO 3382‑1 room acoustic parameters from…