Reproduce “Physiology-Informed Audio Quality and Listening Effort Estimation” 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
Niall McGuire, Dimitra Emmanouilidou
The authors test whether physiological signals can predict audio quality and listening effort, using wearable EEG, fNIRS, eye tracking, and laboratory EEG. Models recover clean-versus-degraded audio above chance for unseen listeners, while wearable EEG and fNIRS show modest correlations with corpus MOS. Effort prediction is limited to within-subject results; clips recur across folds, and quality is not individual preference.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.