Saved in:
Bibliographic Details
Main Authors: Shekar, Ram C. M. C., López-Espejo, Iván
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17937
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We present LIWhiz, a non-intrusive lyric intelligibility prediction system submitted to the ICASSP 2026 Cadenza Challenge. LIWhiz leverages Whisper for robust feature extraction and a trainable back-end for score prediction. Tested on the Cadenza Lyric Intelligibility Prediction (CLIP) evaluation set, LIWhiz achieves a root mean square error (RMSE) of 27.07%, a 22.4% relative RMSE reduction over the STOI-based baseline, yielding a substantial improvement in normalized cross-correlation.