{"ID":2830455,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17937","arxiv_id":"2512.17937","title":"LIWhiz: A Non-Intrusive Lyric Intelligibility Prediction System for the Cadenza Challenge","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.17937","url_pdf":"https://arxiv.org/pdf/2512.17937v2","authors":"[\"Ram C. M. C. Shekar\",\"Iván López-Espejo\"]","published":"2025-12-11T20:26:34Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}