LIWhiz: A Non-Intrusive Lyric Intelligibility Prediction System for the Cadenza Challenge
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915763339657216 |
|---|---|
| author | Shekar, Ram C. M. C. López-Espejo, Iván |
| author_facet | Shekar, Ram C. M. C. López-Espejo, Iván |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LIWhiz: A Non-Intrusive Lyric Intelligibility Prediction System for the Cadenza Challenge Shekar, Ram C. M. C. López-Espejo, Iván Audio and Speech Processing Sound 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. |
| title | LIWhiz: A Non-Intrusive Lyric Intelligibility Prediction System for the Cadenza Challenge |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2512.17937 |