Metraipolis › archive › dc_c968bb8db737

FUSEMOS: Perceptual Evaluation of Text-to-Music Generation with Dual-Encoder Fusion and Ranking-Aware Composite Loss — arXiv:2611.07562

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07562
License (as archived)
CC0-1.0
Archived
2026-11-06T15:00:06.988Z
SHA-256 of the archived text
a0a9246fe68f1c3d355275ec7bdda206d0049ebfc3fc797970e9e27301737569
Stable URL of this page
https://metraipolis.com/documento/dc_c968bb8db737

How to cite

FUSEMOS: Perceptual Evaluation of Text-to-Music Generation with Dual-Encoder Fusion and Ranking-Aware Composite Loss — arXiv:2611.07562 — arXiv (en), https://arxiv.org/abs/2611.07562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c968bb8db737 (Metraipolis archive dc_c968bb8db737, sha256 a0a9246fe68f1c3d355275ec7bdda206d0049ebfc3fc797970e9e27301737569)
BibTeX
@misc{dcc968bb8db737,
  title = {FUSEMOS: Perceptual Evaluation of Text-to-Music Generation with Dual-Encoder Fusion and Ranking-Aware Composite Loss — arXiv:2611.07562},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07562},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c968bb8db737; sha256 a0a9246fe68f1c3d355275ec7bdda206d0049ebfc3fc797970e9e27301737569},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Perceptual evaluation of generated music is essential for developing text-to-music (TTM) generation systems. Existing automatic music perceptual evaluation methods rely solely on the contrastive language audio pretraining (CLAP) model to extract both audio and text features for predicting human-annotated mean opinion scores (MOS), particularly for overall musical impression (OMI) and textual alignment (TA). However, CLAP is limited in capturing fine-grained musical attributes such as timbre and expressiveness \emph{etc}. To address this, we propose FUSEMOS, a dual-encoder fusion framework that integrates CLAP with MERT, a self-supervised model pretrained on large scale music audio, to better capture both high level semantic alignment and detailed musical characteristics for more accurate OMI and TA estimation. Furthermore, to overcome the limitations of conventional regression losses in measuring human preferred relative ranking of music segments, we design a novel ranking-aware composite loss function. Experiments conducted on the MusicEval benchmark demonstrate that our approach outperforms the existing SOTA methods in both mean squared error and rank correlation metrics by a large margin.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2611.07562 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:42:06.073Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).