Metraipolis › archive › dc_fbafbc0fd12b
ARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric Authoring — arXiv:2610.07902
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07902
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:23:15.573Z
- SHA-256 of the archived text
fba781106128fff49c94c1ce8f9e7daa4b55c56dfc8e0e513536cb0367ed2a05- Stable URL of this page
https://metraipolis.com/documento/dc_fbafbc0fd12b
How to cite
ARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric Authoring — arXiv:2610.07902 — arXiv (en), https://arxiv.org/abs/2610.07902 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbafbc0fd12b (Metraipolis archive dc_fbafbc0fd12b, sha256 fba781106128fff49c94c1ce8f9e7daa4b55c56dfc8e0e513536cb0367ed2a05)
BibTeX
@misc{dcfbafbc0fd12b,
title = {ARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric Authoring — arXiv:2610.07902},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07902},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbafbc0fd12b; sha256 fba781106128fff49c94c1ce8f9e7daa4b55c56dfc8e0e513536cb0367ed2a05},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07902. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cantonese lyric writing requires close alignment between lexical tones and melodic pitch. Existing melody-guided lyric generation methods typically rely on symbolic melody to generate lyrics. However, in real songwriting scenarios, melodies are often expressed as raw singing audio or hummed recordings, where pitch is implicit, noisy, and unstructured, making these methods difficult to apply directly. To address this limitation, we propose ARIA, a two-stage audio-driven melody-tone relation modeling framework for Cantonese lyric authoring that generates Cantonese lyrics from singing recordings with provided character-level timestamps. Specifically, we first design a Tri-Stream Relation-Aware Tone Estimator (TRATE) to predict 0243 sequences from timestamped singing audio by modeling multi-stream acoustic cues and relational tonal structure. We then propose a Decoupled Retrieval-Augmented Tone-Conditioned Lyric Generator (DRA-TCLG) to generate fluent lyrics conditioned on predicted tonal plans with retrieval-enhanced lexical guidance. Moreover, we construct a large-scale aligned audio-Jyutping-0243 dataset from real Cantonese singing recordings to support this new task. Experimental results demonstrate that ARIA achieves strong performance in both 0243 prediction and tone-consistent lyric generation, validating the effectiveness of the proposed framework. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.07902 — 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 2026-10-07T11:15:39.439Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).