MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918483941392384 |
|---|---|
| author | Tsai, Fang-Duo Lai, Yi-An Chen, Fei-Yueh Fu, Hsueh-Wei Lee, Wei-Jaw Cheng, Hao-Chung Yang, Yi-Hsuan |
| author_facet | Tsai, Fang-Duo Lai, Yi-An Chen, Fei-Yueh Fu, Hsueh-Wei Lee, Wei-Jaw Cheng, Hao-Chung Yang, Yi-Hsuan |
| contents | While end-to-end lyrics-to-song models offer convenience for casual users, professional songwriters require score-to-song systems that allow them to retain authorship over the core melody. However, existing score-to-song methods are limited to short-form snippets and fail to maintain coherence in long-form generation, particularly during vocal-silent sections like intros and bridges. To address this long-form bottleneck, we propose MIDI-informed singing accompaniment generation (MIDI-SAG). Unlike conventional audio-only models, MIDI-SAG utilizes symbolic timing and chord information derived from the vocal MIDI to provide a stable musical roadmap. By incorporating structure planning, which defines temporal boundaries and semantic labels, our framework facilitates consistent generation across both vocal and non-vocal sections. We demonstrate the feasibility of this compositional pipeline by leveraging specialized pre-trained modules, enabling data-efficient training on a single GPU. Our experiments show the potential of this approach for both professional score-to-song and general lyrics-to-song tasks. While an early exploration, MIDI-SAG suggests a promising direction for structured, long-form music synthesis. Audio demos are available, and the code will be open-sourced at https://composerflow.github.io/web_revealed/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22029 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline Tsai, Fang-Duo Lai, Yi-An Chen, Fei-Yueh Fu, Hsueh-Wei Lee, Wei-Jaw Cheng, Hao-Chung Yang, Yi-Hsuan Sound Audio and Speech Processing While end-to-end lyrics-to-song models offer convenience for casual users, professional songwriters require score-to-song systems that allow them to retain authorship over the core melody. However, existing score-to-song methods are limited to short-form snippets and fail to maintain coherence in long-form generation, particularly during vocal-silent sections like intros and bridges. To address this long-form bottleneck, we propose MIDI-informed singing accompaniment generation (MIDI-SAG). Unlike conventional audio-only models, MIDI-SAG utilizes symbolic timing and chord information derived from the vocal MIDI to provide a stable musical roadmap. By incorporating structure planning, which defines temporal boundaries and semantic labels, our framework facilitates consistent generation across both vocal and non-vocal sections. We demonstrate the feasibility of this compositional pipeline by leveraging specialized pre-trained modules, enabling data-efficient training on a single GPU. Our experiments show the potential of this approach for both professional score-to-song and general lyrics-to-song tasks. While an early exploration, MIDI-SAG suggests a promising direction for structured, long-form music synthesis. Audio demos are available, and the code will be open-sourced at https://composerflow.github.io/web_revealed/. |
| title | MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.22029 |