STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915233762639872 |
|---|---|
| author | Strano, Giorgio Ballanti, Chiara Crisostomi, Donato Mancusi, Michele Cosmo, Luca Rodolà, Emanuele |
| author_facet | Strano, Giorgio Ballanti, Chiara Crisostomi, Donato Mancusi, Michele Cosmo, Luca Rodolà, Emanuele |
| contents | Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering production-level output. Yet, most existing models focus solely on generating music from scratch, limiting their usefulness for musicians who want to integrate such models into a human, iterative composition workflow. In this paper we introduce STAGE, our STemmed Accompaniment GEneration model, fine-tuned from the state-of-the-art MusicGen to generate single-stem instrumental accompaniments conditioned on a given mixture. Inspired by instruction-tuning methods for language models, we extend the transformer's embedding matrix with a context token, enabling the model to attend to a musical context through prefix-based conditioning. Compared to the baselines, STAGE yields accompaniments that exhibit stronger coherence with the input mixture, higher audio quality, and closer alignment with textual prompts. Moreover, by conditioning on a metronome-like track, our framework naturally supports tempo-constrained generation, achieving state-of-the-art alignment with the target rhythmic structure--all without requiring any additional tempo-specific module. As a result, STAGE offers a practical, versatile tool for interactive music creation that can be readily adopted by musicians in real-world workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05690 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning Strano, Giorgio Ballanti, Chiara Crisostomi, Donato Mancusi, Michele Cosmo, Luca Rodolà, Emanuele Sound Audio and Speech Processing Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering production-level output. Yet, most existing models focus solely on generating music from scratch, limiting their usefulness for musicians who want to integrate such models into a human, iterative composition workflow. In this paper we introduce STAGE, our STemmed Accompaniment GEneration model, fine-tuned from the state-of-the-art MusicGen to generate single-stem instrumental accompaniments conditioned on a given mixture. Inspired by instruction-tuning methods for language models, we extend the transformer's embedding matrix with a context token, enabling the model to attend to a musical context through prefix-based conditioning. Compared to the baselines, STAGE yields accompaniments that exhibit stronger coherence with the input mixture, higher audio quality, and closer alignment with textual prompts. Moreover, by conditioning on a metronome-like track, our framework naturally supports tempo-constrained generation, achieving state-of-the-art alignment with the target rhythmic structure--all without requiring any additional tempo-specific module. As a result, STAGE offers a practical, versatile tool for interactive music creation that can be readily adopted by musicians in real-world workflows. |
| title | STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.05690 |