MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917886167089152 |
|---|---|
| author | Rouard, Simon Roman, Robin San Adi, Yossi Roebel, Axel |
| author_facet | Rouard, Simon Roman, Robin San Adi, Yossi Roebel, Axel |
| contents | While most music generation models generate a mixture of stems (in mono or stereo), we propose to train a multi-stem generative model with 3 stems (bass, drums and other) that learn the musical dependencies between them. To do so, we train one specialized compression algorithm per stem to tokenize the music into parallel streams of tokens. Then, we leverage recent improvements in the task of music source separation to train a multi-stream text-to-music language model on a large dataset. Finally, thanks to a particular conditioning method, our model is able to edit bass, drums or other stems on existing or generated songs as well as doing iterative composition (e.g. generating bass on top of existing drums). This gives more flexibility in music generation algorithms and it is to the best of our knowledge the first open-source multi-stem autoregressive music generation model that can perform good quality generation and coherent source editing. Code and model weights will be released and samples are available on https://simonrouard.github.io/musicgenstem/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01757 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling Rouard, Simon Roman, Robin San Adi, Yossi Roebel, Axel Sound Audio and Speech Processing While most music generation models generate a mixture of stems (in mono or stereo), we propose to train a multi-stem generative model with 3 stems (bass, drums and other) that learn the musical dependencies between them. To do so, we train one specialized compression algorithm per stem to tokenize the music into parallel streams of tokens. Then, we leverage recent improvements in the task of music source separation to train a multi-stream text-to-music language model on a large dataset. Finally, thanks to a particular conditioning method, our model is able to edit bass, drums or other stems on existing or generated songs as well as doing iterative composition (e.g. generating bass on top of existing drums). This gives more flexibility in music generation algorithms and it is to the best of our knowledge the first open-source multi-stem autoregressive music generation model that can perform good quality generation and coherent source editing. Code and model weights will be released and samples are available on https://simonrouard.github.io/musicgenstem/. |
| title | MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.01757 |