Simple and Controllable Music Generation
We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns, which eliminates the need for cascading several models, e.g., hierarchically or upsampling. Following this approach, we demonstrate how MusicGen can generate high-quality samples, both mono and stereo, while being conditioned on textual description or melodic features, allowing better controls over the generated output. We conduct extensive empirical evaluation, considering both automatic and human studies, showing the proposed approach is superior to the evaluated baselines on a standard text-to-music benchmark. Through ablation studies, we shed light over the importance of each of the components comprising MusicGen. Music samples, code, and models are available at https://github.com/facebookresearch/audiocraft
PDF Abstract NeurIPS 2023 PDF NeurIPS 2023 AbstractCode
Colab
Datasets
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Text-to-Music Generation | MusicCaps | MusicGen w/o melody (1.5B) | FAD VGG | 3.4 | # 4 | |
| Text-to-Music Generation | MusicCaps | MusicGen w/ random melody (1.5B) | FAD VGG | 5.0 | # 9 | |
| Text-to-Music Generation | MusicCaps | MusicGen w/o melody (3.3B) | FAD VGG | 3.8 | # 6 |
