Simple and Controllable Music Generation
arXiv:2306.05284
Abstract
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
Published at Neurips 2023
Cited by in corpus (7)
- Foundation Models and Transformers for Anomaly Detection: A Survey
- How Voice and Helpfulness Shape Perceptions in Human-Agent Teams
- Benchmarking Music Generation Models and Metrics via Human Preference Studies
- GEMRec: Towards Generative Model Recommendation
- M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature
- Trailer Reimagined: An Innovative, Llm-DRiven, Expressive Automated Movie Summary framework (TRAILDREAMS)
- BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Features