MMM : Exploring Conditional Multi-Track Music Generation with the Transformer
arXiv:2008.06048
Abstract
We propose the Multi-Track Music Machine (MMM), a generative system based on the Transformer architecture that is capable of generating multi-track music. In contrast to previous work, which represents musical material as a single time-ordered sequence, where the musical events corresponding to different tracks are interleaved, we create a time-ordered sequence of musical events for each track and concatenate several tracks into a single sequence. This takes advantage of the Transformer's attention-mechanism, which can adeptly handle long-term dependencies. We explore how various representations can offer the user a high degree of control at generation time, providing an interactive demo that accommodates track-level and bar-level inpainting, and offers control over track instrumentation and note density.
References in corpus (6)
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- Counterpoint by Convolution
- Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context
- LakhNES: Improving multi-instrumental music generation with cross-domain pre-training
- Learning to Traverse Latent Spaces for Musical Score Inpainting
Cited by in corpus (8)
- A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
- Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey
- Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
- The Beauty of Repetition in Machine Composition Scenarios
- Score Transformer: Generating Musical Score from Note-level Representation
- The GigaMIDI Dataset with Features for Expressive Music Performance Detection
- Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music
- 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