Corpus ID: 221218888

MMM : Exploring Conditional Multi-Track Music Generation with the Transformer

@article{Ens2020MMME,
  title={MMM : Exploring Conditional Multi-Track Music Generation with the Transformer},
  author={Jeffrey Ens and P. Pasquier},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.06048}
}
  • Jeffrey Ens, P. Pasquier
  • Published 2020
  • Computer Science
  • ArXiv
  • 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… CONTINUE READING
    2 Citations

    Figures from this paper

    A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 21 REFERENCES
    LakhNES: Improving Multi-instrumental Music Generation with Cross-domain Pre-training
    • 19
    • Highly Influential
    • PDF
    Music Transformer: Generating Music with Long-Term Structure
    • 104
    • Highly Influential
    MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
    • 147
    • PDF
    Learning to Traverse Latent Spaces for Musical Score Inpainting
    • 12
    • PDF
    Counterpoint by Convolution
    • 67
    • PDF
    A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
    • 161
    • PDF
    This time with feeling: learning expressive musical performance
    • 56
    • PDF