Corpus ID: 54477714

Music Transformer.

@article{Huang2018MusicT,
  title={Music Transformer.},
  author={Cheng-Zhi Anna Huang and Ashish Vaswani and Jakob Uszkoreit and Noam Shazeer and I. Simon and C. Hawthorne and Andrew M. Dai and M. Hoffman and M. Dinculescu and D. Eck},
  journal={arXiv: Learning},
  year={2018}
}
  • Cheng-Zhi Anna Huang, Ashish Vaswani, +7 authors D. Eck
  • Published 2018
  • Computer Science, Engineering, Mathematics
  • arXiv: Learning
  • Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani et al., 2017), a sequence model based on self-attention, has achieved compelling results in many generation tasks that require maintaining long-range coherence. This suggests that self-attention might also be well-suited to modeling music. In musical… CONTINUE READING
    Generating Long Sequences with Sparse Transformers
    • 174
    • Open Access
    Deep Learning Techniques for Music Generation - A Survey
    • 131
    • Open Access
    MelNet: A Generative Model for Audio in the Frequency Domain
    • 37
    • Open Access
    Synthesizer: Rethinking Self-Attention in Transformer Models
    • 12
    • Open Access
    Toward Interpretable Music Tagging with Self-Attention
    • 10
    • Highly Influenced
    • Open Access
    Learning to Traverse Latent Spaces for Musical Score Inpainting
    • 10
    • Open Access
    Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel
    • 16
    • Highly Influenced
    • Open Access
    Stand-Alone Self-Attention in Vision Models
    • 59
    • Open Access
    Magenta Studio: Augmenting Creativity with Deep Learning in Ableton Live
    • 7
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES
    Attention is All you Need
    • 11,441
    • Open Access
    Finding temporal structure in music: blues improvisation with LSTM recurrent networks
    • 195
    • Open Access
    DeepBach: a Steerable Model for Bach Chorales Generation
    • 204
    • Open Access
    MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
    • 115
    • Open Access
    Self-Attention with Relative Position Representations
    • 318
    • Open Access
    A Fast Learning Algorithm for Deep Belief Nets
    • 10,871
    • Open Access
    Counterpoint by Convolution
    • 60
    • Open Access
    This time with feeling: learning expressive musical performance
    • 43
    • Open Access