Edit model card

Compose & Embellish: Piano Performance Generation Pipeline

Trained model weights and training datasets for the paper:

Note: Materials here should be used in conjunction with our model implementation Github repo.

Model characteristics

Stage 1: "Compose" model

Generates melody and chord progression from scratch.

Stage 2: "Embellish" model

Generates accompaniment, timing and dynamics conditioned on Stage 1 outputs.


If you find the materials useful, please consider citing our work:

  title={{Compose \& Embellish}: Well-Structured Piano Performance Generation via A Two-Stage Approach},
  author={Wu, Shih-Lun and Yang, Yi-Hsuan},
  booktitle={Proc. Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP)},
Downloads last month
Unable to determine this model's library. Check the docs .