add model and paper info

README.md

@@ -3,5 +3,31 @@ tags:
 - music-generation
 - transformer
 - pytorch
+- audio
+- music
+license: mit
 ---
-# Compose & Embellish
+# Compose & Embellish
+Trained model weights and training datasets for the paper:
+  * Shih-Lun Wu and Yi-Hsuan Yang  
+    "[Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach](https://arxiv.org/abs/2209.08212)."  
+    _Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP)_, 2023
+
+## 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.
+
+## BibTex
+If you find the materials useful, please consider citing our work:
+```
+@inproceedings{wu2023compembellish,
+  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)},
+  year={2023},
+  url={https://arxiv.org/pdf/2209.08212.pdf}
+}
+```