Pre-trained models for paper Towards an Integrated Approach for Expressive Piano Performance Synthesis from Music Scores

README

This repository contains the pre-trained models for our ICASSP 2025 paper

Towards an Integrated Approach for Expressive Piano Performance Synthesis from Music Scores
Jingjing Tang, Erica Cooper, Xin Wang, Junichi Yamagishi, and György Fazekas., ICASSP 2025.

Code and instructions for using these pretrained models can be found in the official git repository: https://github.com/nii-yamagishilab/Score-to-Audio

Please follow the READ in the git repository to use the pre-trained models.

Please cite the paper if you use the codes or pre-trained models in your work.

@INPROCEEDINGS{10890623,
  author={Tang, Jingjing and Cooper, Erica and Wang, Xin and Yamagishi, Junichi and Fazekas, György},
  booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Towards An Integrated Approach for Expressive Piano Performance Synthesis from Music Scores}, 
  year={2025},
  pages={1-5},
  doi={10.1109/ICASSP49660.2025.10890623}

COPYING

This pretrained model is licensed under the Creative Commons License: Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/legalcode
Please see `LICENSE.txt` for the terms and conditions of this pretrained model.

ACKNOWLEDGMENTS

This work is supported by both the UKRI Centre for Doctoral Training in Artificial Intelligence and Music (grant number EP/S022694/1), and the National Institute of Informatics in Japan. J.Tang is a research student supported jointly by the China Scholarship Council [grant number 202008440382] and Queen Mary University of London. E. Cooper conducted this work while at NII, Japan and is currently employed by NICT, Japan.