Pre-trained models for paper MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling

README

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

MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modeling
by Jinging Tang, Xin Wang, Zhe Zhang, Junichi Yamagishi, Geraint Wiggins, and Geroge Fazekas.

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

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

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 was supported by the UKRI Centre for Doctoral Training in Artificial Intelligence and Music [grant number EP/S022694/1] and the National Institute of Informatics (NII), Japan. J. Tang is a research student jointly funded by the China Scholarship Council [grant number 202008440382] and Queen Mary University of London. G. Wiggins received funding from the Flemish Government under the "Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen". We thank the reviewers for their valuable feedback, which helped improve the quality of this work.