Towards An Integrated Approach for Expressive Piano Performance Synthesis from Music Scores

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Jingjing, Cooper, Erica, Wang, Xin, Yamagishi, Junichi, Fazekas, George
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912192622755840
author Tang, Jingjing
Cooper, Erica
Wang, Xin
Yamagishi, Junichi
Fazekas, George
author_facet Tang, Jingjing
Cooper, Erica
Wang, Xin
Yamagishi, Junichi
Fazekas, George
contents This paper presents an integrated system that transforms symbolic music scores into expressive piano performance audio. By combining a Transformer-based Expressive Performance Rendering (EPR) model with a fine-tuned neural MIDI synthesiser, our approach directly generates expressive audio performances from score inputs. To the best of our knowledge, this is the first system to offer a streamlined method for converting score MIDI files lacking expression control into rich, expressive piano performances. We conducted experiments using subsets of the ATEPP dataset, evaluating the system with both objective metrics and subjective listening tests. Our system not only accurately reconstructs human-like expressiveness, but also captures the acoustic ambience of environments such as concert halls and recording studios. Additionally, the proposed system demonstrates its ability to achieve musical expressiveness while ensuring good audio quality in its outputs.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10222
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards An Integrated Approach for Expressive Piano Performance Synthesis from Music Scores
Tang, Jingjing
Cooper, Erica
Wang, Xin
Yamagishi, Junichi
Fazekas, George
Sound
Audio and Speech Processing
This paper presents an integrated system that transforms symbolic music scores into expressive piano performance audio. By combining a Transformer-based Expressive Performance Rendering (EPR) model with a fine-tuned neural MIDI synthesiser, our approach directly generates expressive audio performances from score inputs. To the best of our knowledge, this is the first system to offer a streamlined method for converting score MIDI files lacking expression control into rich, expressive piano performances. We conducted experiments using subsets of the ATEPP dataset, evaluating the system with both objective metrics and subjective listening tests. Our system not only accurately reconstructs human-like expressiveness, but also captures the acoustic ambience of environments such as concert halls and recording studios. Additionally, the proposed system demonstrates its ability to achieve musical expressiveness while ensuring good audio quality in its outputs.
title Towards An Integrated Approach for Expressive Piano Performance Synthesis from Music Scores
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2501.10222