A Method for MIDI Velocity Estimation for Piano Performance by a U-Net With Attention and FiLM

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hyon Kim, Xavier Serra
Format: Recurso digital
Publié: Zenodo 2024
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901206667886592
author Hyon Kim
Xavier Serra
author_facet Hyon Kim
Xavier Serra
contents It is a well known fact that the dynamics in piano performance gives significant effect in expressiveness. Taking the polyphonic nature of the instrument into account, analysing information to form dynamics for each performed note has significant meaning to understand piano performance in a quantitative way. It is also a key element in an education context for piano learners. In this study, we developed a model for estimating MIDI velocity for each note, as one of indicators to represent loudness, with a condition of score assuming educational use case, by a Deep Neural Network (DNN) utilizing a U-Net with Scaled Dot-Product Attention (Attention) and Feature-wise Linear Modulation (FiLM) conditioning. As a result, we prove that effectiveness of Attention and FiLM conditioning, improved estimation accuracy and achieved the best result among previous researches using DNNs and showed its robustness across the various domain of test data.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_14877043
institution Zenodo
language
publishDate 2024
publisher Zenodo
record_format zenodo
spellingShingle A Method for MIDI Velocity Estimation for Piano Performance by a U-Net With Attention and FiLM
Hyon Kim
Xavier Serra
It is a well known fact that the dynamics in piano performance gives significant effect in expressiveness. Taking the polyphonic nature of the instrument into account, analysing information to form dynamics for each performed note has significant meaning to understand piano performance in a quantitative way. It is also a key element in an education context for piano learners. In this study, we developed a model for estimating MIDI velocity for each note, as one of indicators to represent loudness, with a condition of score assuming educational use case, by a Deep Neural Network (DNN) utilizing a U-Net with Scaled Dot-Product Attention (Attention) and Feature-wise Linear Modulation (FiLM) conditioning. As a result, we prove that effectiveness of Attention and FiLM conditioning, improved estimation accuracy and achieved the best result among previous researches using DNNs and showed its robustness across the various domain of test data.
title A Method for MIDI Velocity Estimation for Piano Performance by a U-Net With Attention and FiLM
url https://doi.org/10.5281/zenodo.14877043