A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Weixing, Lalang, Raynaldi, Li, Dichucheng, Yoshii, Kazuyoshi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914575305146368
author Wei, Weixing
Lalang, Raynaldi
Li, Dichucheng
Yoshii, Kazuyoshi
author_facet Wei, Weixing
Lalang, Raynaldi
Li, Dichucheng
Yoshii, Kazuyoshi
contents This paper describes a novel paradigm that formalizes automatic piano transcription (APT) as an optimal transport (OT) problem, not as a frame-level multi-label binary classification problem. Our method learns to minimize the cost of transporting a predicted distribution of note events to the ground-truth distribution over time and frequency. The OT loss can thus accommodate temporal misalignment, leading to perceptually relevant optimization. We also propose a convolutional recurrent neural network (CRNN) with a harmonics-aware attention mechanism to capture the spectro-temporal dependencies inherent in music.Our experiments using the MAESTRO dataset showed that our method attained a state-of-the-art performance in onset detection. We confirmed the versatility of the OT loss in application to existing models.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport
Wei, Weixing
Lalang, Raynaldi
Li, Dichucheng
Yoshii, Kazuyoshi
Sound
Multimedia
This paper describes a novel paradigm that formalizes automatic piano transcription (APT) as an optimal transport (OT) problem, not as a frame-level multi-label binary classification problem. Our method learns to minimize the cost of transporting a predicted distribution of note events to the ground-truth distribution over time and frequency. The OT loss can thus accommodate temporal misalignment, leading to perceptually relevant optimization. We also propose a convolutional recurrent neural network (CRNN) with a harmonics-aware attention mechanism to capture the spectro-temporal dependencies inherent in music.Our experiments using the MAESTRO dataset showed that our method attained a state-of-the-art performance in onset detection. We confirmed the versatility of the OT loss in application to existing models.
title A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport
topic Sound
Multimedia
url https://arxiv.org/abs/2605.17405