cs.SDNov 10, 2026

Assessing Alignment in Automatic Piano Transcription Datasets: A Benchmark for Scoring Methods

Authors: Lucas de Souza Brandão, Lucas Gris, Joaquim Cavalcante, Chukwuemeka Nkama, Andrea Poltronieri

Organizations: Universidade de São Paulo, Brazil · Universidade Federal de Goiás, Brazil · Universidade Federal da Paraíba, Brazil · Universitat Pompeu Fabra, Spain

Abstract

Automatic Music Transcription (AMT) relies on paired audio--MIDI datasets, implicitly assuming near-perfect temporal alignment. However, widely used piano datasets have been shown to contain alignment errors that may bias model evaluation and training. We propose a framework for evaluating audio--MIDI alignment scoring methods through controlled temporal, pitch, and structural MIDI corruptions. We also introduce STI, a scoring method built on AMT models, and benchmark it against existing alignment scoring approaches. Our results show that STI, together with methods based on CENS and spectrograms, achieves the strongest overall performance, with STI exhibiting the highest sensitivity to fine-grained temporal misalignments, the main alignment error in AMT datasets. We then apply the best-performing methods to widely used piano AMT datasets and identify trends in their relative alignment quality. These results support more informed dataset curation, model training, and AMT evaluation.

Figures & tables

Explore similar work

CardsList
  1. Score-Agnostic Structure Analysis in Large-Scale Performance Datasets

    May 25, 2026Patricia Hu, Silvan Peter, Gerhard WidmerHierarchical ClusteringMusic Information Retrieval

  2. Snapping Matters: Context-Aware Onset Refinement for Automatic Music Transcription

    Jun 10, 2026Abhirup Saha, Hans-Ulrich Berendes, Meinard Müller +1Automatic Music TranscriptionMusic Information Retrieval

  3. Precise and Simple Audio-to-Score Alignment

    May 19, 2026Silvan Peter, Patricia Hu, Gerhard WidmerCross-Modal AlignmentMusic Information Retrieval