Explicit Note-Event Tokenization and Pitch-Validity Constrained Decoding for MIDI-to-Tablature Transcription

2026-07-28

AI Summary

This work addresses the challenges of poor cross-dataset generalization and invalid pitch predictions in guitar tablature transcription by proposing a sequence-to-sequence MIDI-to-tablature framework. The approach integrates explicit note events with TAB token representations, incorporates regularization during training, and—uniquely—imposes pitch-validity constraints directly during decoding via a masking mechanism that filters out infeasible fretting candidates while preserving the original rhythmic and note structure. Experimental results demonstrate that the proposed method significantly improves transcription accuracy on both the DadaGP and François Leduc datasets, achieving notably superior performance over the Fretting Transformer baseline, especially in low-data regimes.

Abstract

Guitar tablature transcription predicts the string and fret position for each note so that the resulting tablature reproduces the target musical part. Prior sequence-to-sequence approaches have shown promising results on large-scale datasets, but their generalization behavior across different dataset scales remains less explored. In this work, we propose a guitar tablature transcription framework with explicit note-event tokenization and regularized training. The proposed decoder token representation incorporates note-event tokens together with TAB tokens, allowing note boundaries, pitch-related events, and string-fret positions to be represented more explicitly. We evaluate the proposed framework on DadaGP, a large-scale dataset, and Francois Leduc, a small-scale dataset. Our method improves tablature accuracy over the Fretting Transformer baseline on DadaGP, with especially strong gains when trained directly on the small-scale Leduc dataset. We further introduce a pitch-validity constrained decoding strategy that masks pitch-invalid TAB candidates during generation rather than correcting them after decoding and simultaneously preserves the original timing and note structure from the input. This constraint improves tablature accuracy and provides a controlled setting for measuring how much error remains after pitch-invalid predictions are removed. Our code will be released at:https://github.com/MusicGuitarTab/GuitarTab

Problem

• guitar tablature transcription
• pitch validity
• MIDI-to-tablature
• generalization
• note-event representation

Innovation

• note-event tokenization
• pitch-validity constrained decoding
• MIDI-to-tablature transcription
• guitar tablature
• sequence-to-sequence modeling