Playability-Aware Audio-to-Tablature Guitar Transcription via Diffusion Models

2026-08-31

AI Summary

为解决吉他谱转录中音高准确性和可演奏性问题，提出Noise2Fret模型，通过扩散模型结合五种辅助损失函数来生成更符合物理约束的吉他谱。

Abstract

Guitar tablature transcription requires not only accurate pitch detection but also assigning each note to a specific string-fret position, as the same pitch can be played at multiple fretboard positions. Existing approaches treat this as a standard classification problem, ignoring the musical and physical constraints that govern playable fingering sequences. We propose Noise2Fret, a diffusion model for audio-to-tablature transcription that generates tablature through a continuous latent representation of discrete fret and string targets, conditioned on spectral and audio features. To bridge the gap between pitch accuracy and physical playability, we introduce five auxiliary losses encoding Pitch-Class Distance, Positional Distance, Circle-of-Fifths Distance, String Similarity, and Hand-Span Feasibility directly into the training objective. Experiments on GuitarSet and GOAT datasets demonstrate that the model outperforms baselines while remaining computationally more efficient, and that the auxiliary losses yield consistent gains over the standard training objective.

Problem

• Guitar Tablature Transcription
• Playability
• Physical Constraints
• Fingering Sequences

Innovation

• Diffusion Model
• Audio-to-Tablature Transcription
• Auxiliary Losses
• Playability
• Continuous Latent Representation