Playability-Aware Audio-to-Tablature Guitar Transcription via Diffusion Models
2026-08-31 • Sound
SoundInformation Retrieval
AI summaryⓘ
The authors developed a new method called Noise2Fret to convert guitar audio into tablature, which shows not only the notes but also exactly where to play them on the guitar. Unlike previous methods, their approach considers both the sound and the physical way the guitar is played, making the transcription more realistic and practical for guitarists. They use a special training process that includes rules about musical distances and hand movements to improve accuracy and playability. Tests on popular datasets show their method works better and faster than earlier techniques.
Guitar tablaturePitch detectionDiffusion modelLatent representationCircle of FifthsAuxiliary lossSpectral featuresHand-span feasibilityAudio-to-tab transcriptionGuitarSet dataset
Authors
Riccardo Simionato, Louis Bigo
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.