Summary
Transcribing guitar music from sound recordings is hard because many systems miss important playing effects like bends and slides, mix up which strings or frets are used, and don’t work well with noisy recordings. The authors created a system called TART that breaks the problem into steps: recognizing notes, identifying playing techniques, figuring out the exact finger positions, and then making the guitar tabs. Their approach showed better accuracy than previous methods when tested on several guitar music datasets, even with noisy audio. This is the first tool to directly produce guitar tabs that include both finger placement and expressive techniques from audio recordings.
automatic music transcriptionguitar tablatureaudio-to-MIDIexpressive techniquesstring-fret assignmentmachine learningzero-shot evaluationaudio processingmodular pipelineT5 encoder-decoder
Authors
Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda, Samhita Konduri, Jiachen Lian, Robin Netzorg, Gopala Anumanchipalli
Abstract
Automatic Music Transcription (AMT) for guitar remains limited by three challenges: existing systems often fail to capture expressive techniques such as slides, bends, and percussive hits; they often assign notes to incorrect string-fret combinations; and they are typically trained on clean recordings, limiting their generalization to noisy real-world audio. To address these challenges, we propose TART, a modular four-stage audio-to-tablature pipeline consisting of (1) an audio-to-MIDI transcription model, (2) an expressive technique classifier, (3) an audio-conditioned T5 encoder-decoder for string-fret assignment, and (4) an automated tablature generator. We evaluate TART in a zero-shot setting on GuitarSet, EGDB, and two augmented benchmarks, Noisy GuitarSet and Noisy EGDB. Averaged across these four benchmarks, TART achieves 81.35% audio-to-MIDI F50 (+6.67 points over the best prior baseline), 71.8% string-fret Tab F1 (+8.5 points over the best prior baseline), and 54.08% end-to-end Tab F1. To our knowledge, TART is the first framework to generate guitar tablature with both fingering and expressive technique annotations directly from guitar audio.