Metraipolis › archive › dc_6ca8318e42bf

TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription — arXiv:2609.11904

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11904
License (as archived)
CC0-1.0
Archived
2026-10-16T05:55:04.648Z
SHA-256 of the archived text
c814ad72b59eb77792ec7d2844ed11ad696a5e09f0a8791d3f153d9a167c08a9
Stable URL of this page
https://metraipolis.com/documento/dc_6ca8318e42bf

How to cite

TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription — arXiv:2609.11904 — arXiv (en), https://arxiv.org/abs/2609.11904 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ca8318e42bf (Metraipolis archive dc_6ca8318e42bf, sha256 c814ad72b59eb77792ec7d2844ed11ad696a5e09f0a8791d3f153d9a167c08a9)
BibTeX
@misc{dc6ca8318e42bf,
  title = {TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription — arXiv:2609.11904},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11904},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ca8318e42bf; sha256 c814ad72b59eb77792ec7d2844ed11ad696a5e09f0a8791d3f153d9a167c08a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11904. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.11904 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:44:25.019Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).