# Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcription

arXiv: https://arxiv.org/abs/2508.07987 · HTML: https://mlsanity.com/paper/2508.07987/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [MMM : Exploring Conditional Multi-Track Music Generation with the Transformer](https://mlsanity.com/paper/2008.06048/) (2020)
- [DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models](https://mlsanity.com/paper/2107.14653/) (2021)
- [High Resolution Guitar Transcription via Domain Adaptation](https://mlsanity.com/paper/2402.15258/) (2024)
- [DawDreamer: Bridging the Gap Between Digital Audio Workstations and Python Interfaces](https://mlsanity.com/paper/2111.09931/) (2021)
- [SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription](https://mlsanity.com/paper/2309.09085/) (2023)
- [DDSP-based Neural Waveform Synthesis of Polyphonic Guitar Performance from String-wise MIDI Input](https://mlsanity.com/paper/2309.07658/) (2023)

## Abstract (arXiv)

Automatic transcription of acoustic guitar fingerpicking performances remains a challenging task due to the scarcity of labeled training data and legal constraints connected with musical recordings. This work investigates a procedural data generation pipeline as an alternative to real audio recordings for training transcription models. Our approach synthesizes training data through four stages: knowledge-based fingerpicking tablature composition, MIDI performance rendering, physical modeling using an extended Karplus-Strong algorithm, and audio augmentation including reverb and distortion. We train and evaluate a CRNN-based note-tracking model on both real and synthetic datasets, demonstrating that procedural data can be used to achieve reasonable note-tracking results. Finetuning with a small amount of real data further enhances transcription accuracy, improving over models trained exclusively on real recordings. These results highlight the potential of procedurally generated audio for data-scarce music information retrieval tasks.