# Automatic Composition of Guitar Tabs by Transformers and Groove Modeling

arXiv: https://arxiv.org/abs/2008.01431 · HTML: https://mlsanity.com/paper/2008.01431/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 14 of 14)

- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [Multitrack Music Transformer](https://mlsanity.com/paper/2207.06983/) (2022)
- [DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models](https://mlsanity.com/paper/2107.14653/) (2021)
- [Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding](https://mlsanity.com/paper/2108.05064/) (2021)
- [JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE](https://mlsanity.com/paper/2210.06007/) (2022)
- [GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music Generation with Transformers](https://mlsanity.com/paper/2302.05393/) (2023)
- [Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey](https://mlsanity.com/paper/2402.17467/) (2024)
- [ProgGP: From GuitarPro Tablature Neural Generation To Progressive Metal Production](https://mlsanity.com/paper/2307.05328/) (2023)
- [Modeling Bends in Popular Music Guitar Tablatures](https://mlsanity.com/paper/2308.12307/) (2023)
- [Time-Shifted Token Scheduling for Symbolic Music Generation](https://mlsanity.com/paper/2509.23749/) (2025)
- [Fretting-Transformer: Encoder-Decoder Model for MIDI to Tablature Transcription](https://mlsanity.com/paper/2506.14223/) (2025)
- [Guitar Chord Diagram Suggestion for Western Popular Music](https://mlsanity.com/paper/2407.14260/) (2024)
- [A Machine Learning Approach for MIDI to Guitar Tablature Conversion](https://mlsanity.com/paper/2510.10619/) (2025)

## Abstract (arXiv)

Deep learning algorithms are increasingly developed for learning to compose music in the form of MIDI files. However, whether such algorithms work well for composing guitar tabs, which are quite different from MIDIs, remain relatively unexplored. To address this, we build a model for composing fingerstyle guitar tabs with Transformer-XL, a neural sequence model architecture. With this model, we investigate the following research questions. First, whether the neural net generates note sequences with meaningful note-string combinations, which is important for the guitar but not other instruments such as the piano. Second, whether it generates compositions with coherent rhythmic groove, crucial for fingerstyle guitar music. And, finally, how pleasant the composed music is in comparison to real, human-made compositions. Our work provides preliminary empirical evidence of the promise of deep learning for tab composition, and suggests areas for future study.