Automatic Composition of Guitar Tabs by Transformers and Groove Modeling
This work addresses the challenge of automated guitar tab composition for musicians and researchers, but it is incremental as it applies existing methods to a new domain.
The authors tackled the problem of composing fingerstyle guitar tabs using deep learning, specifically Transformer-XL, and found that the model generated note sequences with meaningful note-string combinations and coherent rhythmic groove, though it was only preliminarily evaluated against human-made compositions.
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.