This is the demo page for the paper AUTOMATIC COMPOSITION OF GUITAR TABS BY TRANSFORMERS AND GROOVE MODELING
Recent years have witnessed great progress in using deep learning algorithms to learn to compose music in the form of a MIDI file. However, whether such algorithms apply equally well to compose 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.
Audio in the same row share identical first 4 bars prompt. No grooving and Hard grooving model are asked to generate 16-bar continuations based on the prompt input.
| |Real data|No grooving|Hard grooving| |1.|||| |2.|||| |3.|||| |4.|||| |5.||||
This video recording is a guitarist from our team playing a generated tab which is generated from scratch.
<iframe width="800" height="500" src="https://www.youtube.com/embed/yccH6kvinq0"> </iframe>Yu-Hua Chen [email protected]