Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
By Yu-Siang Huang, Yi-Hsuan Yang. ACM Multimedia, 2020
399 citations recorded by the source corpus.
A great number of deep learning based models have been recently proposed for automatic music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a coherent structure of up to one minute. The model is powerful in that it learns abstractions of data on its own, without much human-imposed domain knowledge or constraints. In contrast with this general approach, this paper shows that Transformers can do even better for music modeling, when we improve the way a musical score is converted into the data fed to a Transformer model. In particular, we seek to impose a metrical structure in the input data, so that Transformers can be more easily aware of the beat-bar-phrase hierarchical structure in music. The new data representation maintains the flexibility of local tempo changes, and provides hurdles to control the rhythmic and harmonic structure of music. With this approach, we build a Pop Music Transformer that composes Pop piano music with better rhythmic structure than existing Transformer models.
Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Signal Processing
View Paper: https://www.semanticscholar.org/paper/ce510c6cfeac703706460680e977c54554840830
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
In Computer Vision and Pattern Recognition
In Signal Processing
Citations in the corpus
- Datasheet for the Pile (2022, methodology): “Project Gutenberg (PG-19): Project Gutenberg 1919 has been used extensively, including by [Zaheer et al., 2020, Choromanski et al., 2020, Roller et al., 2020, Huang and Yang, 2020, Irie et al., 2020].”