Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance

Dasaem Jeong, Taegyun Kwon, Yoojin Kim, Juhan Nam
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:3060-3070, 2019.

Abstract

Music score is often handled as one-dimensional sequential data. Unlike words in a text document, notes in music score can be played simultaneously by the polyphonic nature and each of them has its own duration. In this paper, we represent the unique form of musical score using graph neural network and apply it for rendering expressive piano performance from the music score. Specifically, we design the model using note-level gated graph neural network and measure-level hierarchical attention network with bidirectional long short-term memory with an iterative feedback method. In addition, to model different styles of performance for a given input score, we employ a variational auto-encoder. The result of the listening test shows that our proposed model generated more human-like performances compared to a baseline model and a hierarchical attention network model that handles music score as a word-like sequence.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-jeong19a, title = {Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance}, author = {Jeong, Dasaem and Kwon, Taegyun and Kim, Yoojin and Nam, Juhan}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {3060--3070}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/jeong19a/jeong19a.pdf}, url = {https://proceedings.mlr.press/v97/jeong19a.html}, abstract = {Music score is often handled as one-dimensional sequential data. Unlike words in a text document, notes in music score can be played simultaneously by the polyphonic nature and each of them has its own duration. In this paper, we represent the unique form of musical score using graph neural network and apply it for rendering expressive piano performance from the music score. Specifically, we design the model using note-level gated graph neural network and measure-level hierarchical attention network with bidirectional long short-term memory with an iterative feedback method. In addition, to model different styles of performance for a given input score, we employ a variational auto-encoder. The result of the listening test shows that our proposed model generated more human-like performances compared to a baseline model and a hierarchical attention network model that handles music score as a word-like sequence.} }
Endnote
%0 Conference Paper %T Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance %A Dasaem Jeong %A Taegyun Kwon %A Yoojin Kim %A Juhan Nam %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-jeong19a %I PMLR %P 3060--3070 %U https://proceedings.mlr.press/v97/jeong19a.html %V 97 %X Music score is often handled as one-dimensional sequential data. Unlike words in a text document, notes in music score can be played simultaneously by the polyphonic nature and each of them has its own duration. In this paper, we represent the unique form of musical score using graph neural network and apply it for rendering expressive piano performance from the music score. Specifically, we design the model using note-level gated graph neural network and measure-level hierarchical attention network with bidirectional long short-term memory with an iterative feedback method. In addition, to model different styles of performance for a given input score, we employ a variational auto-encoder. The result of the listening test shows that our proposed model generated more human-like performances compared to a baseline model and a hierarchical attention network model that handles music score as a word-like sequence.
APA
Jeong, D., Kwon, T., Kim, Y. & Nam, J.. (2019). Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:3060-3070 Available from https://proceedings.mlr.press/v97/jeong19a.html.

Related Material