Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
Abstract
We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our approach outperforms many traditional models of polyphonic music on a variety of realistic datasets. We show how our musical language model can serve as a symbolic prior to improve the accuracy of polyphonic transcription.
Cite
Text
Boulanger-Lewandowski et al. "Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription." International Conference on Machine Learning, 2012.Markdown
[Boulanger-Lewandowski et al. "Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription." International Conference on Machine Learning, 2012.](https://mlanthology.org/icml/2012/boulangerlewandowski2012icml-modeling/)BibTeX
@inproceedings{boulangerlewandowski2012icml-modeling,
title = {{Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription}},
author = {Boulanger-Lewandowski, Nicolas and Bengio, Yoshua and Vincent, Pascal},
booktitle = {International Conference on Machine Learning},
year = {2012},
url = {https://mlanthology.org/icml/2012/boulangerlewandowski2012icml-modeling/}
}