Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription

By Nicolas Boulanger-Lewandowski, Yoshua Bengio, Pascal Vincent. 2012

739 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Music, Representation & Self-Supervised Learning, Model Architectures, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Xiaogang Wang
  5. Ming-Hsuan Yang
  6. Jitendra Malik
  7. Yi Yang
  8. Andrew Zisserman

In Music

  1. Dong Yu
  2. Li Deng
  3. Simon E. Dixon
  4. Sander Dieleman
  5. François Pachet
  6. Gaëtan Hadjeres
  7. Kyunghyun Cho
  8. Emmanouil Benetos

In Representation & Self-Supervised Learning

  1. Yoshua Bengio
  2. Ruslan Salakhutdinov
  3. Li Deng
  4. J. Urgen Schmidhuber
  5. Kyunghyun Cho
  6. Aaron C. Courville
  7. Quoc V. Le
  8. Geoffrey E. Hinton

In Model Architectures

  1. Yoshua Bengio
  2. Kyunghyun Cho
  3. Quoc V. Le
  4. Ruslan Salakhutdinov
  5. Aaron C. Courville
  6. Vladlen Koltun
  7. J. Urgen Schmidhuber
  8. Richard Socher

In Signal Processing

  1. Yoshua Bengio
  2. Yi-Hsuan Yang
  3. Ilya Sutskever
  4. Dong Yu
  5. Aaron C. Courville
  6. Jesse Engel
  7. Li Deng
  8. Kyunghyun Cho

Citations in the corpus