Exploiting long-term temporal dependencies in NMF using recurrent neural networks with application to source separation

Nicolas Boulanger-Lewandowski, Gautham J. Mysore, Matthew D. HoffmanICASSP 2014 · OpenReview

Abstract

This paper seeks to exploit high-level temporal information during feature extraction from audio signals via non-negative matrix factorization. Contrary to existing approaches that impose local temporal constraints, we train powerful recurrent neural network models to capture long-term temporal dependencies and event co-occurrence in the data. This gives our method the ability to “fill in the blanks” in a smart way during feature extraction from complex audio mixtures, an ability very useful for a number of audio applications. We apply these ideas to source separation problems.
BibTeX
@inproceedings{boulangerlewandowski2014exploiting,
  author = {Nicolas Boulanger-Lewandowski and Gautham J. Mysore and Matthew D. Hoffman},
  title = {{Exploiting long-term temporal dependencies in NMF using recurrent neural networks with application to source separation}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  url = {https://openreview.net/forum?id=oEB7pMs6JJ},
}

Loading related content...

Figure