Learning Rhythm And Melody Features With Deep Belief Networks

@inproceedings{Schmidt2013LearningRA,
  title={Learning Rhythm And Melody Features With Deep Belief Networks},
  author={Erik M. Schmidt and Youngmoo Kim},
  booktitle={ISMIR},
  year={2013}
}
Deep learning techniques provide powerful methods for the development of deep structured projections connecting multiple domains of data. But the fine-tuning of such networks for supervised problems is challenging, and many current approaches are therefore heavily reliant on pretraining, which consists of unsupervised processing on the input observation data. In previous work, we have investigated using magnitude spectra as the network observations, finding reasonable improvements over standard… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Harmonic/percussive separation using median filtering

D. FitzGerald
DAFx, Graz, Austria, September 2010. • 2010
View 10 Excerpts
Highly Influenced

Learning emotion-based acoustic features with deep belief networks

2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) • 2011
View 1 Excerpt

Similar Papers

Loading similar papers…