Improved music feature learning with deep neural networks

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2014, Pages 6959-6963

  Sigtia, Siddharth ^a   Dixon, Simon ^a  

^a QUEEN MARY UNIVERSITY OF LONDON   (United Kingdom)

Author keywords

Deep Learning; MIR; Neural Networks

Indexed keywords

CLASSIFICATION (OF INFORMATION); NETWORK ARCHITECTURE; NEURAL NETWORKS;

DEEP LEARNING; DEEP NEURAL NETWORKS; FEATURE LEARNING; GENRE CLASSIFICATION; MIR; MUSIC INFORMATION RETRIEVAL; NEURAL NETWORK TRAINING; STATE OF THE ART;

SIGNAL PROCESSING;

EID: 84905259152     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854949     Document Type: Conference Paper

References (24)

1. ISMIR 2004: Audio Description Contest. http://ismir2004. net/genre contest/, 2004.
2. Yoshua Bengio, Patrice Simard, and Paolo Frasconi. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2):157-166, 1994.
3. James Bergstra, Olivier Breuleux, Fré dé ric Bastien, Pascal Lamblin, Razvan Pascanu, Guillaume Desjardins, Joseph Turian, David Warde-Farley, and Yoshua Bengio. Theano: a CPU and GPU math expression compiler. In Proceedings of the Python for Scientific Computing Conference (SciPy), June 2010. Oral Presentation.
4. James Bergstra, Norman Casagrande, Dumitru Erhan, Douglas Eck, and Balazs Ké gl. Aggregate features and AdaBoost for music classification. Machine Learning, 65(2-3):473-484, 2006.
5. James Bergstra, Michael I Mandel, and Douglas Eck. Scalable genre and tag prediction with spectral covariance. In ISMIR, pages 507-512, 2010.
6. Christopher M Bishop. Neural networks for pattern recognition. Oxford university press, 1995.
7. George E Dahl, Tara N Sainath, and Geoffrey E Hinton. Improving deep neural networks for LVCSR using rectified linear units and dropout. In Proc. ICASSP, 2013.
8. Xavier Glorot and Yoshua Bengio. Understanding the difficulty of training deep feedforward neural networks. In International Conference on Artificial Intelligence and Statistics, pages 249-256, 2010.
9. Xavier Glorot, Antoine Bordes, and Yoshua Bengio. Deep sparse rectifier networks. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. JMLR W&CP Volume, volume 15, pages 315-323, 2011.
10. Philippe Hamel and Douglas Eck. Learning features from music audio with deep belief networks. In ISMIR, pages 339-344. Utrecht, The Netherlands, 2010.
11. Philippe Hamel, Simon Lemieux, Yoshua Bengio, and Douglas Eck. Temporal pooling and multiscale learning for automatic annotation and ranking of music audio. In ISMIR, pages 729-734, 2011.
12. Mikael Henaff, Kevin Jarrett, Koray Kavukcuoglu, and Yann LeCun. Unsupervised learning of sparse features for scalable audio classification. In ISMIR, pages 681-686, 2011.
13. Geoffrey E Hinton, Simon Osindero, and Yee-Whye Teh. A fast learning algorithm for deep belief nets. Neural computation, 18(7):1527-1554, 2006.
14. Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. Technical report, University of Toronto, 2012.
15. Eric J Humphrey, Juan P Bello, and Yann LeCun. Feature learning and deep architectures: new directions for music informatics. Journal of Intelligent Information Systems, 41:1-21, 2013.
16. Alex Krizhevsky, Ilya Sutskever, and Geoff Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, pages 1106-1114, 2012.
17. Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y Ng. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 609-616. ACM, 2009.
18. James Martens. Deep learning via Hessian-Free optimization. In Proc. ICML, pages 735-742, 2010.
19. James Martens and Ilya Sutskever. Learning recurrent neural networks with hessian-free optimization. In Proc. ICML, pages 1033-1040, 2011.
20. Vinod Nair and Geoffrey E Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pages 807-814, 2010.
21. Carlos N Silla Jr, Alessandro L Koerich, and Celso AA Kaestner. Improving automatic music genre classification with hybrid content-based feature vectors. In Proceedings of the 2010 ACM Symposium on Applied Computing, pages 1702-1707. ACM, 2010.
22. Bob L. Sturm. An analysis of the GTZAN music genre dataset. In Proceedings of the second international ACM workshop on Music Information Retrieval with usercentered and multimodal strategies, MIRUM '12, pages 7-12, New York, NY, USA, 2012. ACM.
23. Yichuan Tang. Deep learning using linear support vector machines. In Workshop on Representation Learning, ICML, 2013, Atlanta, USA, 2013.
24. George Tzanetakis and Perry Cook. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5):293-302, 2002.