I was invited to give a talk to the Deep Learning for Speech and Language Winter Seminar @ UPC, Barcelona. Since UPC is the university where I did my undergaduate sudies, it was a great pleasure to give an introductory talk about how our community is using deep learning for approaching music technology problems.
Overall, the talk was centered in reviewing the state-of-the-art (1988-2016) in deep learning for music data processing in order to boost some discussion about current trends. Several key papers were chronologically listed and briefly described: pioneer papers using MLP [1], RNNs [2], LSTMs [3] and CNNs [4] for music data processing; and pioner papers using symbolic data [1], spectrograms [5] and waveforms [6] – among others.
Throghouht the slides, I present a chronology where some papers are highlighted.
Do you agree with this chronology? Feel free to contact me for any suggestion (or claim) about which are the first papers using well-known deep learning techniques for music data processing.
[1] J. P. Lewis. “Creation by refinement: A creativity paradigm for gradient descent learning networks”. International Conf. on Neural Networks. 1988.
[2] P. M. Todd. “A sequential network design for musical applications”. Proceedings of the Connectionist Models Summer School. 1988.
[3] D. Eck and J Schmidhuber. “A first look at music composition using lstm recurrent neural networks”. Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale. 2002.
[4] H. Lee, P. Pham, Y. Largman, and A. Y. Ng. “Unsupervised feature learning for audio classification using convolutional deep belief networks”. Advances in neural information processing systems (NIPS). 2009.
[5] M. Marolt, A. Kavcic, and M. Privosnik. “Neural networks for note onset detection in piano music”. International Computer Music Conference (ICMC). 2002.
[6] S. Dieleman and B. Schrauwen. “End-to-end learning for music audio”. International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2014.
Thanks to @DocXavi for the picture!