AURALISATION OF DEEP CONVOLUTIONAL NEURAL NETWORKS: LISTENING TO LEARNED FEATURES

Deep learning has been actively adopted in the field of music information retrieval, e.g. genre classification, mood detection, and chord recognition. Deep convolutional neural networks (CNNs), one of the most popular deep learning approach, also have been used for these tasks. However, the process of learning and prediction is little understood, particularly when it is applied to spectrograms. We introduce auralisation of CNNs to understand its underlying mechanism.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  Juan Pablo Bello,et al.  Rethinking Automatic Chord Recognition with Convolutional Neural Networks , 2012, 2012 11th International Conference on Machine Learning and Applications.

[3]  Luiz G. Hafemann.  An analysis of deep neural networks for texture classification , 2014 .

[4]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[5]  Sebastian Böck,et al.  Improved musical onset detection with Convolutional Neural Networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).