Music classification

Transfering audio classification problem into a visual one and tackling it with convolutional approach

This notebook explores application of ConvRBM (Lee et al., 2009) to classification of music genra. The main idea is to represent the audio extract as a spectrogram and then solve it as a slef-supervised vision problem. You can check out the details in the notebook below.

References

2009

  1. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
    Honglak Lee, Roger Grosse, Rajesh Ranganath, and 1 more author
    In Proceedings of the 26th annual international conference on machine learning, 2009