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
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representationsIn Proceedings of the 26th annual international conference on machine learning, 2009