We intend to obtain higher level audio features and compare performance with standard features for audio like MFCC. This work is largely inspired by [1]. The applications will be in audio, music and speech.
For more details, please contact: Ashwin Kalyan email: asaavashwin [at] gmail [dot] com OR Deepu Vijayasenan email: deepu [dot] senan [at] gmail [dot] com
[1] Lee, Honglak, et al. "Unsupervised feature learning for audio classification using convolutional deep belief networks." Advances in neural information processing systems. 2009.