A reduced model size of SoundNet [1] by employing SVD-based pruning framework [2].
"p-Snet_model.py" file contains architecture of the pruned SoundNet (p-Snet). "p-Snet_weights.hdf5" file contains the pruned weights.
[1] Aytar, Yusuf, Carl Vondrick, and Antonio Torralba. "Soundnet: Learning sound representations from unlabeled video." Advances in neural information processing systems. 2016.
[2] Singh, Arshdeep, Padmanabhan Rajan, and Arnav Bhavsar. "SVD-Based Redundancy Removal in 1-D CNNs for Acoustic Scene Classification" PRL letters (Accepted, Link: https://doi.org/10.1016/j.patrec.2020.02.004).