Search Results for author:
Found 2 papers, 0 papers with code
Spectrogram Feature Losses for Music Source Separation
In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training.
Unsupervised Deep Representations for Learning Audience Facial Behaviors
In this paper, we present an unsupervised learning approach for analyzing facial behavior based on a deep generative model combined with a convolutional neural network (CNN).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
