A recurrent encoder-decoder approach with skip-filtering connections for monaural singing voice separation

Stylianos Ioannis Mimilakis, Konstantinos Drossos, Tuomas Virtanen, Gerald Schuller. A recurrent encoder-decoder approach with skip-filtering connections for monaural singing voice separation. In Naonori Ueda, Shinji Watanabe, Tomoko Matsui, Jen-Tzung Chien, Jan Larsen, editors, 27th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017, Tokyo, Japan, September 25-28, 2017. pages 1-6, IEEE, 2017. [doi]

Abstract

Abstract is missing.