138 citations · 299 across the 17 of their papers we have counts for
5 papers · 1 filter
Speech Enhancement with Wide Residual Networks in Reverberant Environments
Jorge Llombart, Dayana Ribas, Antonio Miguel +3
This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimen…
Progressive Speech Enhancement with Residual Connections
Jorge Llombart, Dayana Ribas, Antonio Miguel +3
This paper studies the Speech Enhancement based on Deep Neural Networks. The proposed architecture gradually follows the signal transformation during enhancement by means of a visu…
Deep Speech Enhancement for Reverberated and Noisy Signals using Wide Residual Networks
Dayana Ribas, Jorge Llombart, Antonio Miguel +1
This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Resid…
Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification
Victoria Mingote, Antonio Miguel, Alfonso Ortega +1
This paper explores two techniques to improve the performance of text-dependent speaker verification systems based on deep neural networks. Firstly, we propose a general alignment…
Disentangling and Learning Robust Representations with Natural Clustering
Javier Antoran, Antonio Miguel
Learning representations that disentangle the underlying factors of variability in data is an intuitive way to achieve generalization in deep models. In this work, we address the s…