Santiago Pascual

TL;DR: This work proposes the use of generative adversarial networks for speech enhancement, and operates at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them.

TL;DR: PASE+ is proposed, an improved version of PASE that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks and learns transferable representations suitable for highly mismatched acoustic conditions.

TL;DR: This article proposed an improved self-supervised method, where a single neural encoder is followed by multiple workers that jointly solve different selfsupervised tasks, and the needed consensus across different tasks naturally imposes meaningful constraints to the encoder, contributing to discover general representations and to minimize the risk of learning superficial ones.

TL;DR: In this paper, a generative adversarial network (GAN) is proposed for speech enhancement, where the model is trained at the waveform level, training the model end-to-end and incorporating 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them.

TL;DR: Experiments show that the proposed improved self-supervised method can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues.