S
Santiago Pascual
Researcher at Polytechnic University of Catalonia
Publications - 49
Citations - 2434
Santiago Pascual is an academic researcher from Polytechnic University of Catalonia. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 17, co-authored 43 publications receiving 1638 citations. Previous affiliations of Santiago Pascual include Dolby Laboratories.
Papers
More filters
Proceedings ArticleDOI
SEGAN: Speech Enhancement Generative Adversarial Network
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.
Proceedings ArticleDOI
Multi-Task Self-Supervised Learning for Robust Speech Recognition
Mirco Ravanelli,Jianyuan Zhong,Santiago Pascual,Pawel Swietojanski,Joao Monteiro,Jan Trmal,Yoshua Bengio +6 more
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.
Proceedings ArticleDOI
Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks.
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.
Posted Content
SEGAN: Speech Enhancement Generative Adversarial Network
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.
Posted Content
Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks
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.