Upsamplers are a key element for developing computationally efficient and high-fidelity neural audio synthesizers. Given their importance, together with the fact that the audio literature only provides sparse and unorganized insights, our work is aimed at advancing and consolidating our current understanding of neural upsamplers.Continue reading
Category Archives: Deep learning
SESQA: Semi-supervised Learning for Speech Quality Assessment
Can semi-supervised learning help us estimating accurate MOS quality estimates of speech? Yes, and not only that – its heads used for semi-supervised training can also convey relevant information related to the task.
Check our paper!Continue reading
Thesis defence.. but as a jury member!
Now that I’m a doctor, I can be called to be part of a jury for helping to evaluate PhD students. Today was my first experience doing that, and it was double special because the other jury member was Axel Roebel — with whom I started my research career.
Thanks to Javier Nistal, Gaël Richard and Steffan Lattner for inviting me!
Young researcher award!
The fourth edition of the Research Awards Sociedad Científica Informática de España (SCIE) – Fundación BBVA awarded me (under the category of Young Researchers in Computer Science) for my contributions within the discipline of music information retrieval, with special emphasis on the use of deep learning architectures in the labelling of sound and music signals.Continue reading
ICASSP 2020: my selection!
It’s unfortunate that ICASSP 2020 was held online.. because we were excited to share our beloved Barcelona with you, folks. I’m sure, though, that we’ll have other chances to discover the best tapas in town!Continue reading