I’m a PhD student at Pompeu Fabra University in Barcelona.
Audio-visual analysis!: audio inpainting, cross-model generation, lip reading, video inpaining, Blind Source Separation.
How do I do it?
Well… I work on academia so I don’t have many resources. I work with Graph-CNNs and Transformers nor encoder-decoders! This is fast, cheap and reaches SOTA results!
Nice people around
I do belong to the Music Technology Group and to the Image Processing Group, being co-supervised by the Dr. Emilia Gómez and the Dr. Gloria Haro.
Special acknowledgment to Olga Slizovskaia, great researcher and better person for being my menthor in this competitive world.
Who I am outside the lab?
I do love Mountains, I’ve been in the Amazonas, climbed volcanoes, do canyoning, treeking or ski. Eat bugs, termites or ants sometimes :/