AI art trends @ Sónar 2023

As an attendee at Sónar+D 2023, I witnessed the cutting-edge advancements and trends in AI art. This renowned event brought together artists, technologists, and enthusiasts who collectively explored the intersection of artificial intelligence and creativity. From cool installations to thought-provoking discussions, Sónar 2023 provided a platform to delve into AI art world. In this blog post, I’ll cover the key trends and insights I observed at Sónar+D 2023!

Continue reading

Preprint: “Adversarial permutation invariant training for universal sound sepration”

I’m very proud of our recent work, because by simply improving the loss (keeping the same model and dataset) we obtain an improvement of 1.4 dB SI-SNRi! 1 dB in source separation is a lot, and is perceptually noticeable. This is great work led by Emilian, who worked with us as an intern during the summer of 2022.

Check our paper and demo!

Imatge

Preprint: “Universal speech enhancement with score-based diffusion”

In this work we propose to consider the task of speech enhancement as a holistic endeavor, and present a universal speech enhancement system that tackles 55 different distortions at the same time. Our approach consists of a generative model that employs score-based diffusion. We show that this approach significantly outperforms the state of the art in a subjective test performed by expert listeners.

Check our project website, and paper on arXiv!

Continue reading