Slides: Training neural audio classifiers with few data

During the last summer, I have been a research intern at Telefónica Research (Barcelona). The article “Training neural audio classifiers with few data” is the outcome of this short (but intense!) collaboration with Joan Serrà, where we explored how to train deep learning models with just 1, 2 or 10 audios per class. Check it out on arXiv, and reproduce our results running our code! These slides are the extended version of what I will be presenting next week in ICASSP! See you in Brighton 🙂

Download the slides!

Next step: Dolby Laboratories

After five years at the Music Technology Group, I’m pretty excited to announce that I have accepted a full-time position as a researcher at Dolby Laboratories in Barcelona! I’m very happy to see how professional opportunities around machine learning keep growing in Barcelona. Our beloved city is becoming, more and more, an important AI hub in south Europe — what’s great, because it allows me to keep doing my job while being close to my friends and family!

Continue reading

On Ethics and Artificial Intelligence: an Economical Perspective

Which is the outtake of Artificial Intelligence (AI)? This is a recurrent conversation topic among AI practitioners, specialized journalists, and brave politicians. Although some simple concepts are clearly conveyed to the general audience, there are some others that are not so widely known. In this post I’ll be focusing on an important topic that is often overlooked: the economics behind AI.

Since AI is impacting our lives through products available in the marketplace, the goal of this post is to analyze what’s up with AI systems when consumed via the free market. In other words, AI is developed and consumed in a market-driven fashion and I would like to better understand which are the consequences of that. Hence, I’ll be focusing on the economic side of AI to show that for encouraging the main AI actors to behave ethically we better (directly) act over the market.

Continue reading

What’s up with waveform-based VGGs?

In this series of posts I have written a couple of articles discussing the pros & cons of spectrogram-based VGG architectures, to think about which is the role of the computer vision deep learning architectures in the audio field. Now is time to discuss what’s up with waveform-based VGGs!

Continue reading