Efficient Spoken Language Recognition via Multilabel Classification

TL;DR: we present efficient models for the task of Spoken Language Recognition plus an effective strategy to gracefully handle unsupported languages via multilabel classification.

Thumbnail image

ICASSP 2023: The Good, the Bad, and the Ugly

The beautiful Island of Rhodes welcomed the most prestigious signal processing conference in the world this past week.

Thumbnail image

Audio-Text Models Do Not Yet Leverage Natural Language

TL;DR: we thoroughly analyzed state-of-the-art audio-text multimodal models and they do not fully leverage natural language.

Thumbnail image

The Best of ISMIR 2022

And finally, after 2 years with virtual-only ISMIRs, this year we had the first post-pandemic in-person ISMIR.

Thumbnail image

Burning Man Intensifies

I keep seeing wonderful pictures from this year’s Burning Man, and they inspired me to share a terrible one, to counterbalance.

Thumbnail image

Music Signal Enhancement

This year at ICASSP we’re presenting a novel technique to enhance a music signal via generative adversarial networks and diffusion probabilistic models.

Model Architecture

12021 HE

And the year 12021 of the Human Era (i.e., 2021 AD, but let’s try not to be religious here) just ended.

Music Segmentation Talk

Last month, I was invited to give a talk at MagniMind Academy.

Music Segmentation Presentation