Jordi Pons | Jordi Pons

ICASSP 2023: accepted papers

By Jordi Pons in Conferences February 15, 2023

These are the papers we will be presenting at ICASSP 2023! Infinite thanks to all my collaborators for the amazing work 🙂

Full-band General Audio Synthesis with Score-based Diffusion by Santi Pascual, Gautam Bhattacharya, Chunghsin Yeh, Jordi Pons and Joan Serrà.
Adversarial Permutation Invariant Training for Universal Sound Separation by Emilian Postolache, Jordi Pons, Santi Pascual and Joan Serrà.

*Image by DALL·E with prompt: “audio synthesis and sound separation science”.*

Preprint: “Full-band General Audio Synthesis with Score-based Diffusion”

By Jordi Pons in Deep learning, Paper is out, Results November 1, 2022

In this paper we present DAG: a full-band (48kHz) waveform synthesizer based on diffusion-based generative modeling! And style transfer comes for free.. check out our demo! This is great work led by Santi.

See our paper and demo!

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

By Jordi Pons in Deep learning, Paper is out, Results October 21, 2022

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!

Interspeech 2022 paper: “PodcastMix: A dataset for separating music and speech in podcasts”

By Jordi Pons in Conferences, Datasets, Deep learning, Paper is out July 18, 2022

Today we release “PodcastMix”, a dataset for separating music and speech in podcasts:

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

By Jordi Pons in Deep learning, Paper is out June 18, 2022

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!