``Speech Enhancement and Dereverberation with Diffusion-based Generative Models. (arXiv:2208.05830v1 [eess.AS]),'' Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann, ift.tt/wQnkHcL

We are pleased to share our new work: „Speech Enhancement and Dereverberation with Diffusion-based Generative Models“ with exciting audio examples Pre-print: arxiv.org/abs/2208.05830 Audio examples: bit.ly/3Ai8pqT Code: github.com/sp-uhh/sgmse #diffusion

``StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation. (arXiv:2212.11851v1 [eess.AS]),'' Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann, ift.tt/1RnZ84l

``Diffusion Models for Audio Restoration,'' Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, Vesa V\"alim\"aki, Timo Gerkmann, ift.tt/hPW6pEG

🥳 Excited to share that our latest work on generating sample-based instruments from text or audio prompts has been accepted at #ISMIR2024! 🎹 — Our take on making AI-based music generation models useful for musicians! 🔊 gen-inst.netlify.app 📜 arxiv.org/abs/2407.15641 (1/6)

Best Student Paper Award at IWAENC 2024 with Eloi Moliner for our joint work on Unsupervised Speech Dereverberation using Diffusion Models!! Thanks to Simon Signal Processing, Uni Hamburg Aalto Acoustics Lab for the great work! More publications on the topic: inf.uni-hamburg.de/en/inst/ab/sp/…

🔍 Join Our Team! We have exciting open positions: 🎓 Postdoc: Data Science & AI for Speech & Audio 🎓 PhD/Postdoc: AI-based Speech & Audio 🎓 PhD: Diffusion Models for Speech Processing 🎓 3 PhD positions for Imaging & Speech 🔗 inf.uni-hamburg.de/en/inst/ab/sp/…

``Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech,'' Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, ift.tt/zUDo6Gv

New paper: Do social media algorithms shape affective polarization? We ran a field experiment on X/Twitter (N=1,256) using LLMs to rerank content in real-time, adjusting exposure to polarizing posts. Result: Algorithmic ranking impacts feelings toward the political outgroup!🧵⬇️

Seriously, what is wrong with you Suno? If anything, making music is industrious, but CLEARLY enjoyable, and as in most crafts, 99% of the beauty of it is in the process and the strive for perfection. Let us make the process more interesting, not discard it altogether...

Arrived at Hyderabad for #ICASSP2025 🇮🇳🇮🇳🇮🇳 Check out our work with Etienne Thuillier Eloi Moliner Signal Processing, Uni Hamburg on HRTF estimation using diffusion-based posterior sampling ieeexplore.ieee.org/document/10888… Rendez-vous at the session "Spatial Audio II" on Thu 10th 2:00 pm and hit me up for a chat

I onboarded a few weeks ago as a research scientist at NVIDIA Research, (temporarily?) shifted from speech processing to algorithmic-focused discrete diffusion modelling Happy for any discussion on this rapidly-evolving topic!

BREAKING: MIT just completed the first brain scan study of ChatGPT users & the results are terrifying. Turns out, AI isn't making us more productive. It's making us cognitively bankrupt. Here's what 4 months of data revealed: (hint: we've been measuring productivity all wrong)