Julius Richter

Join me tomorrow for a webinar on "Generative Audio Restoration in Multimodal Applications"!
I'll introduce the tractable Schrödinger bridge and discuss the differences between flow matching and score-based methods.
signalprocessingsociety.org/blog/sps-web...

Will present our paper, "Investigating Training Objectives for Generative Speech Enhancement" at #ICASSP2025!
🗓 Wed, 5:00-6:30 PM (AASP-P12)
🔊 Discussing diffusion bridges (Schrödinger bridge) & connections to score-based models—let’s chat!

Very nice! Unfortunately, I can’t open the second link.

Thanks for sharing! I am interested in the latent diffusion model for speech restoration.

Looks interesting! Could potentially be applied to real-time speech processing?

Diffusion Models for Audio Restoration: A review [Special Issue On Model-Based and Data-Driven Audio Signal Processing] With the development of audio playback devices and fast data transmission, the demand for high sound quality is rising for both entertainment and communications. In this quest for better sound quality...

Our article, "Diffusion Models for Audio Restoration: A Review," is now published in the IEEE Signal Processing Magazine!

A huge thank you to all co-authors Jean-Marie Lemercier, Julius Richter, Simon Welker, Eloi Moliner, and Vesa Välimäki for a great collaboration.

doi.org/10.1109/MSP....

GitHub - sp-uhh/sgmse: Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation - sp-uhh/sgmse

🎉 Excited to announce that our paper got accepted at #ICASSP2025! We achieved state-of-the-art performance in PESQ on VB-DMD (yes, we're still using this benchmark 😂). Plus, our method shines on EARS-WHAM at 48 kHz! Check it out: github.com/sp-uhh/sgmse 🚀📈 #GenertiveAI

Presentation day!

I am going to present our contribution of Team Hamburgers 🍔 to the URGENT Challenge.

NeurIPS, Saturday Dec 14, 3:45 pm, West Meeting Room 215, 216.

GitHub - sp-uhh/gen-se-demo: Diffusion-based Speech Enhancement: Demonstration of Performance and Generalization Diffusion-based Speech Enhancement: Demonstration of Performance and Generalization - sp-uhh/gen-se-demo

🗣️ Tomorrow I will be presenting a 𝗗𝗲𝗺𝗼 𝗼𝗻 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗦𝗽𝗲𝗲𝗰𝗵 𝗘𝗻𝗵𝗮𝗻𝗰𝗲𝗺𝗲𝗻𝘁.

NeurIPS: Saturday, Dec 14, 4:15 pm at West Meeting Room 114, 115

Hope to see you there!

Also feel free to try the Demo for yourself:
🔗 github.com/sp-uhh/gen-s...

Having a great time in Vancouver attending @neuripsconf.bsky.social !
Hope to see you at the Urgent Challenge or Audio Imagination Workshop.

Nice trip with the diffusion gang!

Albert Oehlen – Computer paintings
@HamburgerKunsthalle