Guest Seminar - Joseph (Yossi) Keshet

May 7, 2025 1:00pm — 2:00pm

Location:
In Person - Wean Hall 4625

Speaker:
JOSEPH (YOSSI) KESHET , Associate Professor, Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, and Director, Speech, Language, and Deep Learning Lab, The Technion
https://keshet.net.technion.ac.il/

In this talk, I will present two complementary contributions that push the boundaries of diffusion models from both theoretical and practical angles. First, I will introduce a novel spectral analysis framework that interprets the inference process of diffusion models through a frequency-domain lens. This allows for a principled design of noise schedules tailored to the data’s spectral properties, replacing heuristic approaches with theoretically grounded strategies. I will then present DiffAR, an autoregressive diffusion model capable of generating high-fidelity raw speech waveforms end-to-end. By operating directly in the waveform domain and conditioning on overlapping frames, DiffAR achieves coherent, expressive, and naturally varied speech generation.  

— 

Joseph (Yossi) Keshet received his B.Sc. and M.Sc. degrees in Electrical Engineering from Tel Aviv University in 1994 and 2002, respectively. He completed his Ph.D. in Computer Science in 2008 at the School of Computer Engineering, The Hebrew University of Jerusalem. From 2008 to 2009, he was a postdoctoral researcher at EPFL and the IDIAP Research Institute in Switzerland. He then served as a Research Assistant Professor at TTIC from 2009 to 2012. Between 2013 and 2022, he was an Associate Professor in the Department of Computer Science at Bar-Ilan University. Since 2022, he has been an Associate Professor at the Faculty of Electrical and Computer Engineering at the Technion. His research interests include speech recognition, speech synthesis, and speech analysis.  

More on the speaker. 

Faculty Host:  Bhiksha Ramakrishnan

Add event to Google
Add event to iCal