3 papers
cs.SD2026
Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing
Iftach Shoham, Tali Dror, Oren Gal +3
Speech recordings often contain missing, corrupted, or incorrect regions that must be reconstructed or modified without re-synthesizing the entire utterance. Speech inpainting rest…
cs.SD2025
Token-Based Audio Inpainting via Discrete Diffusion
Tali Dror, Iftach Shoham, Moshe Buchris +4
Audio inpainting seeks to restore missing segments in degraded recordings. Previous diffusion-based methods exhibit impaired performance when the missing region is large. We introd…
cs.LG2024
Markov flow policy -- deep MC
Nitsan Soffair, Gilad Katz
Discounted algorithms often encounter evaluation errors due to their reliance on short-term estimations, which can impede their efficacy in addressing simple, short-term tasks and…