A multi-codebook discrete diffusion model with coarse-to-fine RVQ generation and span-localized guidance improves speech inpainting and editing on RealEdit.
For substitution and insertion operations, the system must determine the number of codec frames allocated to the edited span before generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing
A multi-codebook discrete diffusion model with coarse-to-fine RVQ generation and span-localized guidance improves speech inpainting and editing on RealEdit.