A multi-codebook discrete diffusion model with coarse-to-fine RVQ generation and span-localized guidance improves speech inpainting and editing on RealEdit.
SpeechPainter: Text-conditioned Speech Inpainting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose SpeechPainter, a model for filling in gaps of up to one second in speech samples by leveraging an auxiliary textual input. We demonstrate that the model performs speech inpainting with the appropriate content, while maintaining speaker identity, prosody and recording environment conditions, and generalizing to unseen speakers. Our approach significantly outperforms baselines constructed using adaptive TTS, as judged by human raters in side-by-side preference and MOS tests.
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.