# Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards

arXiv: https://arxiv.org/abs/2602.00560 · HTML: https://mlsanity.com/paper/2602.00560/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2026.

## Built on by (most cited first, 1 of 1)

- [Fish Audio Drama 3 Technical Report](https://mlsanity.com/paper/2610.18010/) (2026)

## Abstract (arXiv)

Imperceptible text-based speech editing modifies spoken content through transcript manipulation while preserving acoustic continuity. Prior acoustic-space approaches suffer from content-style entanglement, causing unstable generation and boundary artifacts. We introduce a framework guided by the principle of "Edit Content, Preserve Acoustics". Editing is conducted in a stable semantic space, while acoustic realization is handled by a Flow Matching decoder. To ensure perceptual consistency, we propose Self-Consistency Rewards Group Relative Policy Optimization, which leverages a pre-trained Text-to-Speech model as an implicit critic, together with intelligibility and duration constraints. Experiments demonstrate consistent improvements over state-of-the-art autoregressive and non-autoregressive baselines in intelligibility, robustness, and perceptual quality.