2026/04/30 by Sihan Lv, Yechen Jin, Zhen Li +5
Computer Science · #cs.AI #cs.SD
paper · pdf · doi:10.48550/arxiv.2604.16056
arxiv created 2026/08/03 · arxiv updated 2026/08/04
Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Current approaches generally involve either expensive task-specific training or adapting pre-trained Text-to-Speech (TTS) models. However, both paradigms face challenges: task-specific methods often degrade fidelity in unedited regions, whereas TTS adaptations struggle with a trade-off between editing naturalness and temporal fidelity. To address these issues, we propose AST, an Adaptive, Seamless, and Training-free speech editing framework. Built upon pre-trained TTS, AST leverages Latent Recomposition to stitch preserved source segments with synthesized targets, guaranteeing fidelity in unedited regions. To break the quality-controllability trade-off, we introduce Adaptive Weak Fact Guidance (AWFG), which modulates a mel-space signal to ensure seamless boundary transitions without disrupting the generative manifold. Furthermore, to address evaluation gaps in temporal fidelity, we propose a new benchmark suite: the LibriSpeech-Edit dataset and a novel metric, Word-level Dynamic Time Warping (WDTW). Extensive experiments demonstrate that AST consistently outperforms existing task-specific and fine-tuned speech editing methods across content accuracy, perceptual quality, speaker preservation, and temporal fidelity. Remarkably, AST achieves state-of-the-art zero-shot speech editing performance without any task-specific training or paired editing data, validating the effectiveness of latent recomposition and AWFG in bridging the quality-controllability trade-off.