SOURCE-LINKED INTELLIGENCE

Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, unnatural pauses, or flattened intonation, that utterance-level metrics often fail to expose. We present LoopTTS, a judge-guided Filter-Judge-Refiner framework for recovering low-quality TTS outputs diagnosed by an AudioLLM. Given an initial utterance from a base TTS model, an AudioLLM Judge identifies salient prosodic issues and generates structured refine instructions; a Refiner, our fine-grained instruction-following TTS model, then performs guid

Read original source ↗ Open in workspace

recordType

paper

region

Global