SOURCE-LINKED INTELLIGENCE

Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lacking the curated corpora behind state-of-the-art synthesis. We propose a data curation recipe that transforms audiobook recordings into TTS-ready data via WhisperX alignment and filtering. Then we fine-tune Parler-TTS (880M), a prompt-based multilingual model whose pre-training encodes phonetic priors transferable to Greek. During development, we find that LLM-generated style prompts introduce speaker drift at inference. Replacing them with deter

Read original source ↗ Open in workspace

recordType

paper

region

Global