نسخة أولية وصول مفتوح
All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation
Large Language Models (LLMs) have shown strong performance in low-resource offline translation; however, extending them to simultaneous speech-to-speech translation (Simul-S2ST) remains challenging due to the scarcity of causally aligned training data with high cross-lingual speaker fidelity. In addition, existing appr …