AI RESEARCH

Text-only adaptation in LLM-based ASR through text denoising

arXiv CS.LG

ArXi:2601.20900v3 Announce Type: replace-cross Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet underexplored challenge. Standard fine-tuning of the LLM on the target domain text often disrupts the critical alignment between the speech and text modality learned by the projector, degrading performance. We