Speech-to-LLM2 min read
Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining
Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge. The bridge is usually treated as plumbing, but it in fact defines the geometry of the speech-to-LLM interface, and the pretraining objective decides whether that…
By Xinnian Zhao, Chia-Hua Wu, Pu Wang, Hugo Van HammearXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 9, 2026.
Comments
Sign in to join the discussion.