2 papers
eess.AS2026
Persistent Delivery Optimization for Streaming Speech-to-Text Translation with Revisions
Zixiang Wan, Delin Chen, Wei Shi +3
Revision-capable streaming speech-to-text translation (S2TT) can correct earlier drafts, but process rewards based on visible text may credit content later withdrawn. Persistent De…
cs.CL2026
From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs
Xiaoyong Guo, Nanjie Li, Zijie Zeng +4
Contextual automatic speech recognition (ASR) with Speech-LLMs is typically trained with oracle conversation history, but relies on error-prone history at inference, causing a trai…