Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR

arXiv:2609.18333v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams modeling (DSM) has become the dominant paradigm…

Read the full story at arXiv cs.AI ↗