Search papers, labs, and topics across Lattice.
2
0
4
1
Ditch the heuristics: Hikari achieves state-of-the-art simultaneous speech translation by learning READ/WRITE decisions directly through a probabilistic WAIT token.
Encoder-only multi-talker ASR can now rival LLM-based systems in accuracy while drastically reducing computational cost, thanks to a novel distillation approach and talker-count routing.
