2 papers
cs.CL2024
Target word activity detector: An approach to obtain ASR word boundaries without lexicon
Sunit Sivasankaran, Eric Sun, Jinyu Li +2
Obtaining word timestamp information from end-to-end (E2E) ASR models remains challenging due to the lack of explicit time alignment during training. This issue is further complica…
cs.CL2023
Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach
Junkun Chen, Jian Xue, Peidong Wang +2
Simultaneous Speech-to-Text translation serves a critical role in real-time crosslingual communication. Despite the advancements in recent years, challenges remain in achieving sta…