Kaiqi Fu

This paper identifies a gap in both speech initiation and response content that requires genuine content understanding and intervention decisions grounded in it and constructs context-matched English monologues in which only the trigger utterance varies within a topic.

Tracking text progress directly from latent speech tokens rather than rendered audio cuts alignment error by 88% while slashing compute overhead by 20x.

X2Streaming-ASR slashes commit latency to as low as 27 ms while achieving superior recognition accuracy, setting a new benchmark for streaming ASR systems.

Real-time turn-taking detection can be achieved with unprecedented accuracy and low latency using a novel dual-head modeling approach.