SOURCE-LINKED INTELLIGENCE

X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency. Existing systems commonly use a fixed chunk size, look-ahead, or target delay, or encourage emissions near estimated acoustic boundaries. These approaches do not directly optimize how much additional context to use at each output position under a single-pass, hard-commit constraint. We propose X2Streaming-ASR, which decomposes streaming recognition into when to commit and what to commit. Its three-stage training procedure first esta

Read original source ↗ Open in workspace

recordType

paper

region

Global