G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition 事件

G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition arXiv:2603.10468v2 Announce Type: replace-cross Abstract: We study timestamped speaker-attributed automatic speech recognition (SA-ASR) for long-form, multi-party speech with overlap. In this setting, chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Prior Speech-LLM systems tend to prioritize either local diarization or global labeling, lackin