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, lacking the ability to jointly model fine-grained temporal boundaries and robust cross-chunk identity linking. We propose G-STAR, an end-to-end framework that couples a cache-conditioned speaker-tracking module with a Speech-LLM transcription backbone. The tracker provides structured speaker cues with temporal grounding, and the LLM generates attributed text conditioned on these cues. G-STAR supports component-wise optimization and joint end-to-end training, enabling flexible learning under heterogeneous supervision and domain shift. Under chunk-wise decoding protocols, experiments on both oracle-segmented local evaluation and full-meeting global evaluation show strong speaker-attributed transcription performance.

翻译：我们研究了面向重叠长篇幅多说话人场景的带时间戳说话人属性自动语音识别（SA-ASR）。在该场景下，逐片段推理需在生成带时间戳的说话人标签转录文本的同时，保持会议级说话人身份一致性。现有语音-大语言模型系统倾向于优先处理局部说话人日志或全局标签标注，缺乏联合建模细粒度时间边界与鲁棒跨片段身份关联的能力。本文提出G-STAR——一种将缓存条件说话人追踪模块与语音-大语言模型转录基座结合的端到端框架。追踪器提供具有时间锚定的结构化说话人线索，大语言模型基于这些线索生成带属性标注的文本。G-STAR支持组件级优化与联合端到端训练，可在异构监督信号与领域迁移条件下实现灵活学习。在逐片段解码协议下，基于Oracle分割的局部评估与全程会议全局评估的实验均展现出优异的说话人属性转录性能。