arXiv:2604.22467v2 Announce Type: replace Abstract: Multi-speaker automatic speech recognition (ASR) aims to recognize not only what was said, but also who said it and when. Recent Speech-LLMs have shown promising results in structured multi-speaker transcription, but jointly modeling speaker attribution, temporal information, and lexical content remains challenging and often requires substantial model capacity and training data. To address this challenge, we propose DM-ASR, a Diarization-aware Multi-speaker ASR framework that reformulates multi-speaker recognition as diarization-conditioned multi-turn dialogue generation. By leveraging diarization-derived speaker-time cues as explicit structural priors, DM-ASR decomposes transcription into a sequence of conditioned queries while preserving mixed acoustic information and conversational context. We further introduce optional word-level timestamp prediction for fine-grained temporal grounding and investigate the complementary roles of diarization cues and language-model predictions. The proposed formulation also enables unified offline and causal sentence-level online decoding through flexible acoustic context and dialogue history management. Experiments on Mandarin and English benchmarks demonstrate competitive structured transcription performance with relatively compact models and training data, while effectively supporting both offline and online recognition.