Large Audio-Language Models (LALMs) have demonstrated remarkable performance in end-to-end speaker diarization and recognition. However, their speaker discriminability remains limited due to the scarcity of large-scale conversational data and the absence of explicit speaker representation optimization. To address this, we propose GLSC-SDR, a paradigm that jointly trains speaker classification with diarization and recognition. We further introduce a Global-Local Speaker Classification strategy, which uses clustered speakers as global labels and re-encoded intra-cluster speakers as local labels. This hierarchical design enhances fine-grained speaker discrimination while preserving semantic transcription accuracy. Experiments on AliMeeting, AISHELL-4, and AMI-SDM demonstrate that GLSC-SDR achieves competitive or superior performance compared to simulation-based and multi-encoder approaches, without relying on large-scale real conversational data.

翻译：大型音频-语言模型（LALMs）在端到端说话人日志与识别任务中展现出卓越性能。然而，由于大规模对话数据的稀缺以及缺乏显式说话人表示优化，其说话人区分能力仍存在局限。为此，我们提出GLSC-SDR范式，该范式联合训练说话人分类与日志和识别任务。我们进一步引入全局-局部说话人分类策略，该策略将聚类后的说话人作为全局标签，并将簇内重新编码的说话人作为局部标签。这种层级化设计在保留语义转录准确性的同时，增强了细粒度说话人区分能力。在AliMeeting、AISHELL-4和AMI-SDM上的实验表明，GLSC-SDR在不依赖大规模真实对话数据的情况下，相比基于模拟和多编码器的方法取得了具有竞争力或更优的性能。