AI RESEARCH
MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
arXiv CS.AI
•
ArXi:2511.10262v3 Announce Type: replace-cross Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a dynamic user experience compared to traditional half-duplex models. However, existing benchmarks primarily focus on evaluating single-round interactions, neglecting the complexities of multi-round communication. Evaluating FD-SLMs in multi-round settings poses significant challenges, including blurred turn boundaries in communication and context inconsistency during model inference.