Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces MMedFD, a new real-world Chinese healthcare ASR dataset designed for multi-turn, full-duplex conversations, addressing the scarcity of open benchmarks for clinical dialogue ASR. The dataset contains 5,805 annotated sessions with synchronized user and mixed-channel audio, along with RTTM/CTM timing and role labels. The authors also present a model-agnostic pipeline for streaming segmentation, speaker attribution, and dialogue memory, and fine-tune Whisper-small on role-concatenated audio, providing a reproducible benchmark for streaming ASR and end-to-end duplex agents.
A new Chinese healthcare ASR dataset, MMedFD, offers a challenging real-world benchmark for full-duplex, multi-turn clinical dialogue, complete with synchronized audio, timing annotations, and a model-agnostic processing pipeline.
Automatic speech recognition (ASR) in clinical dialogue demands robustness to full-duplex interaction, speaker overlap, and low-latency constraints, yet open benchmarks remain scarce. We present MMedFD, the first real-world Chinese healthcare ASR corpus designed for multi-turn, full-duplex settings. Captured from a deployed AI assistant, the dataset comprises 5,805 annotated sessions with synchronized user and mixed-channel views, RTTM/CTM timing, and role labels. We introduce a model-agnostic pipeline for streaming segmentation, speaker attribution, and dialogue memory, and fine-tune Whisper-small on role-concatenated audio for long-context recognition. ASR evaluation includes WER, CER, and HC-WER, which measures concept-level accuracy across healthcare settings. LLM-generated responses are assessed using rubric-based and pairwise protocols. MMedFD establishes a reproducible framework for benchmarking streaming ASR and end-to-end duplex agents in healthcare deployment. The dataset and related resources are publicly available at https://github.com/Kinetics-JOJO/MMedFD