Authors:Hongzhao Chen, XiaoYang Wang, Jing Lan, Hexiao Ding, Yufeng Jiang, MingHui Yang, DanHui Xu, Jun Luo, Nga-Chun Ng, Gerald W.Y. Cheng, Yunlin Mao, Jung Sun Yoo
Abstract: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 this https URL
From: Hongzhao Chen [view email]
[v1]
Wed, 24 Sep 2025 06:56:26 UTC (469 KB)
[v2]
Fri, 26 Sep 2025 15:44:51 UTC (469 KB)
[v3]
Wed, 29 Jul 2026 06:28:54 UTC (471 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。