将韩语医学讲座的语音转写结果，改写为更准确的英文术语文本。
AI_LectureNote: A Retrospective Pilot Study of a Post-ASR Workflow for English-Script Rendering and Semantic Drift in Korean-English Medical Lectures
- 后处理重写语音转写内容，还原拉丁字母医学术语
- 英文术语还原率从0.39提升至0.71，3分钟分段后达0.65
- 虽提升可读性，但存在语义偏移和语气判断错误
AI_LectureNote 是一种面向韩语-英语医学讲座的可读性优化型后语音转写（post-ASR）工作流。它将语音识别输出重写为便于学习的笔记文本，并恢复拉丁字母医学术语，而非韩语音译形式。本研究在四场作者录制的讲座上，针对五个不同条件进行回溯评估。结果显示，后处理使 Whisper-1 路径上的英文术语还原率从 0.39 提升至 0.71，而对 3 分钟分块后的 GPT-4o 转录结果，该值从 0.26 提升至 0.65。然而，英文术语还原并不等同于语义忠实：两种后处理条件下分别出现 34 和 36 例（共 282 句）语义偏移，以及 11 和 13 例（共 101 个极性线索）语气判断错误。跨输入对比显示，极性失败模式在不同前端间重叠度更高（Jaccard 0.60，15 项中共享 9 项），而一般语义偏移差异更大（Jaccard 0.23，57 项中共享 13 项）。该单标注者试点研究记录了具体失效模式，支持对表面准确性、术语书写、分块一致性与医学意义保留进行独立评估。
原文摘要 · Abstract (English)
AI_LectureNote is a historical, readability-oriented post-ASR workflow for Korean-English medical lectures. It rewrites speech-to-text output into study transcripts while restoring Latin-script medical terms rather than Korean phonetic transliterations. We retrospectively evaluate the workflow on four author-recorded lectures across five conditions. In this pilot, post-processing raised the macro English-script rendering rate from 0.39 to 0.71 on the whisper-1 path and from 0.26 to 0.65 when applied to 3-minute chunked gpt-4o-transcribe output. However, English-script rendering did not imply semantic faithfulness: the two post-processed conditions showed semantic drift in 34 and 36 of 282 reference sentences and polarity failures in 11 and 13 of 101 polarity-cue rows. A descriptive cross-input comparison suggested different candidate failure patterns: polarity-failure sets overlapped more strongly across front-ends (Jaccard 0.60; 9 shared of 15 unioned failures) than general semantic-drift sets (Jaccard 0.23; 13 shared of 57 unioned drifts). This single-annotator pilot documents concrete failure modes rather than population rates and supports evaluating surface accuracy, term-script rendering, chunk-level script consistency, and medical-meaning preservation separately.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。