Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
更少的幻觉,更多的验证:一种基于LLM的三阶段框架用于语音识别错误纠正
机构 * Huazhong University of Science and Technology, School of Electronic Information and Communications(华中科技大学电子信息与通信学院) ; MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China(人工智能联合实验室、AI研究院、X-LANCE实验室、上海交通大学) ; AISpeech Ltd, Suzhou, China(上海苏州AISpeech有限公司)
专题命中 其他推理 :reasoning(abstract);chain-of-thought(abstract);分类 cs.CL
AI总结 本文提出一种基于LLM的三阶段框架,用于减少语音识别错误纠正中的幻觉问题,通过预检测、链式思维修正和推理验证提高纠正准确性。
Comments This paper has been ACCEPTED for publication in ASRU