带有自适应思维链的检索增强自教推理模型用于ASR命名实体修正
Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction
AI总结：
本文提出一种检索增强自教推理模型，用于改进ASR中命名实体修正，通过自适应思维链和音节级编辑距离提升纠错效果。
摘要：
端到端的自动语音识别（ASR）系统经常错误识别领域特定短语，如命名实体，这可能导致下游任务中的灾难性故障。一种基于大语言模型（LLMs）的新命名实体修正方法最近出现。然而，这些方法尚未充分利用LLMs固有的复杂推理能力。为弥合这一差距，我们提出了一种新的检索增强生成框架，用于纠正ASR中的命名实体错误。我们的方法包含两个关键组成部分：（1）一个用于命名实体识别的重述语言模型（RLM），随后使用音节级编辑距离进行候选检索；（2）一种新的自教推理模型，具有自适应思维链（A-STAR），该模型根据任务难度动态调整推理深度。在AISHELL-1和同音词数据集上的实验表明，我们的方法有效，相比强基线，分别实现了命名实体字符错误率的相对减少17.96%和34.42%。
英文摘要：
End-to-end automatic speech recognition (ASR) systems frequently misrecognize domain-specific phrases like named entities, which can cause catastrophic failures in downstream tasks. A new family of named entity correction methods based on large language models (LLMs) has recently emerged. However, these approaches have yet to fully exploit the sophisticated reasoning capabilities inherent to LLMs. To bridge this gap, we propose a novel retrieval-augmented generation framework for correcting named entity errors in ASR. Our approach consists of two key components: (1) a rephrasing language model (RLM) for named entity recognition, followed by candidate retrieval using a phonetic-level edit distance; and (2) a novel self-taught reasoning model with adaptive chain-of-thought (A-STAR) that dynamically adjusts the depth of its reasoning based on task difficulty. Experiments on the AISHELL-1 and Homophone datasets demonstrate the effectiveness of our method, which achieves relative reductions in the named entity character error rate of 17.96\% and 34.42\%, respectively, compared to a strong baseline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
