针对语音识别错误，提出一种高效纠错检索生成框架。
Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction
- 基于历史错误构建惩罚矩阵，优先召回可纠正文档。
- 在波斯语数据集上错误命中率从53.7%提升至90.9%。
- 无需额外延迟，适合低资源语言实时纠错场景。
端到端语音识别系统在低资源语言中常误识罕见实体和领域术语。现有检索增强生成框架或依赖忽略发音错误的稀疏检索，或使用高延迟的跨模态嵌入。本文提出一种纯词汇的高效错误感知框架，显式解决发音错误与循环幻觉问题。通过集成对称文本归一化模块与新型错误感知TF-IDF算法，基于历史错误构建稀疏对角惩罚矩阵，数学上优先选择包含特定高风险误识的修正文档。在FLEURS波斯语子集上的评估显示，错误感知命中率从53.7%提升至90.9%；端到端测试中，词错误率从23.06%降至18.83%，实现显著精度提升且推理延迟近乎为零。
原文摘要 · Abstract (English)
End-to-end automatic speech recognition systems frequently hallucinate rare entities and domain-specific terms, especially in low-resource languages. While retrieval-augmented generation frameworks can mitigate these errors using large language models, current architectures face significant challenges. They either rely on standard sparse retrieval that ignores phonetic misrecognitions or utilize heavyweight cross-modal embeddings that introduce high latency. This letter proposes a highly efficient, purely lexical error-aware framework designed to explicitly resolve phonetic and loop hallucinations. Our approach integrates a symmetric text normalization module with a novel error-aware term frequency-inverse document frequency algorithm. By constructing a sparse diagonal penalty matrix based on historical errors, the retriever mathematically prioritizes corrective documents containing specific high-risk misrecognitions. Evaluated on the Persian subset of the FLEURS dataset, our method increased the error-aware hit rate from 53.7% to 90.9%. In end-to-end evaluations, the integrated framework reduced the final word error rate from 23.06% to 18.83%, achieving significant accuracy gains with near-zero inference latency.
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。