用语音特征生成标注，纠正语音识别中的实体错误。
Generative Annotation for ASR Named Entity Correction
- 基于语音声学特征检索候选实体，生成错误标注。
- 在词形差异大的场景下，实体准确率显著提升。
- 适合需要高精度实体识别的语音系统下游任务。
端到端语音识别系统常无法正确转录领域特定命名实体，导致下游任务严重失效。近年来提出多种快速轻量的命名实体纠错（NEC）模型，主要依赖音素级编辑距离算法，表现优异。但当错误转录词与真实实体形式差异较大时，这些方法难以定位假设中的错误词，限制了应用。本文提出一种新NEC方法，利用语音声学特征检索候选实体，并创新性设计生成式方法，对语音识别文本中的实体错误进行标注并替换为正确实体。该方法在词形差异大的场景中表现有效。我们在开源和自建测试集上验证了该方法，结果表明其能显著提升实体准确率。自建训练数据和测试集已公开于github.com/L6-NLP/Generative-Annotation-NEC。
原文摘要 · Abstract (English)
End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been proposed in recent years. These models, mainly leveraging phonetic-level edit distance algorithms, have shown impressive performances. However, when the forms of the wrongly-transcribed words(s) and the ground-truth entity are significantly different, these methods often fail to locate the wrongly transcribed words in hypothesis, thus limiting their usage. We propose a novel NEC method that utilizes speech sound features to retrieve candidate entities. With speech sound features and candidate entities, we inovatively design a generative method to annotate entity errors in ASR transcripts and replace the text with correct entities. This method is effective in scenarios of word form difference. We test our method using open-source and self-constructed test sets. The results demonstrate that our NEC method can bring significant improvement to entity accuracy. The self-constructed training data and test set is publicly available at github.com/L6-NLP/Generative-Annotation-NEC.
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。