Total: 1
End-to-end automatic speech recognition systems often fail to transcribe domain-speciffcnamed entities, causing catastrophic failuresin 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 theforms of the wrongly-transcribed words(s) and the ground-truth entity are signiffcantly 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 entityerrors in ASR transcripts and replace the textwith correct entities. This method is effective inscenarios of word form difference. We test ourmethod using open-source and self-constructed test sets. The results demonstrate that our NEC method can bring signiffcant improvement to entity accuracy. We will open source our self constructed test set and training data.