@inproceedings{luo-etal-2025-generative,
title = "Generative Annotation for {ASR} Named Entity Correction",
author = "Luo, Yuanchang and
Wei, Daimeng and
Li, Shaojun and
Shang, Hengchao and
Guo, Jiaxin and
Li, Zongyao and
Wu, Zhanglin and
Chen, Xiaoyu and
Rao, Zhiqiang and
Yang, Jinlong and
Yang, Hao",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1052/",
doi = "10.18653/v1/2025.emnlp-main.1052",
pages = "20835--20846",
ISBN = "979-8-89176-332-6",
abstract = "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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2025-generative">
<titleInfo>
<title>Generative Annotation for ASR Named Entity Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanchang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaojun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">luo-etal-2025-generative</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1052</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1052/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>20835</start>
<end>20846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative Annotation for ASR Named Entity Correction
%A Luo, Yuanchang
%A Wei, Daimeng
%A Li, Shaojun
%A Shang, Hengchao
%A Guo, Jiaxin
%A Li, Zongyao
%A Wu, Zhanglin
%A Chen, Xiaoyu
%A Rao, Zhiqiang
%A Yang, Jinlong
%A Yang, Hao
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F luo-etal-2025-generative
%X 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.
%R 10.18653/v1/2025.emnlp-main.1052
%U https://aclanthology.org/2025.emnlp-main.1052/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1052
%P 20835-20846
Markdown (Informal)
[Generative Annotation for ASR Named Entity Correction](https://aclanthology.org/2025.emnlp-main.1052/) (Luo et al., EMNLP 2025)
ACL
- Yuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Jinlong Yang, and Hao Yang. 2025. Generative Annotation for ASR Named Entity Correction. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20835–20846, Suzhou, China. Association for Computational Linguistics.