@inproceedings{wan-etal-2023-new,
title = "New Datasets and Controllable Iterative Data Augmentation Method for Code-switching {ASR} Error Correction",
author = "Wan, Zhaohong and
Wan, Xiaojun and
Peng, Wei and
Li, Rongjun",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.543",
doi = "10.18653/v1/2023.findings-emnlp.543",
pages = "8075--8087",
abstract = "With the wide use of automatic speech recognition(ASR) systems, researchers pay more attention to the ASR error correction task to improve the quality of recognition results. In particular, ASR in bilingual or multilingual settings, namely code-switching ASR, has greater challenges and research value. In this paper, we first present code-switching ASR correction datasets obtained from solid ASR systems and automatic annotators. The datasets contain Chinese-English code-switching dialogues of bilingual speakers in Singapore, Malaysia, and Hong Kong. Based on this task, we propose a controllable iterative (CI) data augmentation method for improving the performance of mainstream ASR error correction systems. With a small amount of training data, our proposed method has the ability to iteratively produce abundant pseudo parallel data from the monolingual corpus for Chinese-English code-switching ASR correction. Results of experiments show that our method achieves the best performance compared with the rule-based, back-translation-based data augmentation methods and large language model ChatGPT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2023-new">
<titleInfo>
<title>New Datasets and Controllable Iterative Data Augmentation Method for Code-switching ASR Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaohong</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongjun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the wide use of automatic speech recognition(ASR) systems, researchers pay more attention to the ASR error correction task to improve the quality of recognition results. In particular, ASR in bilingual or multilingual settings, namely code-switching ASR, has greater challenges and research value. In this paper, we first present code-switching ASR correction datasets obtained from solid ASR systems and automatic annotators. The datasets contain Chinese-English code-switching dialogues of bilingual speakers in Singapore, Malaysia, and Hong Kong. Based on this task, we propose a controllable iterative (CI) data augmentation method for improving the performance of mainstream ASR error correction systems. With a small amount of training data, our proposed method has the ability to iteratively produce abundant pseudo parallel data from the monolingual corpus for Chinese-English code-switching ASR correction. Results of experiments show that our method achieves the best performance compared with the rule-based, back-translation-based data augmentation methods and large language model ChatGPT.</abstract>
<identifier type="citekey">wan-etal-2023-new</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.543</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.543</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8075</start>
<end>8087</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New Datasets and Controllable Iterative Data Augmentation Method for Code-switching ASR Error Correction
%A Wan, Zhaohong
%A Wan, Xiaojun
%A Peng, Wei
%A Li, Rongjun
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wan-etal-2023-new
%X With the wide use of automatic speech recognition(ASR) systems, researchers pay more attention to the ASR error correction task to improve the quality of recognition results. In particular, ASR in bilingual or multilingual settings, namely code-switching ASR, has greater challenges and research value. In this paper, we first present code-switching ASR correction datasets obtained from solid ASR systems and automatic annotators. The datasets contain Chinese-English code-switching dialogues of bilingual speakers in Singapore, Malaysia, and Hong Kong. Based on this task, we propose a controllable iterative (CI) data augmentation method for improving the performance of mainstream ASR error correction systems. With a small amount of training data, our proposed method has the ability to iteratively produce abundant pseudo parallel data from the monolingual corpus for Chinese-English code-switching ASR correction. Results of experiments show that our method achieves the best performance compared with the rule-based, back-translation-based data augmentation methods and large language model ChatGPT.
%R 10.18653/v1/2023.findings-emnlp.543
%U https://aclanthology.org/2023.findings-emnlp.543
%U https://doi.org/10.18653/v1/2023.findings-emnlp.543
%P 8075-8087
Markdown (Informal)
[New Datasets and Controllable Iterative Data Augmentation Method for Code-switching ASR Error Correction](https://aclanthology.org/2023.findings-emnlp.543) (Wan et al., Findings 2023)
ACL