@inproceedings{li-vu-2024-improving,
title = "Improving Noisy Student Training for Low-resource Languages in End-to-End {ASR} Using {C}ycle{GAN} and Inter-domain Losses",
author = "Li, Chia-Yu and
Vu, Ngoc Thang",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.sigul-1.17",
pages = "133--142",
abstract = "Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is costly for low-resource languages. Therefore, this paper considers a more extreme case of semi-supervised end-to-end automatic speech recognition where there are limited paired speech-text, unlabeled speech (less than five hours), and abundant external text. Firstly, we observe improved performance by training the model using our previous work on semi-supervised learning {``}CycleGAN and inter-domain losses{''} solely with external text. Secondly, we enhance {``}CycleGAN and inter-domain losses{''} by incorporating automatic hyperparameter tuning, calling {``}enhanced CycleGAN inter-domain losses.{''} Thirdly, we integrate it into the noisy student training approach pipeline for low-resource scenarios. Our experimental results, conducted on six non-English languages from Voxforge and Common Voice, show a 20{\%} word error rate reduction compared to the baseline teacher model and a 10{\%} word error rate reduction compared to the baseline best student model, highlighting the significant improvements achieved through our proposed method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-vu-2024-improving">
<titleInfo>
<title>Improving Noisy Student Training for Low-resource Languages in End-to-End ASR Using CycleGAN and Inter-domain Losses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chia-Yu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is costly for low-resource languages. Therefore, this paper considers a more extreme case of semi-supervised end-to-end automatic speech recognition where there are limited paired speech-text, unlabeled speech (less than five hours), and abundant external text. Firstly, we observe improved performance by training the model using our previous work on semi-supervised learning “CycleGAN and inter-domain losses” solely with external text. Secondly, we enhance “CycleGAN and inter-domain losses” by incorporating automatic hyperparameter tuning, calling “enhanced CycleGAN inter-domain losses.” Thirdly, we integrate it into the noisy student training approach pipeline for low-resource scenarios. Our experimental results, conducted on six non-English languages from Voxforge and Common Voice, show a 20% word error rate reduction compared to the baseline teacher model and a 10% word error rate reduction compared to the baseline best student model, highlighting the significant improvements achieved through our proposed method.</abstract>
<identifier type="citekey">li-vu-2024-improving</identifier>
<location>
<url>https://aclanthology.org/2024.sigul-1.17</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>133</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Noisy Student Training for Low-resource Languages in End-to-End ASR Using CycleGAN and Inter-domain Losses
%A Li, Chia-Yu
%A Vu, Ngoc Thang
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F li-vu-2024-improving
%X Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is costly for low-resource languages. Therefore, this paper considers a more extreme case of semi-supervised end-to-end automatic speech recognition where there are limited paired speech-text, unlabeled speech (less than five hours), and abundant external text. Firstly, we observe improved performance by training the model using our previous work on semi-supervised learning “CycleGAN and inter-domain losses” solely with external text. Secondly, we enhance “CycleGAN and inter-domain losses” by incorporating automatic hyperparameter tuning, calling “enhanced CycleGAN inter-domain losses.” Thirdly, we integrate it into the noisy student training approach pipeline for low-resource scenarios. Our experimental results, conducted on six non-English languages from Voxforge and Common Voice, show a 20% word error rate reduction compared to the baseline teacher model and a 10% word error rate reduction compared to the baseline best student model, highlighting the significant improvements achieved through our proposed method.
%U https://aclanthology.org/2024.sigul-1.17
%P 133-142
Markdown (Informal)
[Improving Noisy Student Training for Low-resource Languages in End-to-End ASR Using CycleGAN and Inter-domain Losses](https://aclanthology.org/2024.sigul-1.17) (Li & Vu, SIGUL-WS 2024)
ACL