@inproceedings{tazakka-etal-2024-indonesian,
title = "{I}ndonesian-{E}nglish Code-Switching Speech Recognition Using the Machine Speech Chain Based Semi-Supervised Learning",
author = "Tazakka, Rais Vaza Man and
Lestari, Dessi and
Purwarianti, Ayu and
Tanaya, Dipta and
Azizah, Kurniawati and
Sakti, Sakriani",
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-1.18/",
pages = "143--148",
abstract = "Indonesia is home to a diverse linguistic landscape, where individuals seamlessly transition between Indonesian, English, and local dialects in their everyday conversations{---}a phenomenon known as code-switching. Understanding and accommodating this linguistic fluidity is essential, particularly in the development of accurate speech recognition systems. However, tackling code-switching in Indonesian poses a challenge due to the scarcity of paired code-switching data. Thus, this study endeavors to address Indonesian-English code-switching in speech recognition, leveraging unlabeled data and employing a semi-supervised technique known as the machine speech chain. Our findings demonstrate that the machine speech chain method effectively enhances Automatic Speech Recognition (ASR) performance in recognizing code-switching between Indonesian and English, utilizing previously untapped resources of unlabeled data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tazakka-etal-2024-indonesian">
<titleInfo>
<title>Indonesian-English Code-Switching Speech Recognition Using the Machine Speech Chain Based Semi-Supervised Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rais</namePart>
<namePart type="given">Vaza</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Tazakka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dessi</namePart>
<namePart type="family">Lestari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipta</namePart>
<namePart type="family">Tanaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurniawati</namePart>
<namePart type="family">Azizah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>Indonesia is home to a diverse linguistic landscape, where individuals seamlessly transition between Indonesian, English, and local dialects in their everyday conversations—a phenomenon known as code-switching. Understanding and accommodating this linguistic fluidity is essential, particularly in the development of accurate speech recognition systems. However, tackling code-switching in Indonesian poses a challenge due to the scarcity of paired code-switching data. Thus, this study endeavors to address Indonesian-English code-switching in speech recognition, leveraging unlabeled data and employing a semi-supervised technique known as the machine speech chain. Our findings demonstrate that the machine speech chain method effectively enhances Automatic Speech Recognition (ASR) performance in recognizing code-switching between Indonesian and English, utilizing previously untapped resources of unlabeled data.</abstract>
<identifier type="citekey">tazakka-etal-2024-indonesian</identifier>
<location>
<url>https://aclanthology.org/2024.sigul-1.18/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>143</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Indonesian-English Code-Switching Speech Recognition Using the Machine Speech Chain Based Semi-Supervised Learning
%A Tazakka, Rais Vaza Man
%A Lestari, Dessi
%A Purwarianti, Ayu
%A Tanaya, Dipta
%A Azizah, Kurniawati
%A Sakti, Sakriani
%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 tazakka-etal-2024-indonesian
%X Indonesia is home to a diverse linguistic landscape, where individuals seamlessly transition between Indonesian, English, and local dialects in their everyday conversations—a phenomenon known as code-switching. Understanding and accommodating this linguistic fluidity is essential, particularly in the development of accurate speech recognition systems. However, tackling code-switching in Indonesian poses a challenge due to the scarcity of paired code-switching data. Thus, this study endeavors to address Indonesian-English code-switching in speech recognition, leveraging unlabeled data and employing a semi-supervised technique known as the machine speech chain. Our findings demonstrate that the machine speech chain method effectively enhances Automatic Speech Recognition (ASR) performance in recognizing code-switching between Indonesian and English, utilizing previously untapped resources of unlabeled data.
%U https://aclanthology.org/2024.sigul-1.18/
%P 143-148
Markdown (Informal)
[Indonesian-English Code-Switching Speech Recognition Using the Machine Speech Chain Based Semi-Supervised Learning](https://aclanthology.org/2024.sigul-1.18/) (Tazakka et al., SIGUL 2024)
ACL