@inproceedings{yan-etal-2026-cs,
title = "{CS}-{YODAS}: A Mined Dataset of In-the-Wild Code-Switched Speech",
author = "Yan, Brian and
Wang, Qingzheng and
Wiesner, Matthew and
Diwan, Anuj and
Iakovenko, Olga and
Polok, Alex and
Hamed, Injy and
Shimizu, Shuichiro and
Emerman, Iris and
Hain, Thomas and
Mortensen, David R. and
Viechnicki, Peter and
Watanabe, Shinji",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.456/",
doi = "10.63317/3fir5kp98qyt",
pages = "5776--5784",
abstract = "We present CS-YODAS, a Creative Commons dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching, or the alternation between languages within an utterance or conversation, is common in multilingual settings but remains underrepresented in existing CS speech resources, which are typically small, domain-specific, or artificially constructed. Building on the YODAS corpus, we develop a scalable, human-in-the-loop pipeline for identifying and validating naturally occurring code-switching. The resulting dataset, which totals 313 hrs and spans 7 matrix languages, provides diverse, real-world examples of spontaneous code-switched speech. We further analyze the distribution and characteristics of code-switching in the wild, examining language-pair frequencies and switching patterns, and report baseline results for spoken language identification. We hope that CS-YODAS will encourage broader and more comprehensive research on code-switched speech. Dataset link: \url{https://huggingface.co/datasets/byan/cs-yodas}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2026-cs">
<titleInfo>
<title>CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingzheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Wiesner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Diwan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Iakovenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Polok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuichiro</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Emerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Hain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Mortensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Viechnicki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present CS-YODAS, a Creative Commons dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching, or the alternation between languages within an utterance or conversation, is common in multilingual settings but remains underrepresented in existing CS speech resources, which are typically small, domain-specific, or artificially constructed. Building on the YODAS corpus, we develop a scalable, human-in-the-loop pipeline for identifying and validating naturally occurring code-switching. The resulting dataset, which totals 313 hrs and spans 7 matrix languages, provides diverse, real-world examples of spontaneous code-switched speech. We further analyze the distribution and characteristics of code-switching in the wild, examining language-pair frequencies and switching patterns, and report baseline results for spoken language identification. We hope that CS-YODAS will encourage broader and more comprehensive research on code-switched speech. Dataset link: https://huggingface.co/datasets/byan/cs-yodas.</abstract>
<identifier type="citekey">yan-etal-2026-cs</identifier>
<identifier type="doi">10.63317/3fir5kp98qyt</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.456/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5776</start>
<end>5784</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech
%A Yan, Brian
%A Wang, Qingzheng
%A Wiesner, Matthew
%A Diwan, Anuj
%A Iakovenko, Olga
%A Polok, Alex
%A Hamed, Injy
%A Shimizu, Shuichiro
%A Emerman, Iris
%A Hain, Thomas
%A Mortensen, David R.
%A Viechnicki, Peter
%A Watanabe, Shinji
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F yan-etal-2026-cs
%X We present CS-YODAS, a Creative Commons dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching, or the alternation between languages within an utterance or conversation, is common in multilingual settings but remains underrepresented in existing CS speech resources, which are typically small, domain-specific, or artificially constructed. Building on the YODAS corpus, we develop a scalable, human-in-the-loop pipeline for identifying and validating naturally occurring code-switching. The resulting dataset, which totals 313 hrs and spans 7 matrix languages, provides diverse, real-world examples of spontaneous code-switched speech. We further analyze the distribution and characteristics of code-switching in the wild, examining language-pair frequencies and switching patterns, and report baseline results for spoken language identification. We hope that CS-YODAS will encourage broader and more comprehensive research on code-switched speech. Dataset link: https://huggingface.co/datasets/byan/cs-yodas.
%R 10.63317/3fir5kp98qyt
%U https://aclanthology.org/2026.lrec-1.456/
%U https://doi.org/10.63317/3fir5kp98qyt
%P 5776-5784
Markdown (Informal)
[CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech](https://aclanthology.org/2026.lrec-1.456/) (Yan et al., LREC 2026)
ACL
- Brian Yan, Qingzheng Wang, Matthew Wiesner, Anuj Diwan, Olga Iakovenko, Alex Polok, Injy Hamed, Shuichiro Shimizu, Iris Emerman, Thomas Hain, David R. Mortensen, Peter Viechnicki, and Shinji Watanabe. 2026. CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5776–5784, Palma de Mallorca, Spain. ELRA Language Resource Association.