Southern Kurdish Speech Recognition Resources and Benchmarking

Mohammad Mohammadamini; Marie Tahon

doi:10.63317/2rkqhw7hmo2d

Southern Kurdish Speech Recognition Resources and Benchmarking

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

This article introduces a dedicated speech recognition dataset for Southern Kurdish, which is a threatened variant of Kurdish macrolanguage. We present 30 hours of validated read speech for training and an evaluation benchmark for Southern Kurdish Automatic Speech Recognition (ASR). Both the training data and evaluation benchmark are read speech recorded by crowdsourcing campaigns. Besides a detailed description of the provided resources, we provide the ASR baselines using Whisper-turbo and wav2vec-bert CTC architectures. We achieved a 4.09 CER and 24.26 WER on our benchmark using wav2vec-bert model. We also provide a categorization of errors to support further improvements in future studies.The resources and trained models are released under the CC BY-NC-ND 4.0 license and are publicly available at https://huggingface.co/datasets/aranemini/southern-kurdish-asr

Anthology ID:: 2026.lrec-1.432
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 5538–5544
Language:
External URL:: https://lrec.elra.info/lrec2026-main-432
DOI:: 10.63317/2rkqhw7hmo2d
Bibkey:
Cite (ACL):: Mohammad Mohammadamini and Marie Tahon. 2026. Southern Kurdish Speech Recognition Resources and Benchmarking. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5538–5544, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: Southern Kurdish Speech Recognition Resources and Benchmarking (Mohammadamini & Tahon, LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{mohammadamini-tahon-2026-southern,
    title = "{S}outhern {K}urdish Speech Recognition Resources and Benchmarking",
    author = "Mohammadamini, Mohammad  and
      Tahon, Marie",
    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-1.432/",
    doi = "10.63317/2rkqhw7hmo2d",
    pages = "5538--5544",
    abstract = "This article introduces a dedicated speech recognition dataset for Southern Kurdish, which is a threatened variant of Kurdish macrolanguage. We present 30 hours of validated read speech for training and an evaluation benchmark for Southern Kurdish Automatic Speech Recognition (ASR). Both the training data and evaluation benchmark are read speech recorded by crowdsourcing campaigns. Besides a detailed description of the provided resources, we provide the ASR baselines using Whisper-turbo and wav2vec-bert CTC architectures. We achieved a 4.09 CER and 24.26 WER on our benchmark using wav2vec-bert model. We also provide a categorization of errors to support further improvements in future studies.The resources and trained models are released under the CC BY-NC-ND 4.0 license and are publicly available at \url{https://huggingface.co/datasets/aranemini/southern-kurdish-asr}"
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammadamini-tahon-2026-southern">
    <titleInfo>
        <title>Southern Kurdish Speech Recognition Resources and Benchmarking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">Mohammadamini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marie</namePart>
        <namePart type="family">Tahon</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>This article introduces a dedicated speech recognition dataset for Southern Kurdish, which is a threatened variant of Kurdish macrolanguage. We present 30 hours of validated read speech for training and an evaluation benchmark for Southern Kurdish Automatic Speech Recognition (ASR). Both the training data and evaluation benchmark are read speech recorded by crowdsourcing campaigns. Besides a detailed description of the provided resources, we provide the ASR baselines using Whisper-turbo and wav2vec-bert CTC architectures. We achieved a 4.09 CER and 24.26 WER on our benchmark using wav2vec-bert model. We also provide a categorization of errors to support further improvements in future studies.The resources and trained models are released under the CC BY-NC-ND 4.0 license and are publicly available at https://huggingface.co/datasets/aranemini/southern-kurdish-asr</abstract>
    <identifier type="citekey">mohammadamini-tahon-2026-southern</identifier>
    <identifier type="doi">10.63317/2rkqhw7hmo2d</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.432/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>5538</start>
            <end>5544</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Southern Kurdish Speech Recognition Resources and Benchmarking
%A Mohammadamini, Mohammad
%A Tahon, Marie
%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 mohammadamini-tahon-2026-southern
%X This article introduces a dedicated speech recognition dataset for Southern Kurdish, which is a threatened variant of Kurdish macrolanguage. We present 30 hours of validated read speech for training and an evaluation benchmark for Southern Kurdish Automatic Speech Recognition (ASR). Both the training data and evaluation benchmark are read speech recorded by crowdsourcing campaigns. Besides a detailed description of the provided resources, we provide the ASR baselines using Whisper-turbo and wav2vec-bert CTC architectures. We achieved a 4.09 CER and 24.26 WER on our benchmark using wav2vec-bert model. We also provide a categorization of errors to support further improvements in future studies.The resources and trained models are released under the CC BY-NC-ND 4.0 license and are publicly available at https://huggingface.co/datasets/aranemini/southern-kurdish-asr
%R 10.63317/2rkqhw7hmo2d
%U https://aclanthology.org/2026.lrec-1.432/
%U https://doi.org/10.63317/2rkqhw7hmo2d
%P 5538-5544

Download as File

Markdown (Informal)

[Southern Kurdish Speech Recognition Resources and Benchmarking](https://aclanthology.org/2026.lrec-1.432/) (Mohammadamini & Tahon, LREC 2026)

Southern Kurdish Speech Recognition Resources and Benchmarking (Mohammadamini & Tahon, LREC 2026)

ACL

Mohammad Mohammadamini and Marie Tahon. 2026. Southern Kurdish Speech Recognition Resources and Benchmarking. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5538–5544, Palma de Mallorca, Spain. ELRA Language Resource Association.