Whisper Finetuning For Hakka Recognition in Low Resource

Min Han Teng; Ci Dao Chen; You Ting Lin; Bing-Jhih Huang

Whisper Finetuning For Hakka Recognition in Low Resource

Min Han Teng, Ci Dao Chen, You Ting Lin, Bing Jhih Huang

Correct Metadata for

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>.

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 PDF.)

Authors concatenated from the text boxes above:

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

Abstract

We study automatic speech recognition (ASR) for Hakka, a low-resource language with substantial dialectal variation. Focusing on Zhaoan and Dapu, we fine-tune Whisper using Low-Rank Adaptation (LoRA) and apply data augmentation to mitigate data scarcity. Experiments show that LoRA combined with augmentation substantially improves cross-dialect recognition while maintaining parameter efficiency. Our results demonstrate the potential of lightweight adaptation to extend large-scale ASR systems to underrepresented languages, supporting the preservation of Hakka speech and orthography.

Anthology ID:: 2025.rocling-main.52
Volume:: Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
Month:: November
Year:: 2025
Address:: National Taiwan University, Taipei City, Taiwan
Editors:: Kai-Wei Chang, Ke-Han Lu, Chih-Kai Yang, Zhi-Rui Tam, Wen-Yu Chang, Chung-Che Wang
Venue:: ROCLING
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 450–453
Language:
URL:: https://aclanthology.org/2025.rocling-main.52/
DOI:
Bibkey:
Cite (ACL):: Min Han Teng, Ci Dao Chen, You Ting Lin, and Bing Jhih Huang. 2025. Whisper Finetuning For Hakka Recognition in Low Resource. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 450–453, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.
Cite (Informal):: Whisper Finetuning For Hakka Recognition in Low Resource (Teng et al., ROCLING 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.rocling-main.52.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{teng-etal-2025-whisper,
    title = "Whisper Finetuning For {H}akka Recognition in Low Resource",
    author = "Teng, Min Han  and
      Chen, Ci Dao  and
      Lin, You Ting  and
      Huang, Bing Jhih",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.rocling-main.52/",
    pages = "450--453",
    ISBN = "979-8-89176-379-1",
    abstract = "We study automatic speech recognition (ASR) for Hakka, a low-resource language with substantial dialectal variation. Focusing on Zhaoan and Dapu, we fine-tune Whisper using Low-Rank Adaptation (LoRA) and apply data augmentation to mitigate data scarcity. Experiments show that LoRA combined with augmentation substantially improves cross-dialect recognition while maintaining parameter efficiency. Our results demonstrate the potential of lightweight adaptation to extend large-scale ASR systems to underrepresented languages, supporting the preservation of Hakka speech and orthography."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="teng-etal-2025-whisper">
    <titleInfo>
        <title>Whisper Finetuning For Hakka Recognition in Low Resource</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="given">Han</namePart>
        <namePart type="family">Teng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ci</namePart>
        <namePart type="given">Dao</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">You</namePart>
        <namePart type="given">Ting</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bing</namePart>
        <namePart type="given">Jhih</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kai-Wei</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ke-Han</namePart>
            <namePart type="family">Lu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chih-Kai</namePart>
            <namePart type="family">Yang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zhi-Rui</namePart>
            <namePart type="family">Tam</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wen-Yu</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Che</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">National Taiwan University, Taipei City, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-379-1</identifier>
    </relatedItem>
    <abstract>We study automatic speech recognition (ASR) for Hakka, a low-resource language with substantial dialectal variation. Focusing on Zhaoan and Dapu, we fine-tune Whisper using Low-Rank Adaptation (LoRA) and apply data augmentation to mitigate data scarcity. Experiments show that LoRA combined with augmentation substantially improves cross-dialect recognition while maintaining parameter efficiency. Our results demonstrate the potential of lightweight adaptation to extend large-scale ASR systems to underrepresented languages, supporting the preservation of Hakka speech and orthography.</abstract>
    <identifier type="citekey">teng-etal-2025-whisper</identifier>
    <location>
        <url>https://aclanthology.org/2025.rocling-main.52/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>450</start>
            <end>453</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Whisper Finetuning For Hakka Recognition in Low Resource
%A Teng, Min Han
%A Chen, Ci Dao
%A Lin, You Ting
%A Huang, Bing Jhih
%Y Chang, Kai-Wei
%Y Lu, Ke-Han
%Y Yang, Chih-Kai
%Y Tam, Zhi-Rui
%Y Chang, Wen-Yu
%Y Wang, Chung-Che
%S Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C National Taiwan University, Taipei City, Taiwan
%@ 979-8-89176-379-1
%F teng-etal-2025-whisper
%X We study automatic speech recognition (ASR) for Hakka, a low-resource language with substantial dialectal variation. Focusing on Zhaoan and Dapu, we fine-tune Whisper using Low-Rank Adaptation (LoRA) and apply data augmentation to mitigate data scarcity. Experiments show that LoRA combined with augmentation substantially improves cross-dialect recognition while maintaining parameter efficiency. Our results demonstrate the potential of lightweight adaptation to extend large-scale ASR systems to underrepresented languages, supporting the preservation of Hakka speech and orthography.
%U https://aclanthology.org/2025.rocling-main.52/
%P 450-453

Download as File

Markdown (Informal)

[Whisper Finetuning For Hakka Recognition in Low Resource](https://aclanthology.org/2025.rocling-main.52/) (Teng et al., ROCLING 2025)

Whisper Finetuning For Hakka Recognition in Low Resource (Teng et al., ROCLING 2025)

ACL

Min Han Teng, Ci Dao Chen, You Ting Lin, and Bing Jhih Huang. 2025. Whisper Finetuning For Hakka Recognition in Low Resource. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 450–453, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.