<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2026-adidhwani">
    <titleInfo>
        <title>AdiDhwani: Preservation-Oriented ASR for Endangered Bhili and Mundari Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pooja</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">M</namePart>
        <namePart type="given">Kaab</namePart>
        <namePart type="given">Bin</namePart>
        <namePart type="family">Shahid</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sandeep</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>India’s tribal (*Janjatiya/Adivasi*) languages remain absent from public ASR evaluation, despite their importance for oral history, ecological knowledge, and cultural continuity. We present **AdiDhwani**, a preservation-oriented ASR benchmark for **Bhili** (ISO 639-3: ‘bhb‘), India’s largest non-scheduled language, and **Mundari** (ISO 639-3: ‘unr‘), a Vulnerable North Munda language. The benchmark comprises 56.5 hours of community-validated Bhili speech and 11.7 hours of Mundari speech with fixed evaluation splits and reproducible baselines. We evaluate multilingual ASR under zero-shot transfer, target-language fine-tuning, donor-language initialization, synthetic supervision, and KenLM-assisted decoding. Target-language supervision substantially improves WER, yet lower edit distance does not always reflect better documentation fidelity: models replace attested Bhili forms with Hindi cognates or delete grammatically meaningful Mundari suffixes while still achieving competitive scores. We introduce **Hindi-Normalization Bias (HNB)** and its alignment-constrained variant **(HNBA)**, **Morphological Fragmentation Rate (MFR)**, and **Suffix Deletion Rate (SDR)** as preservation-oriented diagnostics beyond WER. Human transcriber baselines show that these gaps are not fixed limits. **AdiDhwani** provides the first controlled ASR evaluation framework for these two under-documented Indian languages and supports language-preserving speech recognition research in endangered-language settings.</abstract>
    <identifier type="citekey">singh-etal-2026-adidhwani</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1707/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>38870</start>
            <end>38910</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AdiDhwani: Preservation-Oriented ASR for Endangered Bhili and Mundari Languages
%A Singh, Pooja
%A Shahid, M. Kaab Bin
%A Kumar, Sandeep
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F singh-etal-2026-adidhwani
%X India’s tribal (*Janjatiya/Adivasi*) languages remain absent from public ASR evaluation, despite their importance for oral history, ecological knowledge, and cultural continuity. We present **AdiDhwani**, a preservation-oriented ASR benchmark for **Bhili** (ISO 639-3: ‘bhb‘), India’s largest non-scheduled language, and **Mundari** (ISO 639-3: ‘unr‘), a Vulnerable North Munda language. The benchmark comprises 56.5 hours of community-validated Bhili speech and 11.7 hours of Mundari speech with fixed evaluation splits and reproducible baselines. We evaluate multilingual ASR under zero-shot transfer, target-language fine-tuning, donor-language initialization, synthetic supervision, and KenLM-assisted decoding. Target-language supervision substantially improves WER, yet lower edit distance does not always reflect better documentation fidelity: models replace attested Bhili forms with Hindi cognates or delete grammatically meaningful Mundari suffixes while still achieving competitive scores. We introduce **Hindi-Normalization Bias (HNB)** and its alignment-constrained variant **(HNBA)**, **Morphological Fragmentation Rate (MFR)**, and **Suffix Deletion Rate (SDR)** as preservation-oriented diagnostics beyond WER. Human transcriber baselines show that these gaps are not fixed limits. **AdiDhwani** provides the first controlled ASR evaluation framework for these two under-documented Indian languages and supports language-preserving speech recognition research in endangered-language settings.
%U https://aclanthology.org/2026.emnlp-main.1707/
%P 38870-38910

Markdown (Informal)

[AdiDhwani: Preservation-Oriented ASR for Endangered Bhili and Mundari Languages](https://aclanthology.org/2026.emnlp-main.1707/) (Singh et al., EMNLP 2026)

• AdiDhwani: Preservation-Oriented ASR for Endangered Bhili and Mundari Languages (Singh et al., EMNLP 2026)

ACL

• Pooja Singh, M Kaab Bin Shahid, and Sandeep Kumar. 2026. AdiDhwani: Preservation-Oriented ASR for Endangered Bhili and Mundari Languages. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 38870–38910, Budapest, Hungary. Association for Computational Linguistics.