<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pendevska-nastevska-2026-digital">
    <titleInfo>
        <title>Digital Preservation of Aromanian Through Knowledge Management and Automatic Speech Recognition Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marija</namePart>
        <namePart type="family">Pendevska</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hristina</namePart>
        <namePart type="family">Nastevska</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 First Workshop on Dialects in NLP — A Resource Perspective</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Antonis</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stella</namePart>
            <namePart type="family">Markantonatou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angela</namePart>
            <namePart type="family">Ralli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stavros</namePart>
            <namePart type="family">Bompolas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivian</namePart>
            <namePart type="family">Stamou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents a knowledge management framework for the digital preservation of Aromanian, an endangered Eastern Romance language spoken across the Balkans, combined with the first systematic evaluation of automatic speech recognition (ASR) models on Aromanian dialectal speech. The proposed three-module framework encompasses localization of existing resources, distribution through digital platforms, and creation of new linguistic content through technological innovation. Empirical analysis of knowledge management practices among 176 respondents validates the framework design, revealing that information quality (28.3%) and personal utility (24.1%) are the most valued criteria for knowledge sharing, while digital information seeking (27.1%) is the dominant behaviour. Within this framework, we evaluate models from the OpenAI Whisper family across three sizes (medium, large-v2, large-v3) and multiple language settings on two Aromanian varieties: Gramosteanj and Crushova. All configurations yield word error rates (WER) above 88%, with character error rates (CER) as low as 34% under optimal conditions, indicating partial phonotactic capture despite word-level failure. The Latin language setting with large-v3 consistently achieves the best results. Romanization of non-Latin script output substantially reduces CER, confirming script mismatch as a major error source. These findings underscore the limitations of current pretrained ASR models for endangered languages and the need for dedicated resources and adaptation strategies within a broader language preservation framework</abstract>
    <identifier type="citekey">pendevska-nastevska-2026-digital</identifier>
    <identifier type="doi">10.63317/34e4awcc69g4</identifier>
    <location>
        <url>https://aclanthology.org/2026.dialres-1.32/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>327</start>
            <end>336</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Digital Preservation of Aromanian Through Knowledge Management and Automatic Speech Recognition Evaluation
%A Pendevska, Marija
%A Nastevska, Hristina
%Y Anastasopoulos, Antonis
%Y Markantonatou, Stella
%Y Ralli, Angela
%Y Zampieri, Marcos
%Y Bompolas, Stavros
%Y Stamou, Vivian
%S Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca
%F pendevska-nastevska-2026-digital
%X This paper presents a knowledge management framework for the digital preservation of Aromanian, an endangered Eastern Romance language spoken across the Balkans, combined with the first systematic evaluation of automatic speech recognition (ASR) models on Aromanian dialectal speech. The proposed three-module framework encompasses localization of existing resources, distribution through digital platforms, and creation of new linguistic content through technological innovation. Empirical analysis of knowledge management practices among 176 respondents validates the framework design, revealing that information quality (28.3%) and personal utility (24.1%) are the most valued criteria for knowledge sharing, while digital information seeking (27.1%) is the dominant behaviour. Within this framework, we evaluate models from the OpenAI Whisper family across three sizes (medium, large-v2, large-v3) and multiple language settings on two Aromanian varieties: Gramosteanj and Crushova. All configurations yield word error rates (WER) above 88%, with character error rates (CER) as low as 34% under optimal conditions, indicating partial phonotactic capture despite word-level failure. The Latin language setting with large-v3 consistently achieves the best results. Romanization of non-Latin script output substantially reduces CER, confirming script mismatch as a major error source. These findings underscore the limitations of current pretrained ASR models for endangered languages and the need for dedicated resources and adaptation strategies within a broader language preservation framework
%R 10.63317/34e4awcc69g4
%U https://aclanthology.org/2026.dialres-1.32/
%U https://doi.org/10.63317/34e4awcc69g4
%P 327-336

Markdown (Informal)

[Digital Preservation of Aromanian Through Knowledge Management and Automatic Speech Recognition Evaluation](https://aclanthology.org/2026.dialres-1.32/) (Pendevska & Nastevska, DialRes 2026)

• Digital Preservation of Aromanian Through Knowledge Management and Automatic Speech Recognition Evaluation (Pendevska & Nastevska, DialRes 2026)

ACL

• Marija Pendevska and Hristina Nastevska. 2026. Digital Preservation of Aromanian Through Knowledge Management and Automatic Speech Recognition Evaluation. In Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective, pages 327–336, Palma de Mallorca. Association for Computational Linguistics.