<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdjul-etal-2025-indonesian">
    <titleInfo>
        <title>Indonesian Speech Content De-Identification in Low Resource Transcripts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rifqi</namePart>
        <namePart type="given">Naufal</namePart>
        <namePart type="family">Abdjul</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dessi</namePart>
        <namePart type="family">Puji Lestari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ayu</namePart>
        <namePart type="family">Purwarianti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Candy</namePart>
        <namePart type="given">Olivia</namePart>
        <namePart type="family">Mawalim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sakriani</namePart>
        <namePart type="family">Sakti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masashi</namePart>
        <namePart type="family">Unoki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop in South East Asian Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Derry</namePart>
            <namePart type="family">Wijaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alham</namePart>
            <namePart type="given">Fikri</namePart>
            <namePart type="family">Aji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Clara</namePart>
            <namePart type="family">Vania</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Genta</namePart>
            <namePart type="given">Indra</namePart>
            <namePart type="family">Winata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Advancements in technology and the increased use of digital data threaten individual privacy, especially in speech containing Personally Identifiable Information (PII). Therefore, systems that can remove or process privacy-sensitive data in speech are needed, particularly for low-resource transcripts. These transcripts are minimally annotated or labeled automatically, which is less precise than human annotation. However, using them can simplify the development of de-identification systems in any language. In this study, we develop and evaluate an efficient speech de-identification system. We create an Indonesian speech dataset containing sensitive private information and design a system with three main components: speech recognition, information extraction, and masking. To enhance performance in low-resource settings, we incorporate transcription data in training, use data augmentation, and apply weakly supervised learning. Our results show that our techniques significantly improve privacy detection performance, with approximately 29% increase in F1 score, 20% in precision, and 30% in recall with minimally labeled data.</abstract>
    <identifier type="citekey">abdjul-etal-2025-indonesian</identifier>
    <location>
        <url>https://aclanthology.org/2025.sealp-1.6/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>63</start>
            <end>71</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Indonesian Speech Content De-Identification in Low Resource Transcripts
%A Abdjul, Rifqi Naufal
%A Puji Lestari, Dessi
%A Purwarianti, Ayu
%A Mawalim, Candy Olivia
%A Sakti, Sakriani
%A Unoki, Masashi
%Y Wijaya, Derry
%Y Aji, Alham Fikri
%Y Vania, Clara
%Y Winata, Genta Indra
%Y Purwarianti, Ayu
%S Proceedings of the Second Workshop in South East Asian Language Processing
%D 2025
%8 January
%I Association for Computational Linguistics
%C Online
%F abdjul-etal-2025-indonesian
%X Advancements in technology and the increased use of digital data threaten individual privacy, especially in speech containing Personally Identifiable Information (PII). Therefore, systems that can remove or process privacy-sensitive data in speech are needed, particularly for low-resource transcripts. These transcripts are minimally annotated or labeled automatically, which is less precise than human annotation. However, using them can simplify the development of de-identification systems in any language. In this study, we develop and evaluate an efficient speech de-identification system. We create an Indonesian speech dataset containing sensitive private information and design a system with three main components: speech recognition, information extraction, and masking. To enhance performance in low-resource settings, we incorporate transcription data in training, use data augmentation, and apply weakly supervised learning. Our results show that our techniques significantly improve privacy detection performance, with approximately 29% increase in F1 score, 20% in precision, and 30% in recall with minimally labeled data.
%U https://aclanthology.org/2025.sealp-1.6/
%P 63-71

Markdown (Informal)

[Indonesian Speech Content De-Identification in Low Resource Transcripts](https://aclanthology.org/2025.sealp-1.6/) (Abdjul et al., sealp 2025)

• Indonesian Speech Content De-Identification in Low Resource Transcripts (Abdjul et al., sealp 2025)

ACL

• Rifqi Naufal Abdjul, Dessi Puji Lestari, Ayu Purwarianti, Candy Olivia Mawalim, Sakriani Sakti, and Masashi Unoki. 2025. Indonesian Speech Content De-Identification in Low Resource Transcripts. In Proceedings of the Second Workshop in South East Asian Language Processing, pages 63–71, Online. Association for Computational Linguistics.