@inproceedings{popescu-etal-2026-added,
title = "The Added Value of Metadata and Annotations: Evidence from Two Large-Scale, Naturalistic Corpus Studies",
author = "Popescu, Anisia and
Cronenberg, Johanna and
Vasilescu, Ioana and
Chitoran, Ioana and
Lamel, Lori and
Adda-Decker, Martine",
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-1.455/",
doi = "10.63317/4c4triganae3",
pages = "5767--5775",
abstract = "This paper presents two case studies that highlight both the challenges and benefits of working with large-scale, naturalistic phonetic data. Our aim is to encourage researchers not to shy away from phonetic data found ``in the wild'', even when such data are messy, noisy, or incomplete {--} because they can yield robust, novel insights beyond the reach of controlled laboratory studies. We focus on challenges that are endemic to large corpora, including degraded audio quality, sparse or inconsistent annotations, and missing speaker metadata. By comparing two corpus-based studies that diverge in methodology and statistical design, we show how different approaches can mitigate these limitations while still extracting meaningful patterns."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popescu-etal-2026-added">
<titleInfo>
<title>The Added Value of Metadata and Annotations: Evidence from Two Large-Scale, Naturalistic Corpus Studies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anisia</namePart>
<namePart type="family">Popescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Cronenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Vasilescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Chitoran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lori</namePart>
<namePart type="family">Lamel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martine</namePart>
<namePart type="family">Adda-Decker</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 paper presents two case studies that highlight both the challenges and benefits of working with large-scale, naturalistic phonetic data. Our aim is to encourage researchers not to shy away from phonetic data found “in the wild”, even when such data are messy, noisy, or incomplete – because they can yield robust, novel insights beyond the reach of controlled laboratory studies. We focus on challenges that are endemic to large corpora, including degraded audio quality, sparse or inconsistent annotations, and missing speaker metadata. By comparing two corpus-based studies that diverge in methodology and statistical design, we show how different approaches can mitigate these limitations while still extracting meaningful patterns.</abstract>
<identifier type="citekey">popescu-etal-2026-added</identifier>
<identifier type="doi">10.63317/4c4triganae3</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.455/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5767</start>
<end>5775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Added Value of Metadata and Annotations: Evidence from Two Large-Scale, Naturalistic Corpus Studies
%A Popescu, Anisia
%A Cronenberg, Johanna
%A Vasilescu, Ioana
%A Chitoran, Ioana
%A Lamel, Lori
%A Adda-Decker, Martine
%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 popescu-etal-2026-added
%X This paper presents two case studies that highlight both the challenges and benefits of working with large-scale, naturalistic phonetic data. Our aim is to encourage researchers not to shy away from phonetic data found “in the wild”, even when such data are messy, noisy, or incomplete – because they can yield robust, novel insights beyond the reach of controlled laboratory studies. We focus on challenges that are endemic to large corpora, including degraded audio quality, sparse or inconsistent annotations, and missing speaker metadata. By comparing two corpus-based studies that diverge in methodology and statistical design, we show how different approaches can mitigate these limitations while still extracting meaningful patterns.
%R 10.63317/4c4triganae3
%U https://aclanthology.org/2026.lrec-1.455/
%U https://doi.org/10.63317/4c4triganae3
%P 5767-5775
Markdown (Informal)
[The Added Value of Metadata and Annotations: Evidence from Two Large-Scale, Naturalistic Corpus Studies](https://aclanthology.org/2026.lrec-1.455/) (Popescu et al., LREC 2026)
ACL