@inproceedings{nowenstein-etal-2026-icelandic,
title = "The {I}celandic Language Biobank: Data Collection through a Clinical Analysis Platform",
author = {Nowenstein, Iris and
N{\'u}{\~n}ez Mac{\'i}as, Naizeth and
{\"O}rn{\'o}lfsson, Gunnar Thor and
{\'O}lafsson, Stef{\'a}n and
Berg{\th}{\'o}rsd{\'o}ttir, Brynd{\'i}s and
Krist{\'i}nard{\'o}ttir, I{\dh}unn and
Hafsteinsson, Hinrik},
editor = {Kokkinakis, Dimitrios and
Themistocleous, Charalambos and
Dias, Ga{\"e}l and
Fraser, Kathleen C. and
{\"O}hman, Fredrik and
Pais, Sebasti{\~a}o},
booktitle = "Proceedings of the Sixth Resources and {P}rocess{I}ng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the {MENTAL}.ai consortium",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.rapid-1.2/",
doi = "10.63317/56ceuachi82w",
pages = "13--23",
abstract = "Recent work on clinical applications of language technology shows considerable potential for people with speech and language symptoms and disorders, including for the diagnosis and monitoring of diseases and disorders as well as the development of novel communication aids. This has resulted in a variety of digital health tools becoming accessible, including personalized automatic speech recognition for disordered speech and the monitoring of disease progression in neurodegeneration through language samples. Currently, these tools are almost exclusively accessible to speakers of high-resource languages. A major hurdle for small, lower-resourced language communities in this context is the creation of clinical language corpora. We describe ongoing efforts to build the necessary infrastructure for clinical speech and language data collection in Iceland through the Icelandic Language Biobank, a resource that leverages collaboration with clinicians and robust linguistically-informed data collection against data scarcity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nowenstein-etal-2026-icelandic">
<titleInfo>
<title>The Icelandic Language Biobank: Data Collection through a Clinical Analysis Platform</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Nowenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naizeth</namePart>
<namePart type="family">Núñez Macías</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunnar</namePart>
<namePart type="given">Thor</namePart>
<namePart type="family">Örnólfsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefán</namePart>
<namePart type="family">Ólafsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryndís</namePart>
<namePart type="family">Berg\thórsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">I\dhunn</namePart>
<namePart type="family">Kristínardóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrik</namePart>
<namePart type="family">Hafsteinsson</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 Sixth Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the MENTAL.ai consortium</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Kokkinakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charalambos</namePart>
<namePart type="family">Themistocleous</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaël</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fredrik</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastião</namePart>
<namePart type="family">Pais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work on clinical applications of language technology shows considerable potential for people with speech and language symptoms and disorders, including for the diagnosis and monitoring of diseases and disorders as well as the development of novel communication aids. This has resulted in a variety of digital health tools becoming accessible, including personalized automatic speech recognition for disordered speech and the monitoring of disease progression in neurodegeneration through language samples. Currently, these tools are almost exclusively accessible to speakers of high-resource languages. A major hurdle for small, lower-resourced language communities in this context is the creation of clinical language corpora. We describe ongoing efforts to build the necessary infrastructure for clinical speech and language data collection in Iceland through the Icelandic Language Biobank, a resource that leverages collaboration with clinicians and robust linguistically-informed data collection against data scarcity.</abstract>
<identifier type="citekey">nowenstein-etal-2026-icelandic</identifier>
<identifier type="doi">10.63317/56ceuachi82w</identifier>
<location>
<url>https://aclanthology.org/2026.rapid-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>13</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Icelandic Language Biobank: Data Collection through a Clinical Analysis Platform
%A Nowenstein, Iris
%A Núñez Macías, Naizeth
%A Örnólfsson, Gunnar Thor
%A Ólafsson, Stefán
%A Berg\thórsdóttir, Bryndís
%A Kristínardóttir, I\dhunn
%A Hafsteinsson, Hinrik
%Y Kokkinakis, Dimitrios
%Y Themistocleous, Charalambos
%Y Dias, Gaël
%Y Fraser, Kathleen C.
%Y Öhman, Fredrik
%Y Pais, Sebastião
%S Proceedings of the Sixth Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the MENTAL.ai consortium
%D 2026
%8 May
%I European Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F nowenstein-etal-2026-icelandic
%X Recent work on clinical applications of language technology shows considerable potential for people with speech and language symptoms and disorders, including for the diagnosis and monitoring of diseases and disorders as well as the development of novel communication aids. This has resulted in a variety of digital health tools becoming accessible, including personalized automatic speech recognition for disordered speech and the monitoring of disease progression in neurodegeneration through language samples. Currently, these tools are almost exclusively accessible to speakers of high-resource languages. A major hurdle for small, lower-resourced language communities in this context is the creation of clinical language corpora. We describe ongoing efforts to build the necessary infrastructure for clinical speech and language data collection in Iceland through the Icelandic Language Biobank, a resource that leverages collaboration with clinicians and robust linguistically-informed data collection against data scarcity.
%R 10.63317/56ceuachi82w
%U https://aclanthology.org/2026.rapid-1.2/
%U https://doi.org/10.63317/56ceuachi82w
%P 13-23
Markdown (Informal)
[The Icelandic Language Biobank: Data Collection through a Clinical Analysis Platform](https://aclanthology.org/2026.rapid-1.2/) (Nowenstein et al., RaPID 2026)
ACL
- Iris Nowenstein, Naizeth Núñez Macías, Gunnar Thor Örnólfsson, Stefán Ólafsson, Bryndís Bergþórsdóttir, Iðunn Kristínardóttir, and Hinrik Hafsteinsson. 2026. The Icelandic Language Biobank: Data Collection through a Clinical Analysis Platform. In Proceedings of the Sixth Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the MENTAL.ai consortium, pages 13–23, Palma, Mallorca, Spain. European Language Resources Association (ELRA).