@inproceedings{zgank-etal-2026-developing,
title = "Developing Zila: A Spoken Language Resource for the Endangered {S}lovenian {G}ail Valley Dialect",
author = "Zgank, Andrej and
Donaj, Gregor and
Kolaric, Urh and
Sereinig, Usi and
Koren-Zwitter, Tatjana and
Boto, Sanja and
Zwitter-Grilc, Sabina and
Vidinic, Jasna and
Verdonik, Darinka",
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-1.262/",
doi = "10.63317/3fhhk948chhm",
pages = "3325--3332",
abstract = "Slovenian is a less-resourced South Slavic language. Existing Slovenian spoken language resources mainly cover the standard language in everyday communication. However, Slovenian encompasses a wide range of dialects, most of which are not represented in available spoken language resources. This paper presents the development of Zila, a Slovenian spoken language resource for the Gail Valley dialect. This dialect is one of the most endangered varieties of Slovenian and is spoken in the extreme north-western periphery of the Slovenian language area. The goal of the project was to build a language resource comprising 100 hours of speech with manually produced transcriptions. The spoken material was collected from members of the Slovenian minority in Carinthia, Austria, with the local community playing a key role in the data acquisition process. A dedicated set of transcription rules was created to capture the full range of acoustic and linguistic features of the Gail Valley dialect, which differs significantly from standard Slovenian. A preliminary speech recognition experiment was conducted to analyze these differences further. The Zila project demonstrates how spoken language technologies can help to preserve the cultural and linguistic heritage of an endangered dialect."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zgank-etal-2026-developing">
<titleInfo>
<title>Developing Zila: A Spoken Language Resource for the Endangered Slovenian Gail Valley Dialect</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrej</namePart>
<namePart type="family">Zgank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregor</namePart>
<namePart type="family">Donaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Urh</namePart>
<namePart type="family">Kolaric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usi</namePart>
<namePart type="family">Sereinig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatjana</namePart>
<namePart type="family">Koren-Zwitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Boto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabina</namePart>
<namePart type="family">Zwitter-Grilc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasna</namePart>
<namePart type="family">Vidinic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darinka</namePart>
<namePart type="family">Verdonik</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>Slovenian is a less-resourced South Slavic language. Existing Slovenian spoken language resources mainly cover the standard language in everyday communication. However, Slovenian encompasses a wide range of dialects, most of which are not represented in available spoken language resources. This paper presents the development of Zila, a Slovenian spoken language resource for the Gail Valley dialect. This dialect is one of the most endangered varieties of Slovenian and is spoken in the extreme north-western periphery of the Slovenian language area. The goal of the project was to build a language resource comprising 100 hours of speech with manually produced transcriptions. The spoken material was collected from members of the Slovenian minority in Carinthia, Austria, with the local community playing a key role in the data acquisition process. A dedicated set of transcription rules was created to capture the full range of acoustic and linguistic features of the Gail Valley dialect, which differs significantly from standard Slovenian. A preliminary speech recognition experiment was conducted to analyze these differences further. The Zila project demonstrates how spoken language technologies can help to preserve the cultural and linguistic heritage of an endangered dialect.</abstract>
<identifier type="citekey">zgank-etal-2026-developing</identifier>
<identifier type="doi">10.63317/3fhhk948chhm</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.262/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3325</start>
<end>3332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing Zila: A Spoken Language Resource for the Endangered Slovenian Gail Valley Dialect
%A Zgank, Andrej
%A Donaj, Gregor
%A Kolaric, Urh
%A Sereinig, Usi
%A Koren-Zwitter, Tatjana
%A Boto, Sanja
%A Zwitter-Grilc, Sabina
%A Vidinic, Jasna
%A Verdonik, Darinka
%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 zgank-etal-2026-developing
%X Slovenian is a less-resourced South Slavic language. Existing Slovenian spoken language resources mainly cover the standard language in everyday communication. However, Slovenian encompasses a wide range of dialects, most of which are not represented in available spoken language resources. This paper presents the development of Zila, a Slovenian spoken language resource for the Gail Valley dialect. This dialect is one of the most endangered varieties of Slovenian and is spoken in the extreme north-western periphery of the Slovenian language area. The goal of the project was to build a language resource comprising 100 hours of speech with manually produced transcriptions. The spoken material was collected from members of the Slovenian minority in Carinthia, Austria, with the local community playing a key role in the data acquisition process. A dedicated set of transcription rules was created to capture the full range of acoustic and linguistic features of the Gail Valley dialect, which differs significantly from standard Slovenian. A preliminary speech recognition experiment was conducted to analyze these differences further. The Zila project demonstrates how spoken language technologies can help to preserve the cultural and linguistic heritage of an endangered dialect.
%R 10.63317/3fhhk948chhm
%U https://aclanthology.org/2026.lrec-1.262/
%U https://doi.org/10.63317/3fhhk948chhm
%P 3325-3332
Markdown (Informal)
[Developing Zila: A Spoken Language Resource for the Endangered Slovenian Gail Valley Dialect](https://aclanthology.org/2026.lrec-1.262/) (Zgank et al., LREC 2026)
ACL
- Andrej Zgank, Gregor Donaj, Urh Kolaric, Usi Sereinig, Tatjana Koren-Zwitter, Sanja Boto, Sabina Zwitter-Grilc, Jasna Vidinic, and Darinka Verdonik. 2026. Developing Zila: A Spoken Language Resource for the Endangered Slovenian Gail Valley Dialect. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3325–3332, Palma de Mallorca, Spain. ELRA Language Resource Association.