@inproceedings{ljubesic-etal-2026-parlaspeech,
title = "{P}arla{S}peech 3.0: Richly Annotated Spoken Parliamentary Corpora of {C}roatian, {C}zech, {P}olish, and {S}erbian",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Rupnik, Peter and
Porupski, Ivan and
Kuzman Punger{\v{s}}ek, Taja",
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-1.447/",
doi = "10.63317/3b7dnbjr75es",
pages = "5677--5688",
abstract = "ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages {--} Croatian, Czech, Polish and Serbian {--} with a total size of more than 6 thousand hours. The corpora were built in an automatic fashion from the ParlaMint transcripts and their corresponding metadata, which were aligned to the speech recordings of each corresponding parliament. In this release of the dataset, each of the corpora has been significantly enriched with several automatic annotation layers. The textual modality of all four corpora has been enriched with linguistic annotations and sentiment predictions. Similarly, their spoken modality has been automatically enriched with occurrences of filled pauses, the most frequent type of disfluency in typical speech. Two languages have been additionally enriched with detailed word- and grapheme-level alignments, and the automatic annotation of the position of primary stress in multisyllabic words. With these enrichments, the usefulness of the corpora has been greatly increased for downstream research across multiple disciplines, which we showcase through an analysis of acoustic correlates of sentiment. All the corpora are made available for download in JSONL and TextGrid formats, as well as for search through a concordancer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2026-parlaspeech">
<titleInfo>
<title>ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Rupnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Porupski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taja</namePart>
<namePart type="family">Kuzman Pungeršek</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>ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages – Croatian, Czech, Polish and Serbian – with a total size of more than 6 thousand hours. The corpora were built in an automatic fashion from the ParlaMint transcripts and their corresponding metadata, which were aligned to the speech recordings of each corresponding parliament. In this release of the dataset, each of the corpora has been significantly enriched with several automatic annotation layers. The textual modality of all four corpora has been enriched with linguistic annotations and sentiment predictions. Similarly, their spoken modality has been automatically enriched with occurrences of filled pauses, the most frequent type of disfluency in typical speech. Two languages have been additionally enriched with detailed word- and grapheme-level alignments, and the automatic annotation of the position of primary stress in multisyllabic words. With these enrichments, the usefulness of the corpora has been greatly increased for downstream research across multiple disciplines, which we showcase through an analysis of acoustic correlates of sentiment. All the corpora are made available for download in JSONL and TextGrid formats, as well as for search through a concordancer.</abstract>
<identifier type="citekey">ljubesic-etal-2026-parlaspeech</identifier>
<identifier type="doi">10.63317/3b7dnbjr75es</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.447/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5677</start>
<end>5688</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian
%A Ljubešić, Nikola
%A Rupnik, Peter
%A Porupski, Ivan
%A Kuzman Pungeršek, Taja
%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 ljubesic-etal-2026-parlaspeech
%X ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages – Croatian, Czech, Polish and Serbian – with a total size of more than 6 thousand hours. The corpora were built in an automatic fashion from the ParlaMint transcripts and their corresponding metadata, which were aligned to the speech recordings of each corresponding parliament. In this release of the dataset, each of the corpora has been significantly enriched with several automatic annotation layers. The textual modality of all four corpora has been enriched with linguistic annotations and sentiment predictions. Similarly, their spoken modality has been automatically enriched with occurrences of filled pauses, the most frequent type of disfluency in typical speech. Two languages have been additionally enriched with detailed word- and grapheme-level alignments, and the automatic annotation of the position of primary stress in multisyllabic words. With these enrichments, the usefulness of the corpora has been greatly increased for downstream research across multiple disciplines, which we showcase through an analysis of acoustic correlates of sentiment. All the corpora are made available for download in JSONL and TextGrid formats, as well as for search through a concordancer.
%R 10.63317/3b7dnbjr75es
%U https://aclanthology.org/2026.lrec-1.447/
%U https://doi.org/10.63317/3b7dnbjr75es
%P 5677-5688
Markdown (Informal)
[ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian](https://aclanthology.org/2026.lrec-1.447/) (Ljubešić et al., LREC 2026)
ACL