@inproceedings{siegert-2026-voices,
title = "Voices across Decades: A Multimodal Diachronic Corpus of {G}erman Bundestag Debates ({G}er{P}arl{D}ia-{MM})",
author = "Siegert, Ingo",
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-1.498/",
doi = "10.63317/3vgihkgnkg75",
pages = "6289--6297",
abstract = "This paper presents a multimodal diachronic corpus of German parliamentary debates spanning 1949 {--} 2025. The dataset focuses on speakers with exceptionally long political careers in the Bundestag, covering at least six parliamentary terms for female and eight for male members, comprising 75 individuals (43 men/32 female) and 2,136 speeches. The corpus integrates audio, video (when available), and official transcripts, enriched with metadata on date, party affiliation, and legislative term. Transcripts were temporally aligned with parliamentary media recordings, and non-speech segments were automatically removed. The corpus enables research on voice aging, intra-speaker variability, and longitudinal political language, and supports benchmarking of ASR and speaker recognition across decades. Thus, this corpus bridges the gap between short-term speech corpora and single-speaker longitudinal datasets, offering a unique foundation for studying change in voice, style, and rhetoric over more than seventy years of German parliamentary history."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siegert-2026-voices">
<titleInfo>
<title>Voices across Decades: A Multimodal Diachronic Corpus of German Bundestag Debates (GerParlDia-MM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ingo</namePart>
<namePart type="family">Siegert</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 a multimodal diachronic corpus of German parliamentary debates spanning 1949 – 2025. The dataset focuses on speakers with exceptionally long political careers in the Bundestag, covering at least six parliamentary terms for female and eight for male members, comprising 75 individuals (43 men/32 female) and 2,136 speeches. The corpus integrates audio, video (when available), and official transcripts, enriched with metadata on date, party affiliation, and legislative term. Transcripts were temporally aligned with parliamentary media recordings, and non-speech segments were automatically removed. The corpus enables research on voice aging, intra-speaker variability, and longitudinal political language, and supports benchmarking of ASR and speaker recognition across decades. Thus, this corpus bridges the gap between short-term speech corpora and single-speaker longitudinal datasets, offering a unique foundation for studying change in voice, style, and rhetoric over more than seventy years of German parliamentary history.</abstract>
<identifier type="citekey">siegert-2026-voices</identifier>
<identifier type="doi">10.63317/3vgihkgnkg75</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.498/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6289</start>
<end>6297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Voices across Decades: A Multimodal Diachronic Corpus of German Bundestag Debates (GerParlDia-MM)
%A Siegert, Ingo
%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 siegert-2026-voices
%X This paper presents a multimodal diachronic corpus of German parliamentary debates spanning 1949 – 2025. The dataset focuses on speakers with exceptionally long political careers in the Bundestag, covering at least six parliamentary terms for female and eight for male members, comprising 75 individuals (43 men/32 female) and 2,136 speeches. The corpus integrates audio, video (when available), and official transcripts, enriched with metadata on date, party affiliation, and legislative term. Transcripts were temporally aligned with parliamentary media recordings, and non-speech segments were automatically removed. The corpus enables research on voice aging, intra-speaker variability, and longitudinal political language, and supports benchmarking of ASR and speaker recognition across decades. Thus, this corpus bridges the gap between short-term speech corpora and single-speaker longitudinal datasets, offering a unique foundation for studying change in voice, style, and rhetoric over more than seventy years of German parliamentary history.
%R 10.63317/3vgihkgnkg75
%U https://aclanthology.org/2026.lrec-1.498/
%U https://doi.org/10.63317/3vgihkgnkg75
%P 6289-6297
Markdown (Informal)
[Voices across Decades: A Multimodal Diachronic Corpus of German Bundestag Debates (GerParlDia-MM)](https://aclanthology.org/2026.lrec-1.498/) (Siegert, LREC 2026)
ACL