@inproceedings{hunter-etal-2024-meeting,
title = "{MEETING}: A corpus of {F}rench meeting-style conversations",
author = "Hunter, Julie and
Yamasaki, Hiroyoshi and
Granier, Oc{\'e}ane and
Louradour, J{\'e}r{\^o}me and
Bertrand, Roxane and
Thompson, Kate and
Pr{\'e}vot, Laurent",
editor = "Balaguer, Mathieu and
Bendahman, Nihed and
Ho-dac, Lydia-Mai and
Mauclair, Julie and
G Moreno, Jose and
Pinquier, Julien",
booktitle = "Actes de la 31{\`e}me Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position",
month = "7",
year = "2024",
address = "Toulouse, France",
publisher = "ATALA and AFPC",
url = "https://aclanthology.org/2024.jeptalnrecital-taln.35",
pages = "508--529",
abstract = "We present the MEETING corpus, a dataset of roughly 95 hours of spontaneous meeting-style conversations in French. The corpus is designed to serve as a foundation for downstream tasks such as meeting summarization. In its current state, it offers 25 hours of manually corrected transcripts that are aligned with the audio signal, making it a valuable resource for evaluating ASR and speaker recognition systems. It also includes automatic transcripts and alignments of the whole corpus which can be used for downstream NLP tasks. The aim of this paper is to describe the conception, production and annotation of the corpus up to the transcription level as well as to provide statistics that shed light on the main linguistic features of the corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hunter-etal-2024-meeting">
<titleInfo>
<title>MEETING: A corpus of French meeting-style conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Hunter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroyoshi</namePart>
<namePart type="family">Yamasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Océane</namePart>
<namePart type="family">Granier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jérôme</namePart>
<namePart type="family">Louradour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roxane</namePart>
<namePart type="family">Bertrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Prévot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Balaguer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nihed</namePart>
<namePart type="family">Bendahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lydia-Mai</namePart>
<namePart type="family">Ho-dac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Mauclair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">G Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Pinquier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA and AFPC</publisher>
<place>
<placeTerm type="text">Toulouse, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the MEETING corpus, a dataset of roughly 95 hours of spontaneous meeting-style conversations in French. The corpus is designed to serve as a foundation for downstream tasks such as meeting summarization. In its current state, it offers 25 hours of manually corrected transcripts that are aligned with the audio signal, making it a valuable resource for evaluating ASR and speaker recognition systems. It also includes automatic transcripts and alignments of the whole corpus which can be used for downstream NLP tasks. The aim of this paper is to describe the conception, production and annotation of the corpus up to the transcription level as well as to provide statistics that shed light on the main linguistic features of the corpus.</abstract>
<identifier type="citekey">hunter-etal-2024-meeting</identifier>
<location>
<url>https://aclanthology.org/2024.jeptalnrecital-taln.35</url>
</location>
<part>
<date>2024-7</date>
<extent unit="page">
<start>508</start>
<end>529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEETING: A corpus of French meeting-style conversations
%A Hunter, Julie
%A Yamasaki, Hiroyoshi
%A Granier, Océane
%A Louradour, Jérôme
%A Bertrand, Roxane
%A Thompson, Kate
%A Prévot, Laurent
%Y Balaguer, Mathieu
%Y Bendahman, Nihed
%Y Ho-dac, Lydia-Mai
%Y Mauclair, Julie
%Y G Moreno, Jose
%Y Pinquier, Julien
%S Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position
%D 2024
%8 July
%I ATALA and AFPC
%C Toulouse, France
%F hunter-etal-2024-meeting
%X We present the MEETING corpus, a dataset of roughly 95 hours of spontaneous meeting-style conversations in French. The corpus is designed to serve as a foundation for downstream tasks such as meeting summarization. In its current state, it offers 25 hours of manually corrected transcripts that are aligned with the audio signal, making it a valuable resource for evaluating ASR and speaker recognition systems. It also includes automatic transcripts and alignments of the whole corpus which can be used for downstream NLP tasks. The aim of this paper is to describe the conception, production and annotation of the corpus up to the transcription level as well as to provide statistics that shed light on the main linguistic features of the corpus.
%U https://aclanthology.org/2024.jeptalnrecital-taln.35
%P 508-529
Markdown (Informal)
[MEETING: A corpus of French meeting-style conversations](https://aclanthology.org/2024.jeptalnrecital-taln.35) (Hunter et al., JEP/TALN/RECITAL 2024)
ACL
- Julie Hunter, Hiroyoshi Yamasaki, Océane Granier, Jérôme Louradour, Roxane Bertrand, Kate Thompson, and Laurent Prévot. 2024. MEETING: A corpus of French meeting-style conversations. In Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position, pages 508–529, Toulouse, France. ATALA and AFPC.