@inproceedings{felice-etal-2024-audiocite-net,
title = "Audiocite.net : A Large Spoken Read Dataset in {F}rench",
author = "Felice, Soline and
Evain, Solene Virginie and
Rossato, Solange and
Portet, Fran{\c{c}}ois",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.159",
pages = "1795--1800",
abstract = "The advent of self-supervised learning (SSL) in speech processing has allowed the use of large unlabeled datasets to learn pre-trained models, serving as powerful encoders for various downstream tasks. However, the application of these SSL methods to languages such as French has proved difficult due to the scarcity of large French speech datasets. To advance the emergence of pre-trained models for French speech, we present the Audiocite.net corpus composed of 6,682 hours of recordings from 130 readers. This corpus is composed of audiobooks from the audiocite.net website, shared by 130 readers. In addition to describing the creation process and final statistics, we also show how this dataset impacted the models of LeBenchmark project in its 14k version for speech processing downstream tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="felice-etal-2024-audiocite-net">
<titleInfo>
<title>Audiocite.net : A Large Spoken Read Dataset in French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soline</namePart>
<namePart type="family">Felice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solene</namePart>
<namePart type="given">Virginie</namePart>
<namePart type="family">Evain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solange</namePart>
<namePart type="family">Rossato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Portet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The advent of self-supervised learning (SSL) in speech processing has allowed the use of large unlabeled datasets to learn pre-trained models, serving as powerful encoders for various downstream tasks. However, the application of these SSL methods to languages such as French has proved difficult due to the scarcity of large French speech datasets. To advance the emergence of pre-trained models for French speech, we present the Audiocite.net corpus composed of 6,682 hours of recordings from 130 readers. This corpus is composed of audiobooks from the audiocite.net website, shared by 130 readers. In addition to describing the creation process and final statistics, we also show how this dataset impacted the models of LeBenchmark project in its 14k version for speech processing downstream tasks.</abstract>
<identifier type="citekey">felice-etal-2024-audiocite-net</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.159</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1795</start>
<end>1800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Audiocite.net : A Large Spoken Read Dataset in French
%A Felice, Soline
%A Evain, Solene Virginie
%A Rossato, Solange
%A Portet, François
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F felice-etal-2024-audiocite-net
%X The advent of self-supervised learning (SSL) in speech processing has allowed the use of large unlabeled datasets to learn pre-trained models, serving as powerful encoders for various downstream tasks. However, the application of these SSL methods to languages such as French has proved difficult due to the scarcity of large French speech datasets. To advance the emergence of pre-trained models for French speech, we present the Audiocite.net corpus composed of 6,682 hours of recordings from 130 readers. This corpus is composed of audiobooks from the audiocite.net website, shared by 130 readers. In addition to describing the creation process and final statistics, we also show how this dataset impacted the models of LeBenchmark project in its 14k version for speech processing downstream tasks.
%U https://aclanthology.org/2024.lrec-main.159
%P 1795-1800
Markdown (Informal)
[Audiocite.net : A Large Spoken Read Dataset in French](https://aclanthology.org/2024.lrec-main.159) (Felice et al., LREC-COLING 2024)
ACL
- Soline Felice, Solene Virginie Evain, Solange Rossato, and François Portet. 2024. Audiocite.net : A Large Spoken Read Dataset in French. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1795–1800, Torino, Italia. ELRA and ICCL.