@inproceedings{kjartansson-etal-2020-open,
title = "Open-Source High Quality Speech Datasets for {B}asque, {C}atalan and {G}alician",
author = "Kjartansson, Oddur and
Gutkin, Alexander and
Butryna, Alena and
Demirsahin, Isin and
Rivera, Clara",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.3/",
pages = "21--27",
language = "eng",
ISBN = "979-10-95546-35-1",
abstract = "This paper introduces new open speech datasets for three of the languages of Spain: Basque, Catalan and Galician. Catalan is furthermore the official language of the Principality of Andorra. The datasets consist of high-quality multi-speaker recordings of the three languages along with the associated transcriptions. The resulting corpora include over 33 hours of crowd-sourced recordings of 132 male and female native speakers. The recording scripts also include material for elicitation of global and local place names, personal and business names. The datasets are released under a permissive license and are available for free download for commercial, academic and personal use. The high-quality annotated speech datasets described in this paper can be used to, among other things, build text-to-speech systems, serve as adaptation data in automatic speech recognition and provide useful phonetic and phonological insights in corpus linguistics."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kjartansson-etal-2020-open">
<titleInfo>
<title>Open-Source High Quality Speech Datasets for Basque, Catalan and Galician</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oddur</namePart>
<namePart type="family">Kjartansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gutkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alena</namePart>
<namePart type="family">Butryna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isin</namePart>
<namePart type="family">Demirsahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Rivera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</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">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>This paper introduces new open speech datasets for three of the languages of Spain: Basque, Catalan and Galician. Catalan is furthermore the official language of the Principality of Andorra. The datasets consist of high-quality multi-speaker recordings of the three languages along with the associated transcriptions. The resulting corpora include over 33 hours of crowd-sourced recordings of 132 male and female native speakers. The recording scripts also include material for elicitation of global and local place names, personal and business names. The datasets are released under a permissive license and are available for free download for commercial, academic and personal use. The high-quality annotated speech datasets described in this paper can be used to, among other things, build text-to-speech systems, serve as adaptation data in automatic speech recognition and provide useful phonetic and phonological insights in corpus linguistics.</abstract>
<identifier type="citekey">kjartansson-etal-2020-open</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.3/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>21</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open-Source High Quality Speech Datasets for Basque, Catalan and Galician
%A Kjartansson, Oddur
%A Gutkin, Alexander
%A Butryna, Alena
%A Demirsahin, Isin
%A Rivera, Clara
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G eng
%F kjartansson-etal-2020-open
%X This paper introduces new open speech datasets for three of the languages of Spain: Basque, Catalan and Galician. Catalan is furthermore the official language of the Principality of Andorra. The datasets consist of high-quality multi-speaker recordings of the three languages along with the associated transcriptions. The resulting corpora include over 33 hours of crowd-sourced recordings of 132 male and female native speakers. The recording scripts also include material for elicitation of global and local place names, personal and business names. The datasets are released under a permissive license and are available for free download for commercial, academic and personal use. The high-quality annotated speech datasets described in this paper can be used to, among other things, build text-to-speech systems, serve as adaptation data in automatic speech recognition and provide useful phonetic and phonological insights in corpus linguistics.
%U https://aclanthology.org/2020.sltu-1.3/
%P 21-27
Markdown (Informal)
[Open-Source High Quality Speech Datasets for Basque, Catalan and Galician](https://aclanthology.org/2020.sltu-1.3/) (Kjartansson et al., SLTU 2020)
ACL
- Oddur Kjartansson, Alexander Gutkin, Alena Butryna, Isin Demirsahin, and Clara Rivera. 2020. Open-Source High Quality Speech Datasets for Basque, Catalan and Galician. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), pages 21–27, Marseille, France. European Language Resources association.