@inproceedings{zevallos-etal-2022-huqariq,
title = "Huqariq: A Multilingual Speech Corpus of Native Languages of {P}eru for{S}peech Recognition",
author = "Zevallos, Rodolfo and
Camacho, Luis and
Melgarejo, Nelsi",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.537",
pages = "5029--5034",
abstract = "The Huqariq corpus is a multilingual collection of speech from native Peruvian languages. The transcribed corpus is intended for the research and development of speech technologies to preserve endangered languages in Peru. Huqariq is primarily designed for the development of automatic speech recognition, language identification and text-to-speech tools. In order to achieve corpus collection sustainably, we employs the crowdsourcing methodology. Huqariq includes four native languages of Peru, and it is expected that by the year 2022, it can reach up to 20 native languages out of the 48 native languages in Peru. The corpus has 220 hours of transcribed audio recorded by more than 500 volunteers, making it the largest speech corpus for native languages in Peru. In order to verify the quality of the corpus, we present speech recognition experiments using 220 hours of fully transcribed audio.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zevallos-etal-2022-huqariq">
<titleInfo>
<title>Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="family">Zevallos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Camacho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelsi</namePart>
<namePart type="family">Melgarejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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>
</relatedItem>
<abstract>The Huqariq corpus is a multilingual collection of speech from native Peruvian languages. The transcribed corpus is intended for the research and development of speech technologies to preserve endangered languages in Peru. Huqariq is primarily designed for the development of automatic speech recognition, language identification and text-to-speech tools. In order to achieve corpus collection sustainably, we employs the crowdsourcing methodology. Huqariq includes four native languages of Peru, and it is expected that by the year 2022, it can reach up to 20 native languages out of the 48 native languages in Peru. The corpus has 220 hours of transcribed audio recorded by more than 500 volunteers, making it the largest speech corpus for native languages in Peru. In order to verify the quality of the corpus, we present speech recognition experiments using 220 hours of fully transcribed audio.</abstract>
<identifier type="citekey">zevallos-etal-2022-huqariq</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.537</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5029</start>
<end>5034</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition
%A Zevallos, Rodolfo
%A Camacho, Luis
%A Melgarejo, Nelsi
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F zevallos-etal-2022-huqariq
%X The Huqariq corpus is a multilingual collection of speech from native Peruvian languages. The transcribed corpus is intended for the research and development of speech technologies to preserve endangered languages in Peru. Huqariq is primarily designed for the development of automatic speech recognition, language identification and text-to-speech tools. In order to achieve corpus collection sustainably, we employs the crowdsourcing methodology. Huqariq includes four native languages of Peru, and it is expected that by the year 2022, it can reach up to 20 native languages out of the 48 native languages in Peru. The corpus has 220 hours of transcribed audio recorded by more than 500 volunteers, making it the largest speech corpus for native languages in Peru. In order to verify the quality of the corpus, we present speech recognition experiments using 220 hours of fully transcribed audio.
%U https://aclanthology.org/2022.lrec-1.537
%P 5029-5034
Markdown (Informal)
[Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition](https://aclanthology.org/2022.lrec-1.537) (Zevallos et al., LREC 2022)
ACL