@inproceedings{georgescu-etal-2020-rsc,
title = "{RSC}: A {R}omanian Read Speech Corpus for Automatic Speech Recognition",
author = "Georgescu, Alexandru-Lucian and
Cucu, Horia and
Buzo, Andi and
Burileanu, Corneliu",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.814",
pages = "6606--6612",
abstract = "Although many efforts have been made in the last decade to enhance the speech and language resources for Romanian, this language is still considered under-resourced. While for many other languages there are large speech corpora available for research and commercial applications, for Romanian language the largest publicly available corpus to date comprises less than 50 hours of speech. In this context, Speech and Dialogue research group releases Read Speech Corpus (RSC) {--} a Romanian speech corpus developed in-house, comprising 100 hours of speech recordings from 164 different speakers. The paper describes the development of the corpus and presents baseline automatic speech recognition (ASR) results using state-of-the-art ASR technology: Kaldi speech recognition toolkit.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="georgescu-etal-2020-rsc">
<titleInfo>
<title>RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandru-Lucian</namePart>
<namePart type="family">Georgescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horia</namePart>
<namePart type="family">Cucu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andi</namePart>
<namePart type="family">Buzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corneliu</namePart>
<namePart type="family">Burileanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Although many efforts have been made in the last decade to enhance the speech and language resources for Romanian, this language is still considered under-resourced. While for many other languages there are large speech corpora available for research and commercial applications, for Romanian language the largest publicly available corpus to date comprises less than 50 hours of speech. In this context, Speech and Dialogue research group releases Read Speech Corpus (RSC) – a Romanian speech corpus developed in-house, comprising 100 hours of speech recordings from 164 different speakers. The paper describes the development of the corpus and presents baseline automatic speech recognition (ASR) results using state-of-the-art ASR technology: Kaldi speech recognition toolkit.</abstract>
<identifier type="citekey">georgescu-etal-2020-rsc</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.814</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6606</start>
<end>6612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition
%A Georgescu, Alexandru-Lucian
%A Cucu, Horia
%A Buzo, Andi
%A Burileanu, Corneliu
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F georgescu-etal-2020-rsc
%X Although many efforts have been made in the last decade to enhance the speech and language resources for Romanian, this language is still considered under-resourced. While for many other languages there are large speech corpora available for research and commercial applications, for Romanian language the largest publicly available corpus to date comprises less than 50 hours of speech. In this context, Speech and Dialogue research group releases Read Speech Corpus (RSC) – a Romanian speech corpus developed in-house, comprising 100 hours of speech recordings from 164 different speakers. The paper describes the development of the corpus and presents baseline automatic speech recognition (ASR) results using state-of-the-art ASR technology: Kaldi speech recognition toolkit.
%U https://aclanthology.org/2020.lrec-1.814
%P 6606-6612
Markdown (Informal)
[RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition](https://aclanthology.org/2020.lrec-1.814) (Georgescu et al., LREC 2020)
ACL