@inproceedings{he-etal-2020-open,
title = "Open-source Multi-speaker Speech Corpora for Building {G}ujarati, {K}annada, {M}alayalam, {M}arathi, {T}amil and {T}elugu Speech Synthesis Systems",
author = "He, Fei and
Chu, Shan-Hui Cathy and
Kjartansson, Oddur and
Rivera, Clara and
Katanova, Anna and
Gutkin, Alexander and
Demirsahin, Isin and
Johny, Cibu and
Jansche, Martin and
Sarin, Supheakmungkol and
Pipatsrisawat, Knot",
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-1.800",
pages = "6494--6503",
abstract = "We present free high quality multi-speaker speech corpora for Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu, which are six of the twenty two official languages of India spoken by 374 million native speakers. The datasets are primarily intended for use in text-to-speech (TTS) applications, such as constructing multilingual voices or being used for speaker or language adaptation. Most of the corpora (apart from Marathi, which is a female-only database) consist of at least 2,000 recorded lines from female and male native speakers of the language. We present the methodological details behind corpora acquisition, which can be scaled to acquiring data for other languages of interest. We describe the experiments in building a multilingual text-to-speech model that is constructed by combining our corpora. Our results indicate that using these corpora results in good quality voices, with Mean Opinion Scores (MOS) {\textgreater} 3.6, for all the languages tested. We believe that these resources, released with an open-source license, and the described methodology will help in the progress of speech applications for the languages described and aid corpora development for other, smaller, languages of India and beyond.",
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="he-etal-2020-open">
<titleInfo>
<title>Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shan-Hui</namePart>
<namePart type="given">Cathy</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Clara</namePart>
<namePart type="family">Rivera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Katanova</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">Isin</namePart>
<namePart type="family">Demirsahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cibu</namePart>
<namePart type="family">Johny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Jansche</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Supheakmungkol</namePart>
<namePart type="family">Sarin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Knot</namePart>
<namePart type="family">Pipatsrisawat</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>We present free high quality multi-speaker speech corpora for Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu, which are six of the twenty two official languages of India spoken by 374 million native speakers. The datasets are primarily intended for use in text-to-speech (TTS) applications, such as constructing multilingual voices or being used for speaker or language adaptation. Most of the corpora (apart from Marathi, which is a female-only database) consist of at least 2,000 recorded lines from female and male native speakers of the language. We present the methodological details behind corpora acquisition, which can be scaled to acquiring data for other languages of interest. We describe the experiments in building a multilingual text-to-speech model that is constructed by combining our corpora. Our results indicate that using these corpora results in good quality voices, with Mean Opinion Scores (MOS) \textgreater 3.6, for all the languages tested. We believe that these resources, released with an open-source license, and the described methodology will help in the progress of speech applications for the languages described and aid corpora development for other, smaller, languages of India and beyond.</abstract>
<identifier type="citekey">he-etal-2020-open</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.800</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6494</start>
<end>6503</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems
%A He, Fei
%A Chu, Shan-Hui Cathy
%A Kjartansson, Oddur
%A Rivera, Clara
%A Katanova, Anna
%A Gutkin, Alexander
%A Demirsahin, Isin
%A Johny, Cibu
%A Jansche, Martin
%A Sarin, Supheakmungkol
%A Pipatsrisawat, Knot
%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 he-etal-2020-open
%X We present free high quality multi-speaker speech corpora for Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu, which are six of the twenty two official languages of India spoken by 374 million native speakers. The datasets are primarily intended for use in text-to-speech (TTS) applications, such as constructing multilingual voices or being used for speaker or language adaptation. Most of the corpora (apart from Marathi, which is a female-only database) consist of at least 2,000 recorded lines from female and male native speakers of the language. We present the methodological details behind corpora acquisition, which can be scaled to acquiring data for other languages of interest. We describe the experiments in building a multilingual text-to-speech model that is constructed by combining our corpora. Our results indicate that using these corpora results in good quality voices, with Mean Opinion Scores (MOS) \textgreater 3.6, for all the languages tested. We believe that these resources, released with an open-source license, and the described methodology will help in the progress of speech applications for the languages described and aid corpora development for other, smaller, languages of India and beyond.
%U https://aclanthology.org/2020.lrec-1.800
%P 6494-6503
Markdown (Informal)
[Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems](https://aclanthology.org/2020.lrec-1.800) (He et al., LREC 2020)
ACL
- Fei He, Shan-Hui Cathy Chu, Oddur Kjartansson, Clara Rivera, Anna Katanova, Alexander Gutkin, Isin Demirsahin, Cibu Johny, Martin Jansche, Supheakmungkol Sarin, and Knot Pipatsrisawat. 2020. Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6494–6503, Marseille, France. European Language Resources Association.