@inproceedings{oo-etal-2020-burmese,
title = "{B}urmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech",
author = "Oo, Yin May and
Wattanavekin, Theeraphol and
Li, Chenfang and
De Silva, Pasindu and
Sarin, Supheakmungkol and
Pipatsrisawat, Knot and
Jansche, Martin and
Kjartansson, Oddur and
Gutkin, Alexander",
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-1.777/",
pages = "6328--6339",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "This paper introduces an open-source crowd-sourced multi-speaker speech corpus along with the comprehensive set of finite-state transducer (FST) grammars for performing text normalization for the Burmese (Myanmar) language. We also introduce the open-source finite-state grammars for performing grapheme-to-phoneme (G2P) conversion for Burmese. These three components are necessary (but not sufficient) for building a high-quality text-to-speech (TTS) system for Burmese, a tonal Southeast Asian language from the Sino-Tibetan family which presents several linguistic challenges. We describe the corpus acquisition process and provide the details of our finite state-based approach to Burmese text normalization and G2P. Our experiments involve building a multi-speaker TTS system based on long short term memory (LSTM) recurrent neural network (RNN) models, which were previously shown to perform well for other languages in a low-resource setting. Our results indicate that the data and grammars that we are announcing are sufficient to build reasonably high-quality models comparable to other systems. We hope these resources will facilitate speech and language research on the Burmese language, which is considered by many to be low-resource due to the limited availability of free linguistic data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oo-etal-2020-burmese">
<titleInfo>
<title>Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="given">May</namePart>
<namePart type="family">Oo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theeraphol</namePart>
<namePart type="family">Wattanavekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenfang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pasindu</namePart>
<namePart type="family">De Silva</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>
<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">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>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">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>This paper introduces an open-source crowd-sourced multi-speaker speech corpus along with the comprehensive set of finite-state transducer (FST) grammars for performing text normalization for the Burmese (Myanmar) language. We also introduce the open-source finite-state grammars for performing grapheme-to-phoneme (G2P) conversion for Burmese. These three components are necessary (but not sufficient) for building a high-quality text-to-speech (TTS) system for Burmese, a tonal Southeast Asian language from the Sino-Tibetan family which presents several linguistic challenges. We describe the corpus acquisition process and provide the details of our finite state-based approach to Burmese text normalization and G2P. Our experiments involve building a multi-speaker TTS system based on long short term memory (LSTM) recurrent neural network (RNN) models, which were previously shown to perform well for other languages in a low-resource setting. Our results indicate that the data and grammars that we are announcing are sufficient to build reasonably high-quality models comparable to other systems. We hope these resources will facilitate speech and language research on the Burmese language, which is considered by many to be low-resource due to the limited availability of free linguistic data.</abstract>
<identifier type="citekey">oo-etal-2020-burmese</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.777/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6328</start>
<end>6339</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech
%A Oo, Yin May
%A Wattanavekin, Theeraphol
%A Li, Chenfang
%A De Silva, Pasindu
%A Sarin, Supheakmungkol
%A Pipatsrisawat, Knot
%A Jansche, Martin
%A Kjartansson, Oddur
%A Gutkin, Alexander
%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 eng
%F oo-etal-2020-burmese
%X This paper introduces an open-source crowd-sourced multi-speaker speech corpus along with the comprehensive set of finite-state transducer (FST) grammars for performing text normalization for the Burmese (Myanmar) language. We also introduce the open-source finite-state grammars for performing grapheme-to-phoneme (G2P) conversion for Burmese. These three components are necessary (but not sufficient) for building a high-quality text-to-speech (TTS) system for Burmese, a tonal Southeast Asian language from the Sino-Tibetan family which presents several linguistic challenges. We describe the corpus acquisition process and provide the details of our finite state-based approach to Burmese text normalization and G2P. Our experiments involve building a multi-speaker TTS system based on long short term memory (LSTM) recurrent neural network (RNN) models, which were previously shown to perform well for other languages in a low-resource setting. Our results indicate that the data and grammars that we are announcing are sufficient to build reasonably high-quality models comparable to other systems. We hope these resources will facilitate speech and language research on the Burmese language, which is considered by many to be low-resource due to the limited availability of free linguistic data.
%U https://aclanthology.org/2020.lrec-1.777/
%P 6328-6339
Markdown (Informal)
[Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech](https://aclanthology.org/2020.lrec-1.777/) (Oo et al., LREC 2020)
ACL
- Yin May Oo, Theeraphol Wattanavekin, Chenfang Li, Pasindu De Silva, Supheakmungkol Sarin, Knot Pipatsrisawat, Martin Jansche, Oddur Kjartansson, and Alexander Gutkin. 2020. Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6328–6339, Marseille, France. European Language Resources Association.