@inproceedings{samsudin-lee-2012-building,
title = "Building Text-to-Speech Systems for Resource Poor Languages",
author = "Samsudin, Nur-Hana and
Lee, Mark",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1070_Paper.pdf",
pages = "3327--3334",
abstract = "This paper describes research on building text-to-speech synthesis systems (TTS) for resource poor languages using available resources from other languages and describes our general approach to building cross-linguistic polyglot TTS. Our approach involves three main steps: language clustering, grapheme to phoneme mapping and prosody modelling. We have tested the mapping of phonemes from German to English and from Indonesian to Spanish. We have also constructed three prosody representations for different language characteristics. For evaluation we have developed an English TTS based on German data, and a Spanish TTS based on Indonesian data and compared their performance against pre-existing monolingual TTSs. Since our motivation is to develop speech synthesis for resource poor languages, we have also developed three TTS for Iban, an Austronesian language with practically no available language resources, using Malay, Indonesian and Spanish resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samsudin-lee-2012-building">
<titleInfo>
<title>Building Text-to-Speech Systems for Resource Poor Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nur-Hana</namePart>
<namePart type="family">Samsudin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes research on building text-to-speech synthesis systems (TTS) for resource poor languages using available resources from other languages and describes our general approach to building cross-linguistic polyglot TTS. Our approach involves three main steps: language clustering, grapheme to phoneme mapping and prosody modelling. We have tested the mapping of phonemes from German to English and from Indonesian to Spanish. We have also constructed three prosody representations for different language characteristics. For evaluation we have developed an English TTS based on German data, and a Spanish TTS based on Indonesian data and compared their performance against pre-existing monolingual TTSs. Since our motivation is to develop speech synthesis for resource poor languages, we have also developed three TTS for Iban, an Austronesian language with practically no available language resources, using Malay, Indonesian and Spanish resources.</abstract>
<identifier type="citekey">samsudin-lee-2012-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1070_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3327</start>
<end>3334</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Text-to-Speech Systems for Resource Poor Languages
%A Samsudin, Nur-Hana
%A Lee, Mark
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F samsudin-lee-2012-building
%X This paper describes research on building text-to-speech synthesis systems (TTS) for resource poor languages using available resources from other languages and describes our general approach to building cross-linguistic polyglot TTS. Our approach involves three main steps: language clustering, grapheme to phoneme mapping and prosody modelling. We have tested the mapping of phonemes from German to English and from Indonesian to Spanish. We have also constructed three prosody representations for different language characteristics. For evaluation we have developed an English TTS based on German data, and a Spanish TTS based on Indonesian data and compared their performance against pre-existing monolingual TTSs. Since our motivation is to develop speech synthesis for resource poor languages, we have also developed three TTS for Iban, an Austronesian language with practically no available language resources, using Malay, Indonesian and Spanish resources.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1070_Paper.pdf
%P 3327-3334
Markdown (Informal)
[Building Text-to-Speech Systems for Resource Poor Languages](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1070_Paper.pdf) (Samsudin & Lee, LREC 2012)
ACL