@inproceedings{keith-2024-work,
title = "Work in Progress: Text-to-speech on Edge Devices for Te Reo {M}{\=a}ori and {`}{\=O}lelo Hawaiʻi",
author = "Keith, T{\=u}reiti",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.sigul-1.50",
pages = "421--426",
abstract = "Existing popular text-to-speech technologies focus on large models requiring a large corpus of recorded speech to train. The resulting models are typically run on high-resource servers where users synthesise speech from a client device requiring constant connectivity. For speakers of low-resource languages living in remote areas, this approach does not work. Corpora are typically small and synthesis needs to run on an unconnected, battery or solar-powered edge device. In this paper, we demonstrate how knowledge transfer and adversarial training can be used to create efficient models capable of running on edge devices using a corpus of only several hours. We apply these concepts to create a voice synthesiser for te reo M{\=a}ori (the indigenous language of Aotearoa New Zealand) for a non-speaking user and {`}{\=o}lelo Hawaiʻi (the indigenous language of Hawaiʻi) for a legally blind user, thus creating the first high-quality text-to-speech tools for these endangered, central-eastern Polynesian languages capable of running on a low powered edge device.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keith-2024-work">
<titleInfo>
<title>Work in Progress: Text-to-speech on Edge Devices for Te Reo Māori and ‘Ōlelo Hawaiʻi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tūreiti</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing popular text-to-speech technologies focus on large models requiring a large corpus of recorded speech to train. The resulting models are typically run on high-resource servers where users synthesise speech from a client device requiring constant connectivity. For speakers of low-resource languages living in remote areas, this approach does not work. Corpora are typically small and synthesis needs to run on an unconnected, battery or solar-powered edge device. In this paper, we demonstrate how knowledge transfer and adversarial training can be used to create efficient models capable of running on edge devices using a corpus of only several hours. We apply these concepts to create a voice synthesiser for te reo Māori (the indigenous language of Aotearoa New Zealand) for a non-speaking user and ‘ōlelo Hawaiʻi (the indigenous language of Hawaiʻi) for a legally blind user, thus creating the first high-quality text-to-speech tools for these endangered, central-eastern Polynesian languages capable of running on a low powered edge device.</abstract>
<identifier type="citekey">keith-2024-work</identifier>
<location>
<url>https://aclanthology.org/2024.sigul-1.50</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>421</start>
<end>426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Work in Progress: Text-to-speech on Edge Devices for Te Reo Māori and ‘Ōlelo Hawaiʻi
%A Keith, Tūreiti
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F keith-2024-work
%X Existing popular text-to-speech technologies focus on large models requiring a large corpus of recorded speech to train. The resulting models are typically run on high-resource servers where users synthesise speech from a client device requiring constant connectivity. For speakers of low-resource languages living in remote areas, this approach does not work. Corpora are typically small and synthesis needs to run on an unconnected, battery or solar-powered edge device. In this paper, we demonstrate how knowledge transfer and adversarial training can be used to create efficient models capable of running on edge devices using a corpus of only several hours. We apply these concepts to create a voice synthesiser for te reo Māori (the indigenous language of Aotearoa New Zealand) for a non-speaking user and ‘ōlelo Hawaiʻi (the indigenous language of Hawaiʻi) for a legally blind user, thus creating the first high-quality text-to-speech tools for these endangered, central-eastern Polynesian languages capable of running on a low powered edge device.
%U https://aclanthology.org/2024.sigul-1.50
%P 421-426
Markdown (Informal)
[Work in Progress: Text-to-speech on Edge Devices for Te Reo Māori and ‘Ōlelo Hawaiʻi](https://aclanthology.org/2024.sigul-1.50) (Keith, SIGUL-WS 2024)
ACL