@inproceedings{james-etal-2024-development,
title = "Development of Community-Oriented Text-to-Speech Models for {M}{\=a}ori {`}Avaiki {N}ui ({C}ook {I}slands {M}{\=a}ori)",
author = "James, Jesin and
Coto-Solano, Rolando and
Nicholas, Sally Akevai and
Zhu, Joshua and
Yu, Bovey and
Babasaki, Fuki and
Wang, Jenny Tyler and
Derby, Nicholas",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.432",
pages = "4820--4831",
abstract = {In this paper we describe the development of a text-to-speech system for M{\=a}ori {`}Avaiki Nui (Cook Islands M{\=a}ori). We provide details about the process of community-collaboration that was followed throughout the project, a continued engagement where we are trying to develop speech and language technology for the benefit of the community. During this process we gathered a group of recordings that we used to train a TTS system. When training we used two approaches, the HMM-system MaryTTS (Schr{\"o}der et al., 2011) and the deep learning system FastSpeech2 (Ren et al., 2020). We performed two evaluation tasks on the models: First, we measured their quality by having the synthesized speech transcribed by ASR. The human produced ground truth had lower error rates (CER=4.3, WER=18), but the FastSpeech2 audio has lower error rates (CER=11.8 and WER=42.7) than the MaryTTS voice (CER=17.9 and WER=48.1). The second evaluation was a survey amongst speakers of the language so they could judge the voice{'}s quality. The ground truth was rated with the highest quality (MOS=4.6), but the FastSpeech2 voice had an overall quality of MOS=3.2, which was significantly higher than that of the MaryTTS synthesized recordings (MOS=2.0). We intend to use the FastSpeech2 model to create language learning tools for community members both on the Cook Islands and in the diaspora.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="james-etal-2024-development">
<titleInfo>
<title>Development of Community-Oriented Text-to-Speech Models for Māori ‘Avaiki Nui (Cook Islands Māori)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesin</namePart>
<namePart type="family">James</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Coto-Solano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sally</namePart>
<namePart type="given">Akevai</namePart>
<namePart type="family">Nicholas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bovey</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuki</namePart>
<namePart type="family">Babasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jenny</namePart>
<namePart type="given">Tyler</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Derby</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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">Nianwen</namePart>
<namePart type="family">Xue</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>In this paper we describe the development of a text-to-speech system for Māori ‘Avaiki Nui (Cook Islands Māori). We provide details about the process of community-collaboration that was followed throughout the project, a continued engagement where we are trying to develop speech and language technology for the benefit of the community. During this process we gathered a group of recordings that we used to train a TTS system. When training we used two approaches, the HMM-system MaryTTS (Schröder et al., 2011) and the deep learning system FastSpeech2 (Ren et al., 2020). We performed two evaluation tasks on the models: First, we measured their quality by having the synthesized speech transcribed by ASR. The human produced ground truth had lower error rates (CER=4.3, WER=18), but the FastSpeech2 audio has lower error rates (CER=11.8 and WER=42.7) than the MaryTTS voice (CER=17.9 and WER=48.1). The second evaluation was a survey amongst speakers of the language so they could judge the voice’s quality. The ground truth was rated with the highest quality (MOS=4.6), but the FastSpeech2 voice had an overall quality of MOS=3.2, which was significantly higher than that of the MaryTTS synthesized recordings (MOS=2.0). We intend to use the FastSpeech2 model to create language learning tools for community members both on the Cook Islands and in the diaspora.</abstract>
<identifier type="citekey">james-etal-2024-development</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.432</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4820</start>
<end>4831</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of Community-Oriented Text-to-Speech Models for Māori ‘Avaiki Nui (Cook Islands Māori)
%A James, Jesin
%A Coto-Solano, Rolando
%A Nicholas, Sally Akevai
%A Zhu, Joshua
%A Yu, Bovey
%A Babasaki, Fuki
%A Wang, Jenny Tyler
%A Derby, Nicholas
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F james-etal-2024-development
%X In this paper we describe the development of a text-to-speech system for Māori ‘Avaiki Nui (Cook Islands Māori). We provide details about the process of community-collaboration that was followed throughout the project, a continued engagement where we are trying to develop speech and language technology for the benefit of the community. During this process we gathered a group of recordings that we used to train a TTS system. When training we used two approaches, the HMM-system MaryTTS (Schröder et al., 2011) and the deep learning system FastSpeech2 (Ren et al., 2020). We performed two evaluation tasks on the models: First, we measured their quality by having the synthesized speech transcribed by ASR. The human produced ground truth had lower error rates (CER=4.3, WER=18), but the FastSpeech2 audio has lower error rates (CER=11.8 and WER=42.7) than the MaryTTS voice (CER=17.9 and WER=48.1). The second evaluation was a survey amongst speakers of the language so they could judge the voice’s quality. The ground truth was rated with the highest quality (MOS=4.6), but the FastSpeech2 voice had an overall quality of MOS=3.2, which was significantly higher than that of the MaryTTS synthesized recordings (MOS=2.0). We intend to use the FastSpeech2 model to create language learning tools for community members both on the Cook Islands and in the diaspora.
%U https://aclanthology.org/2024.lrec-main.432
%P 4820-4831
Markdown (Informal)
[Development of Community-Oriented Text-to-Speech Models for Māori ‘Avaiki Nui (Cook Islands Māori)](https://aclanthology.org/2024.lrec-main.432) (James et al., LREC-COLING 2024)
ACL
- Jesin James, Rolando Coto-Solano, Sally Akevai Nicholas, Joshua Zhu, Bovey Yu, Fuki Babasaki, Jenny Tyler Wang, and Nicholas Derby. 2024. Development of Community-Oriented Text-to-Speech Models for Māori ‘Avaiki Nui (Cook Islands Māori). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4820–4831, Torino, Italia. ELRA and ICCL.