@inproceedings{wang-etal-2025-developing,
title = "Developing multilingual speech synthesis system for {O}jibwe, Mi{'}kmaq, and Maliseet",
author = "Wang, Shenran and
Yang, Changbing and
Parkhill, Michael l and
Quinn, Chad and
Hammerly, Christopher and
Zhu, Jian",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-short.69/",
doi = "10.18653/v1/2025.naacl-short.69",
pages = "817--826",
ISBN = "979-8-89176-190-2",
abstract = "We present lightweight flow matching multilingual text-to-speech (TTS) systems for Ojibwe, Mi{'}kmaq, and Maliseet, three Indigenous languages in North America. Our results show that training a multilingual TTS model on three typologically similar languages can improve the performance over monolingual models, especially when data are scarce. Attention-free architectures are highly competitive with self-attention architecture with higher memory efficiency. Our research provides technical development to language revitalization for low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-developing">
<titleInfo>
<title>Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shenran</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changbing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">l</namePart>
<namePart type="family">Parkhill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chad</namePart>
<namePart type="family">Quinn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Hammerly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-190-2</identifier>
</relatedItem>
<abstract>We present lightweight flow matching multilingual text-to-speech (TTS) systems for Ojibwe, Mi’kmaq, and Maliseet, three Indigenous languages in North America. Our results show that training a multilingual TTS model on three typologically similar languages can improve the performance over monolingual models, especially when data are scarce. Attention-free architectures are highly competitive with self-attention architecture with higher memory efficiency. Our research provides technical development to language revitalization for low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation.</abstract>
<identifier type="citekey">wang-etal-2025-developing</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-short.69</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-short.69/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>817</start>
<end>826</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet
%A Wang, Shenran
%A Yang, Changbing
%A Parkhill, Michael l.
%A Quinn, Chad
%A Hammerly, Christopher
%A Zhu, Jian
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-190-2
%F wang-etal-2025-developing
%X We present lightweight flow matching multilingual text-to-speech (TTS) systems for Ojibwe, Mi’kmaq, and Maliseet, three Indigenous languages in North America. Our results show that training a multilingual TTS model on three typologically similar languages can improve the performance over monolingual models, especially when data are scarce. Attention-free architectures are highly competitive with self-attention architecture with higher memory efficiency. Our research provides technical development to language revitalization for low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation.
%R 10.18653/v1/2025.naacl-short.69
%U https://aclanthology.org/2025.naacl-short.69/
%U https://doi.org/10.18653/v1/2025.naacl-short.69
%P 817-826
Markdown (Informal)
[Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet](https://aclanthology.org/2025.naacl-short.69/) (Wang et al., NAACL 2025)
ACL
- Shenran Wang, Changbing Yang, Michael l Parkhill, Chad Quinn, Christopher Hammerly, and Jian Zhu. 2025. Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 817–826, Albuquerque, New Mexico. Association for Computational Linguistics.