Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet
Computation and Language
2025-02-06 v1 Artificial Intelligence
Machine Learning
Sound
Audio and Speech Processing
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 not only advances technical development for the revitalization of low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation.
Keywords
Cite
@article{arxiv.2502.02703,
title = {Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet},
author = {Shenran Wang and Changbing Yang and Mike Parkhill and Chad Quinn and Christopher Hammerly and Jian Zhu},
journal= {arXiv preprint arXiv:2502.02703},
year = {2025}
}