SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.02703 · NAACL · 2025

Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet

Jian Zhu, Changbing Yang, Shenran Wang, Mike Parkhill, Chad Quinn, Christopher Hammerly

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 selfattention architecture with higher memory efficiency. Our research not only advances technical development for the revitalization of lowresource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.02703")
get_code_for_paper("2502.02703")
have("2502.02703")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2502.02703.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2502.02703.svg)](https://syntology.ai/paper/2502.02703)

Connect an agent — have() is free.