Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915138314960896 |
|---|---|
| author | Wang, Shenran Yang, Changbing Parkhill, Mike Quinn, Chad Hammerly, Christopher Zhu, Jian |
| author_facet | Wang, Shenran Yang, Changbing Parkhill, Mike Quinn, Chad Hammerly, Christopher Zhu, Jian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet Wang, Shenran Yang, Changbing Parkhill, Mike Quinn, Chad Hammerly, Christopher Zhu, Jian Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing 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. |
| title | Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet |
| topic | Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2502.02703 |