为奥吉布韦语、米克马克语和马利西特语开发多语言语音合成系统
Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet
AI总结:
本文为三种北美原住民语言开发轻量级流匹配多语言TTS系统,证明多语言训练在低资源场景下优于单语言模型,并指出无注意力架构兼具竞争力与内存效率,同时呼吁建立以社区为中心的人类评估协议。
摘要:
我们提出了轻量级流匹配多语言文本到语音(TTS)系统,用于奥吉布韦语、米克马克语和马利西特语这三种北美原住民语言。我们的结果表明,在三种类型学相似的语言上训练多语言TTS模型,相比单语言模型能够提升性能,尤其是在数据稀缺的情况下。无注意力架构在与自注意力架构的竞争中表现出很强的竞争力,并且具有更高的内存效率。我们的研究不仅推动了低资源语言复兴的技术发展,还揭示了人类评估协议中的文化差距,呼吁采用更加以社区为中心的人类评估方法。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。