为曼尼普尔语梅泰文开发了首个神经文本转语音系统。
Text to Speech System for Meitei Mayek Script
- 基于Tacotron 2与HiFi-GAN构建适配声调语言的TTS架构
- 建立梅泰文到ARPAbet的音素映射，打造单说话人数据集
- 生成语音自然流畅，适用于语言保护与技术普惠
本文提出一种基于梅泰文的曼尼普尔语文本转语音（TTS）系统。结合Tacotron 2与HiFi-GAN，构建了支持声调音系和资源匮乏语言环境的神经TTS架构。通过建立梅泰文至ARPAbet的音素映射，构建单说话人语料库，实现了可懂且自然的语音合成，并通过主观与客观评估验证。该系统为曼尼普尔语的语言保存与技术包容奠定了基础。
原文摘要 · Abstract (English)
This paper presents the development of a Text-to-Speech (TTS) system for the Manipuri language using the Meitei Mayek script. Leveraging Tacotron 2 and HiFi-GAN, we introduce a neural TTS architecture adapted to support tonal phonology and under-resourced linguistic environments. We develop a phoneme mapping for Meitei Mayek to ARPAbet, curate a single-speaker dataset, and demonstrate intelligible and natural speech synthesis, validated through subjective and objective metrics. This system lays the groundwork for linguistic preservation and technological inclusion of Manipuri.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。