arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.00657eess.AScs.AIcs.CL
收藏

MnTTS2:一个开源的蒙古语多说话人文本转语音合成数据集

MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset

Inner Mongolia University(内蒙古大学)

Kailin Liang, Bin Liu, Yifan Hu, Rui Liu, Feilong Bao, Guanglai Gao

摘要:

低资源语言的文本转语音(TTS)合成是当前学术界和工业界的一个研究热点。蒙古语是内蒙古自治区的官方语言,也是一种代表性的低资源语言,全球有1000多万人使用。然而,蒙古文TTS的开源数据集相对缺乏。因此,我们公开了一个开源的多说话人蒙古文TTS数据集,命名为MnTTS 2,以供相关研究人员参考。在这项工作中,我们准备了各种主题的转录,并邀请三名专业的蒙古语播音员组成一个三人TTS数据集,其中每个播音员记录了10个小时的蒙古语演讲,总共30小时。此外,我们建立了基于最先进的FastSpeech 2模型和HiFi-GAN声码器的基线系统。实验结果表明,所构建的MnTTS 2数据集足以构建鲁棒的多说话人TTS模型,用于现实世界的应用。MnTTS 2数据集、训练配方和预训练模型发布于:\url{https://github.com/ssmlkl/MnTTS2}

英文摘要:

Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongolia Autonomous Region and a representative low-resource language spoken by over 10 million people worldwide. However, there is a relative lack of open-source datasets for Mongolian TTS. Therefore, we make public an open-source multi-speaker Mongolian TTS dataset, named MnTTS2, for the benefit of related researchers. In this work, we prepare the transcription from various topics and invite three professional Mongolian announcers to form a three-speaker TTS dataset, in which each announcer records 10 hours of speeches in Mongolian, resulting 30 hours in total. Furthermore, we build the baseline system based on the state-of-the-art FastSpeech2 model and HiFi-GAN vocoder. The experimental results suggest that the constructed MnTTS2 dataset is sufficient to build robust multi-speaker TTS models for real-world applications. The MnTTS2 dataset, training recipe, and pretrained models are released at: \url{https://github.com/ssmlkl/MnTTS2}

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。

↑