| 基于神经网络的藏语语音合成 |
| |
| 引用本文： | 都格草,才让卓玛,南措吉,算太本.基于神经网络的藏语语音合成[J].中文信息学报,2019,33(2):75-80. |
| |
| 作者姓名： | 都格草 才让卓玛 南措吉 算太本 |
| |
| 作者单位： | 青海师范大学 计算机学院 藏文智能信息处理与机器翻译重点实验室,青海 西宁 810008 |
| |
| 基金项目： | 国家自然科学基金(61866032,61163018,61262051,61662061);国家社会科学基金(13BYY141,16BYY167,15BYY167);教育部“春晖计划”合作科研项目(Z2012093,Z2016077);青海省科技厅项目(2017-ZJ-767,2019-SF-129);“长江学者和创新团队发展计划”创新团队资助项目(IRT1068);青海省重点实验室项目(2013-Z-Y17,2014-Z-Y32,2015-Z-Y03);藏文信息处理与机器翻译重点实验室(2013-Y-17);青海师范大学2017年度创新训练项目 |
| |
| 摘 要： | 语音合成是人机交互的核心技术之一,也是中文信息处理领域的一项前沿技术。随着神经网络理论的不断深入,基于神经网络的语音合成技术越来越引起人们的关注。该文通过分析藏文字结构与藏语拼读规则,融合Sequence to Sequence模型和注意力机制,研究了基于神经网络的藏语语音合成技术。实验数据表明,该文方法在藏语语音合成上具有良好的性能表现。
|
| 关 键 词： | 藏语语音合成 神经网络 Sequence to Sequence模型 注意力机制 |
Neural Network Based Tibetan Speech Synthesis |
| |
| DOU Gecao,CAI Rangzhuoma,NAN Cuoji,SUAN Taiben.Neural Network Based Tibetan Speech Synthesis[J].Journal of Chinese Information Processing,2019,33(2):75-80. |
| |
| Authors: | DOU Gecao CAI Rangzhuoma NAN Cuoji SUAN Taiben |
| |
| Affiliation: | Key Laboratory of Tibetan Information Processing, Ministry of Education, School of Computer Science, Qinghai Normal University, Xining, Qinghai 810008, China |
| |
| Abstract: | Speech synthesis is one of the core technologies of human-computer interaction. With the development of neural network, the speech synthesis technology based on neural network has attracted more and more attention. After analyzing the structure and spelling rules of Tibetan characters, this paper studies Tibetan speech synthesis by combining Sequence to Sequence model and attention mechanism. The experimental results show that this method has good performance in the speech synthesis of Tibetan. |
| |
| Keywords: | Tibetan speech synthesis neural network Sequence to Sequence attention |
|
| 点击此处可从《中文信息学报》浏览原始摘要信息 |
|
点击此处可从《中文信息学报》下载全文 |
|
