| 基于决策树的语音基元语境特征权重训练算法 |
| |
| 引用本文： | 杨鸿武,郭威彤,蔡莲红,吴志勇.基于决策树的语音基元语境特征权重训练算法[J].西北师范大学学报,2007,43(4):50-54. |
| |
| 作者姓名： | 杨鸿武 郭威彤 蔡莲红 吴志勇 |
| |
| 作者单位： | 西北师范大学物理与电子工程学院 甘肃兰州730070(杨鸿武，郭威彤)，清华大学计算机科学与技术系普适计算教育部重点实验室 北京100084(蔡莲红，吴志勇) |
| |
| 基金项目： | 西北师范大学科研骨干培育项目 |
| |
| 摘 要： | 提出了一种基于决策树的语音合成基元的语境特征权重训练算法.对语音数据库中的每个带调音节,利用语境相关的问题集和候选基元的频谱距离建立决策树.对每个要合成的音节,根据其语境特征,获得语音合成系统选择的基元的语境特征F*和该语境特征下决策树叶子结点中基元的语境特征F′.统计F′中每一个语境特征相对于F*的变化,根据语境特征变化的概率对权重进行调整.实验结果表明,这种方法能够训练出合理的语境特征权重,使得合成语音的自然度有一定提高.同时,利用这种方法还可以对语音合成系统进行实时优化.
|
| 关 键 词： | 语音合成 文语转换 基元选取 权重训练 |
| 文章编号： | 1001-988X（2007）04-0050-05 |
| 修稿时间： | 2007-01-022007-05-28 |
CARD based context specified weights training algorism for unit selection in speech synthesis |
| |
| YANG Hong-wu,GUO Wei-tong,CAI Lian-hong,WU Zhi-yong.CARD based context specified weights training algorism for unit selection in speech synthesis[J].Journal of Northwest Normal University Natural Science (Bimonthly),2007,43(4):50-54. |
| |
| Authors: | YANG Hong-wu GUO Wei-tong CAI Lian-hong WU Zhi-yong |
| |
| Institution: | 1. College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, 730070, Gansu, China; 2. Key Laboratory of Pervasive Computing, Ministry of Education; Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China |
| |
| Abstract: | The paper introduces a context specified weights training algorism for contextual features of speech unit in speech synthesis based on Classification and Regression Tree(CART).A CART is created for each tonal syllable with the spectral distance of each candidate unit and the context dependent question set.The increments of contextual features are counted by comparing the units selected by TTS and given by leaf node of CART.The weights of contextual features are then adjusted in accordance with their probability of increment.The experiments demonstrate that a set of reasonable weights can be trained by the algorism so the naturalness of synthetic speech can also be improved.The algorism can also be used to optimize the speech synthesis system online. |
| |
| Keywords: | speech synthesis text-to-speech unit selection weight training |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
