| 用CART模型指导TBL算法预测语调短语 |
| |
| 引用本文： | 刘方舟,周游,陶建华.用CART模型指导TBL算法预测语调短语[J].清华大学学报(自然科学版),2011(9):1226-1229. |
| |
| 作者姓名： | 刘方舟 周游 陶建华 |
| |
| 作者单位： | 湖南师范大学数学与计算机科学学院;湖南财政经济学院应用数学系;中国科学院自动化研究所模式识别国家重点实验室; |
| |
| 基金项目： | 国家自然科学基金面上项目(61011140075); 湖南省科技计划项目(2010FJ4131); 湖南省高等学校科学研究项目(10C0955) |
| |
| 摘 要： | 语调短语的自动预测是影响合成语音的可懂度和自然度的关键因素之一。该文提出了一种结合分类与回归树(classification and regression tree,CART)和基于转换的错误驱动的学习(transformation-based error-driven learning,TBL)算法的混合算法,从无限制的文本中预测语调短语边界。该方法根据CART模型的指导,自动生成TBL算法的规则模板,从而减少了规则学习过程中的人工参与。实验结果表明:基于该混合算法的语调短语预测的F-score达70.0%。自动生成的TBL模板不仅能较好地替代手工模板,而且在与手工模板一起使用时,也能为其提供有益的补充。
|
| 关 键 词： | 语调短语预测 模板生成 分类与回归树(CART) 基于转换的错误驱动的学习(TBL) |
Intonational phrase prediction based on a CART-guided TBL |
| |
| LIU Fangzhou,ZHOU You,TAO Jianhua.Intonational phrase prediction based on a CART-guided TBL[J].Journal of Tsinghua University(Science and Technology),2011(9):1226-1229. |
| |
| Authors: | LIU Fangzhou ZHOU You TAO Jianhua |
| |
| Institution: | LIU Fangzhou1,ZHOU You2,TAO Jianhua3(1.College of Mathematics and Computer Science,Hunan Normal University,Changsha 410081,China,2.Department of Applied Mathematics,Hunan University of Finance and Economics,Changsha 410205,3.National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Science,Beijing 100190,China) |
| |
| Abstract: | Intonational phrase prediction is important for both the naturalness and intelligibility of synthetic speech.This paper presents a hybrid tree-guided transformation-based learning(TGTBL) algorithm which combines a classification and regression tree(CART) with transformation-based error-driven learning(TBL) to predict intonational phrase breaks from unrestricted text.CART automatically generates the TBL rule templates,thereby minimizing the need for human supervision during the TBL training.Results of compar... |
| |
| Keywords: | intonational phrase prediction template generation classification and regression tree(CART) transformation-based error-driven learning(TBL) |
| 本文献已被 CNKI 等数据库收录！ |
