机构地区: 北京语言大学信息科学学院语言信息处理研究所
出 处: 《中文信息学报》 2006年第3期1-5,28,共6页
摘 要: 句子的韵律短语识别是语音合成的重要研究内容。本文提出了应用统计语言模型生成的二叉树,结合最大熵方法识别待合成汉语句子的语音停顿点。文中给出了二叉树相关的模型训练和生成算法;二叉树与语音停顿点之间的关系;在最大熵方法中应用二叉树剪枝识别句子的韵律短语。实验结果表明,在搜索算法中,利用二叉树进行剪枝,可以很大程度上提高语音停顿预测的正确率和召回率,基于试验数据的f-Score提高了近35%。 It is important to recognize the prosodic phrase breaks in text-to-speech. In this papcr,a new method is introduced for this purpose,which uses binary tree as pruning strategy in the Maximal Entropy Model (MaxEnt) framework. First of all, the concept of binary tree generated from a statistical language model is given. Then the process of generating the binary tree is discussed. In the process of applying MaxEnt to seeking optimal prosodic phrases, the binary tree is exploited so as to narrow the search space and improve the performance. Experimental results show that the F-score of predicating prosodic phrase breaks is about 35% better than the previous system, in which the binary tree strategy is not adopted.
关 键 词: 人工智能 自然语言处理 统计语言模型 二叉树 韵律短语 最大熵
领 域: [自动化与计算机技术] [自动化与计算机技术]