中文摘要：

在语音合成技术的研究中，情感语音合成是当前研究的热点．在众多研究因素中，建立恰当的韵律模型和选取好的韵律参数是研究的关键，它们描述的正确与否，直接影响到情感语音合成的输出效果．为了攻克提高情感语音自然度这一难点，对影响情感语音合成技术韵律参数进行了分析，建立了基于关联规则的情感语音韵律基频模型．本文通过研究关联规则、改进数据挖掘Apriori算法并由此来获得韵律参数中基频变化规则，并为情感语音合成的选音提供指导和帮助．

英文摘要：

Emotional Speech Synthesis is a prevalent trend in current speech synthesis technology research. Among all the factors, appropriate emotional prosody model building and prosodic parameter selecting are the key matter. Whether it describes correct or not, will have a direct impact on the outputting effects of the emotional speech synthesis. In order to overcome the difficulty of improving natural degree in emotional speech, the parameters that affect the prosody of emotional speech synthesis technology are analyzed and an emotional prosody model based on association rules is built. This paper studies the association rules, and through improving data mining Apriori algorithm so as to obtain the fundamental frequency changing rules in prosodic parameters, and thus provide guidance and convenience for selecting sound in emotional speech synthesis.