面向汉语统计参数语音合成的标注生成方法.pdfVIP

146 2016 ，52（19） Computer Engineering and Applications 计算机工程与应用 面向汉语统计参数语音合成的标注生成方法 郝东亮，杨鸿武，张 策，张 帅，郭立钊，杨静波 HAO Dongliang, YANG Hongwu, ZHANG Ce, ZHANG Shuai, GUO Lizhao, YANG Jingbo 西北师范大学 物理与电子工程学院，兰州 730070 College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, China HAO Dongliang, YANG Hongwu, ZHANG Ce, et al. Label generation for Chinese statistical parametric speech syn- thesis. Computer Engineering and Applications, 2016, 52 （19）：146-153. Abstract ：This paper designs a six-level context-dependent label format, which includes an initial and final level, a syllable level, a word level, a prosodic word level, a prosody phrase level and a sentence level, for Chinese statistical parametric speech synthesis. The input Chinese sentence is firstly normalized and performs grammar analysis to obtain sentence struc- ture and word segmentation information. Then the initial, final and tone of Chinese character are obtained by grapheme- to-phoneme conversion. The Transformation-Based error driven Learning （TBL ）algorithm is finally employed to predict the prosodic word boundary and prosodic phrase boundary of the input sentence. Context-dependent labels of each sen- tence for statistical parametric speech synthesis are generated according to the context information obtained from above text analysis and prosodic prediction procedures. A Hidden Markov Model （HMM ）based Mandarin statistical parametric speech synthesis is designed to evaluate the influences of different labels on quality of synthesized speech. Tests show that more context-dependent label information can achieve higher quality of synthesized speech. Key words ：text analysis; speech synthesis; context-dependent label; prosodic prediction; grapheme-to-phoneme conversion 摘 要：针对汉语统计参数语音合成中的上下文相关标注生成，设计了声韵母层、音节层、词层、韵律词层、韵律短语 层和语句层6 层上下文相关的标注格式。对输入的中文语句进行文本规范并利用语法分析获得语句的结构和分词 信息;通过字音转换获得每个汉字的声韵母及声调;利用TBL （Transformation-Based