The study of the trainable prosodic model for Chinese text to speech system 汉语文语转换系统中可训练韵律模型的研究
Prosodic phrase analysis is a very important modular in a text-to-speech system. 韵律短语分析是文语转换(Text-to-Speech)系统的重要组成部分。
Research findings prove that an improvement to apriori algorithm for generating association rules of prosodic parameters including pitch parameters and duration parameters from corpus and for syllable choice is able to offer convenience in speech system. 结果表明,经改进后适合语音数据的Apriori算法,可以获得汉语韵律参数中基频参数和时长参数的变化规则,这些规则较方便的为语音合成系统的选音提供帮助和指导。
The Competed Artificial Neural Network Apply in Mandarin Prosodic Model of TTS System 竞争型神经网在汉语TTS系统中的应用
Extract the TC ( tertium comparations) of the comparative items, namely, distinctive prosodic features in phonological system of both English and Chinese language which can distinguish meaning of words and part of speech in a sentence. 从对比项中析出了共同对比项&英汉语音音系系统中可区分词性和词义的区别性韵律特征;
Both the Chinese part-of-speech automatic tagging and prosodic phrase segmentation are important modulars in a Chinese text-to-speech system. 汉语自动词性标注和韵律短语切分都是汉语文语转换(Text-to-Speech)系统的重要组成部分。
The article redefines the prosodic word for TTS system. 本文针对TTS系统的需要制定了韵律词的标准。
In orienting the dynamic flow of information, thematic development gives value to some nodes as the interpersonal starting points staging the prosodic realization of instantial interpersonal system. 主位发展动态推动话语信息流,赋予实例体系中某些特定项以人际出发点和导向价值,使这些特定项成为实例人际体系韵律表现的信息生长点。
Prosodic Control for Speech Synthesis of Wu-Dialect Chinese Text to Speech System 吴语文语转换中的语音韵律控制
Based on the prosodic characteristics of Chinese digit strings and the application of the LMA synthesizer, a new speech synthesis system is introduced in this paper. 根据汉语普通话中数字串发音的韵律规则和特点,利用LMA语音合成器,实现了一种全新的数字串报号系统。
This paper presents the flowchart of the new Chinese text-to-speech system, the research result of acoustics analysis of news broadcast speech, prosodic rules of the new system, and the evaluation results of speech quality of the new system. 本文介绍新的汉语文语转换系统的结构及流程、对广播语言韵律特征的初步研究结果、汉语合成规则及合成系统语音质量的评测结果。
In this paper, we analyze statistically the prosodic data in the large corpus for our Chinese TTS system. The relationship between the prosodic features of syllables, the positions and the boundaries of prosodic constituents is discussed. 对汉语TTS系统的大规模语料库做了基本的韵律参数统计,分析了音节的韵律特征与其所在的韵律结构位置以及韵律结构边界的关系。
ToBI ( Tones and Break Indices) is currently a widely-used prosodic labeling system. ToBI(TonesandBreakIndices)是目前国际上较为流行的韵律标注体系。
In addition, this paper, came up with maximum entropy based multi-pass prosodic structure prediction system, and compared with the CRFs-based prediction system. 此外,本文提出了基于最大熵模型的多遍韵律结构预测系统,并和基于CRFs的预测系统进行了性能上比较和分析。
However, the naturalness of synthesized speech is still insufficiently ideal, mainly because of deficient prosodic model in synthesis system. 但是,合成语音的自然度依然不够理想,这主要是由于合成系统中的韵律模型还不是很完善。