汉语双音节词VCV序列协同发音

该文通过分析跨音段情况下前音节元音对后音节元音第二共振峰F2起点的影响,考察了汉语普通话双音节词"元音-塞音-元音"序列中2个元音之间的协同发音现象。结果发现:当2个元音之间为送气塞音时,由于送气塞音时值较长,元音间的协同发音作用便比较小,送气是抑制协同发音作用的重要因素;在塞音发音部位方面,当后接元音为/i/时,跨唇音的协同作用较大,而跨舌尖音的协同作用较小,不过发音部位与后接元音的交互作用很大,超过发音部位单方面的作用。     

基于古音系统的汉语方言语音合成

采用HTS语音训练合成工具和STRAIGHT语音合成器,尝试在未知某方言(或土语)的实际语音系统的条件下开展相应的语音训练合成工作。采用古音系统来转写汉语字音,并在此基础上设计相应的问题集以实现语音训练合成。设计了一套面向汉语方言语音合成的通用发音文本;录制了一些汉语方言点的合成语音语料库;搭建了基于古音系统的汉语方言语音合成平台。普通话的合成实验结果表明:基于古音系统训练合成出来的语音,在可懂度和音质上跟基于普通话拼音系统训练合成出来的语音非常接近。这表明基于古音系统进行汉语方言语音合成的方法是有效的、可行的。     

Improved Grapheme-to-Phoneme Conversion for Mandarin TTS

Several methods were developed to improve grapheme-to-phoneme (G2P) conversion models for Chinese text-to-speech (TTS) systems. The critical problem of data sparsity was handled by combining approaches. First, a text-selection method was designed to cover as many G2P text corpus contexts as possible. Then, various data-driven modeling methods were used with comparisons to select the best method for each polyphonic word. Finally, independent models were used for some neutral tone words in addition to the normal G2P models to achieve more compact and flexible G2P models. Tests show that these methods reduce the relative errors by 50% for both normal polyphonic words and Chinese neutral tones.