Prosody control for speaking and singing styles
Prosody control for speaking and singing styles
复制标题
口语和歌唱风格的韵律控制
DOI：
10.21437/eurospeech.2001-175
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
G. Kochanski
中科院分区：
文献类型：
--
作者：
Chilin Shih;G. Kochanski
通过对韵律的适当控制，文语转换系统已经具备了模仿不同说话风格的能力。我们展示了两个例子，我们可以捕捉的关键功能：歌唱风格的黛娜海岸和说话风格的马丁路德金。这些风格由Stem-ML标签（软模板标记语言）描述，它提供了控制语音和唱歌的口音形状、短语音高轮廓和幅度轮廓所需的灵活性。
By proper control of prosody, text-to-speech systems already have the capability to imitate distinctive speaking styles. We show two examples where we can capture the critical features: the singing style of Dinah Shore and the speaking style of Martin Luther King Jr. The styles are described by Stem-ML tags (soft template mark-up language), which offers the flexibility needed to control accent shapes, phrasal pitch contours, and amplitude profiles, for speech as well as for singing.