Synthesis Units for Conversational Speech-Using Phrasal Segments -
Synthesis Units for Conversational Speech-Using Phrasal Segments -
复制标题
DOI：
--
复制
发表时间：
2004
影响因子：
1.1
通讯作者：
N. Campbell
中科院分区：
文献类型：
--
作者：
N. Campbell
本文介绍了使用短语大小的段会话语音的拼接合成，并讨论了选择标准的差异，成为必要时，源语料库包含几年的会话语音样本。它声称，naturalsounding会话语音可以通过使用这样的短语大小的块连接，并在语音中的物理相邻增强连续性的感觉，尽管他们在语料库中的离散起源。
This paper describes the use of phrase-sized segments for the concatenative synthesis of conversational speech and discusses the differences in selection criteria that become necessary when the source corpus contains several years of conversational speech samples. It claims that naturalsounding conversational speech can be reproduced by use of such phrase-sized chunks for concatenation, and that their physical adjacency in the speech enhances the sense of continuity in spite of their discrete origins in the corpus.