• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Symposium on Chinese Spoken Language Processing >Superpositional HMM-based intonation synthesis using a functional F0 model
【24h】

Superpositional HMM-based intonation synthesis using a functional F0 model

机译：使用功能性F0模型的基于HMM的重叠语调合成

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper addresses intonation synthesis combining statistical and functional approach with manipulation of fundamental frequency (F) contours in HMM-based speech synthesis. An F contour is represented as a sum of micro, accent, and register components at the logarithmic scale, which is rooted in the Fujisaki model. Separated context-dependent (CD) HMMs are trained for each type of components extracted from a speech corpus based on a functional F model. At the phase of synthesis, CDHMM-generated micro, accent, and register components are superimposed to form F contours for input text. Objective and subjective evaluations are carried out on a Japanese speech corpus. Compared with the conventional approach, this method not only demonstrates the improved performance in naturalness of synthetic speech by achieving better global F behaviors but also shows its flexibility for intonation manipulation through modifying the functional model parameters.
机译：本文讨论了语调合成，该方法在基于HMM的语音合成中将统计和功能方法与基本频率（F）轮廓的处理相结合。 F轮廓表示为对数刻度上的微型，重音和配准分量的总和，植根于Fujisaki模型。基于功能性F模型，针对从语音语料库中提取的每种类型的成分，对分离的上下文相关（CD）HMM进行训练。在合成阶段，将CDHMM生成的微，重音和套准分量叠加起来，以形成用于输入文本的F轮廓。对日语言语语料库进行客观和主观评估。与传统方法相比，该方法不仅通过实现更好的全局F行为展示了合成语音自然性方面的改进性能，而且还通过修改功能模型参数展示了其在语调操纵方面的灵活性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号