• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International journal of speech technology >F_0 contour generation and synthesis using Bengali Hmm-based speech synthesis system
【24h】

F_0 contour generation and synthesis using Bengali Hmm-based speech synthesis system

机译：使用基于孟加拉语Hmm的语音合成系统进行F_0轮廓生成和合成

获取原文
获取原文并翻译 | 示例
       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

HMM based Bengali speech synthesis system (Bengali-HTS) generates highly intelligible synthesized speech but its naturalness is not adequate even though it is trained with a very good amount of speech corpus. In case of interrogative, imperative and exclamatory sentences, naturalness of the synthesized speech falls drastically. This paper proposes a method to overcome this problem by modifying the Fo contour of synthetic speech based on Fujisaki model. The Fujisaki model features for different types of Bengali sentences are analyzed for the generation of F_0 contour. These features depend on prosodic word/phrase boundary of the sentence. So a two layer supervised classification and regression tree is trained to predict the prosodic word/phrase boundary. Fujisaki model then generates Fo contour from input text using the prosodic word/phrase boundary and segmen-tal duration information from HMM-based speech synthesis system. Moreover, for HMM training purpose, prosodic structure of sentence has been employed rather than lexical structure. From MOS and preference test it is found that proposed method significantly improved the overall quality of synthesized speech than that of Bengali-HTS.
机译：基于HMM的孟加拉语语音合成系统（Bengali-HTS）生成高度可理解的合成语音，但是即使使用大量语音语料进行训练，其自然性也不足。在疑问句，命令句和感叹词的情况下，合成语音的自然性急剧下降。本文提出了一种基于Fujisaki模型的修正合成语音的Fo轮廓的方法。分析了不同类型的孟加拉语句子的Fujisaki模型特征，以生成F_0轮廓。这些特征取决于句子的韵律词/短语边界。因此，训练了两层监督分类和回归树来预测韵律词/短语边界。然后，Fujisaki模型使用韵律词/短语边界和基于HMM的语音合成系统的段持续时间信息，从输入文本生成Fo轮廓。此外，出于HMM训练的目的，已采用句子的韵律结构而不是词汇结构。通过MOS和偏好测试发现，所提出的方法比Bengali-HTS显着提高了合成语音的整体质量。

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