...
  • 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 >Hidden-Markov-model based statistical parametric speech synthesis for Marathi with optimal number of hidden states
【24h】

Hidden-Markov-model based statistical parametric speech synthesis for Marathi with optimal number of hidden states

机译：基于隐马尔可夫模型的具有最优隐藏状态数的马拉地语统计参数语音合成

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

Hidden Markov Model and Deep Neural Networks based Statistical Parametric Speech Synthesis systems, gain a significant attention from researchers because of their flexibility in generating speech waveforms in diverse voice qualities as well as in styles. This paper describes HMM-based speech synthesis system (SPSS) for the Marathi language. In proposed synthesis method, speech parameter trajectories used for synthesis are generated from the trained hidden Markov models (HMM). We have recorded our database of 5300 phonetically balanced Marathi sentences to train the context-dependent HMM with five, seven and nine hidden states. The subjective quality measures (MOS and PWP) shows that the HMMs with seven hidden states are capable of giving an adequate quality of synthesized speech as compared to five state and with less time complexity than seven state HMMs. The contextual features used for experimentation are inclusive of a position of an observed phoneme in a respective syllable, word, and sentence.
机译：基于隐马尔可夫模型和基于深度神经网络的统计参数语音合成系统，由于其在生成各种语音质量和样式的语音波形方面具有灵活性，因此受到了研究人员的极大关注。本文介绍了用于Marathi语言的基于HMM的语音合成系统（SPSS）。在提出的合成方法中，用于合成的语音参数轨迹是从训练有素的隐马尔可夫模型（HMM）中生成的。我们已经记录了5300个语音平衡的马拉地语句子数据库，以训练具有五个，七个和九个隐藏状态的依赖于上下文的HMM。主观质量度量（MOS和PWP）显示，与五个状态的HMM相比，具有七个隐藏状态的HMM能够提供足够质量的合成语音，并且时间复杂度更低。用于实验的上下文特征包括观察到的音素在各个音节，单词和句子中的位置。

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