A parameter generation algorithm using local variance for HMM-based speech synthesis
A parameter generation algorithm using local variance for HMM-based speech synthesis
复制标题
基于 HMM 的语音合成中使用局部方差的参数生成算法
DOI：
10.1109/jstsp.2013.2283459
复制
发表时间：
2014
影响因子：
7.5
通讯作者：
Takao Kobayashi
中科院分区：
文献类型：
--
作者：
Takashi Nose;Vataya Chunwijitra;Takao Kobayashi
提出了一种基于局部方差(LV)模型的HMM语音合成参数生成算法。在所提出的技术中，我们将LV定义为表示谱参数序列的局部变化的特征，并使用隐马尔可夫模型来建模LV。上下文相关隐马尔可夫模型用于捕捉LV轨迹对语音和韵律上下文的依赖。此外，考虑了LV的动态特性和静态特性，对LV轨迹的动态特性进行了适当的建模。通过将LV模型引入到谱参数生成过程中，该方法可以对每一帧施加比传统的全局方差(GV)模型更精确的方差约束。因此，所提出的技术缓解了基于GV的参数生成中经常出现的过度的谱峰增强。客观评价结果表明，该方法在频谱和LV失真方面比基于GV的方法能产生更好的频谱参数轨迹。主观评价结果表明，在保持语音自然度的前提下，该方法生成的合成语音更接近原始语音。
This paper proposes a parameter generation algorithm using a local variance (LV) model in HMM-based speech synthesis. In the proposed technique, we define the LV as a feature that represents the local variation of a spectral parameter sequence and model LVs using HMMs. Context-dependent HMMs are used to capture the dependence of LV trajectories on phonetic and prosodic contexts. In addition, the dynamic features of LVs are taken into account as well as the static one to appropriately model the dynamic characteristics of LV trajectories. By introducing the LV model into the spectral parameter generation process, the proposed technique can impose a more precise variance constraint for each frame than the conventional technique with a global variance (GV) model. Consequently, the proposed technique alleviates the excessive spectral peak enhancement that often occurs in GV-based parameter generation. Objective evaluation results show that the proposed technique can generate better spectral parameter trajectories than the GV-based technique in terms of spectral and LV distortion. Moreover, the results of subjective evaluation demonstrate that the proposed technique can generate synthetic speech significantly closer to the original one than the conventional technique while maintaining speech naturalness.