Speech parameter generation algorithms for HMM-based speech synthesis
Speech parameter generation algorithms for HMM-based speech synthesis
复制标题
DOI：
10.1109/icassp.2000.861820
复制
发表时间：
2000-06
期刊：
影响因子：
--
通讯作者：
K. Tokuda;Takayoshi Yoshimura;T. Masuko;Takao Kobayashi;T. Kitamura
中科院分区：
文献类型：
--
作者：
K. Tokuda;Takayoshi Yoshimura;T. Masuko;Takao Kobayashi;T. Kitamura
本文推导了一种基于隐马尔可夫模型的语音合成参数生成算法，该算法由隐马尔可夫模型生成语音参数序列，该隐马尔可夫模型的观测向量由谱参数向量及其动态特征向量组成。在该算法中，我们假设状态序列(多混合情况下的状态和混合序列)或状态序列的一部分是不可观测的(即隐藏或潜在的)。结果，在给定状态序列的情况下，该算法迭代前向-后向算法和参数生成算法。实验结果表明，与单一混合隐马尔可夫模型相比，该算法可以从多个混合隐马尔可夫模型中再现清晰的共振峰结构。
This paper derives a speech parameter generation algorithm for HMM-based speech synthesis, in which the speech parameter sequence is generated from HMMs whose observation vector consists of a spectral parameter vector and its dynamic feature vectors. In the algorithm, we assume that the state sequence (state and mixture sequence for the multi-mixture case) or a part of the state sequence is unobservable (i.e., hidden or latent). As a result, the algorithm iterates the forward-backward algorithm and the parameter generation algorithm for the case where the state sequence is given. Experimental results show that by using the algorithm, we can reproduce clear formant structure from multi-mixture HMMs as compared with that produced from single-mixture HMMs.