Articulatory control of HMM-based parametric speech synthesis driven by phonetic knowledge
Articulatory control of HMM-based parametric speech synthesis driven by phonetic knowledge
复制标题
DOI：
10.21437/interspeech.2008-169
复制
发表时间：
2008-09
期刊：
影响因子：
--
通讯作者：
Zhenhua Ling;Korin Richmond;J. Yamagishi;Ren-Hua Wang
中科院分区：
文献类型：
--
作者：
Zhenhua Ling;Korin Richmond;J. Yamagishi;Ren-Hua Wang
本文提出了一种通过将发音特征集成到基于隐马尔可夫模型（HMM）的参数化语音合成系统中来灵活控制合成语音特征的方法。与用于说话风格控制的模型自适应和插值方法相比，该方法由语音知识驱动，并且不需要目标语音样本。估计考虑跨流特征依赖性的并行声学和发音特征的联合分布。在合成时，根据最大似然标准同时生成声学和发音特征。通过在参数生成过程中根据任意语音规则修改生成的发音特征，可以灵活地控制合成语音。我们的实验表明，所提出的方法在改变合成语音的整体特征和控制特定元音的质量方面都是有效的。
This paper presents a method to control the characteristics of synthetic speech flexibly by integrating articulatory features into a Hidden Markov Model (HMM)-based parametric speech synthesis system. In contrast to model adaptation and interpolation approaches for speaking style control, this method is driven by phonetic knowledge, and target speech samples are not required. The joint distribution of parallel acoustic and articulatory features considering cross-stream feature dependency is estimated. At synthesis time, acoustic and articulatory features are generated simultaneously based on the maximum-likelihood criterion. The synthetic speech can be controlled flexibly by modifying the generated articulatory features according to arbitrary phonetic rules in the parameter generation process. Our experiments show that the proposed method is effective in both changing the overall character of synthesized speech and in controlling the quality of a specific vowel.