Pronunciation variation generation for spontaneous speech synthesis using state-based voice transformation
Pronunciation variation generation for spontaneous speech synthesis using state-based voice transformation
复制标题
使用基于状态的语音变换生成自发语音合成的发音变化
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Jun Guo
中科院分区：
文献类型：
--
作者：
Chung;Chung;Jun Guo
本文提出了一种基于隐马尔可夫模型（HMM）的语音合成方法。语音变异普遍存在于自然言语中，对自然言语的表达起着重要的作用。在这项研究中，一个基于状态的转换函数被用来模拟读语音和相应的发音变化的自发语音之间的关系。然后使用变换函数来生成基于状态的发音变化。由于缺乏训练数据，发音特征用于使用分类和回归树（CART）对变换函数进行聚类，使得可以从同一聚类中的变换函数生成具有相同发音特征的看不见的发音变化。客观和主观的测试进行评估所提出的方法的性能。实验结果表明，所提出的转换函数在合成语音的自发性方面有了明显的改善。
This study presents an approach to Hidden Markov Models (HMM)-based spontaneous speech synthesis with pronunciation variation for better spontaneity. Pronunciation variation generally occurs in spontaneous speech and plays an important role in expressing the spontaneity. In this study, a state-based transformation function is adopted to model the relation between read speech and the corresponding spontaneous speech with pronunciation variations. The transformation function is then used to generate the state-based pronunciation variations. Due to the lack of training data, the articulatory features are used to cluster the transformation functions using Classification and Regression Trees (CARTs) such that the unseen pronunciation variation with the same articulatory features can be generated from the transformation function in the same cluster. Objective and subjective tests are conducted to evaluate the performance of the proposed approach. The experimental results show that the proposed transformation function achieves a significant improvement on spontaneity in synthesized speech.
DOI：
10.21437/interspeech.2008-169
发表时间：
2008-09
期刊：
--
影响因子：
--
作者：
Zhenhua Ling;Korin Richmond;J. Yamagishi;Ren-Hua Wang
通讯作者：
Zhenhua Ling;Korin Richmond;J. Yamagishi;Ren-Hua Wang