【摘要】 统计参数语音合成中的跨语种模型自适应主要应用于目标说话人语种与源模型语种不同时,使用目标发音人少量语音数据快速构建具有其音色特征的源模型语种合成系统.本文对传统的基于音素映射和三音素模型的跨语种自适应方法进行改进,一方面通过结合数据挑选的音素映射方法以提高音素映射的可靠性,另一方面引入跨语种的韵律信息映射以弥补原有方法中三音素模型在韵律表征上的不足.在中英文跨语种模型自适应系统上的实验结果表明,改进后系统合成语音的自然度与相似度相对传统方法都有了明显提升.更多还原

【Abstract】 Cross-language model adaptation in statistical parametric speech synthesis is used for rapidly constructing a text-to-speech (TTS) system with the target speaker’s characteristics when the source and the target speakers’ languages are different. In this paper, the conventional cross-language adaptation method based on phone-mapping and triphone models is improved by two means. Firstly, phone mapping combined with data-selection is adopted to improve its reliability. Secondly, cross-language prosodic information mapping is introduced to make use of prosodic information, which is ignored in the triphone model. Experiments on Chinese-to-English adaptation show that the synthesized speech using the improved method has much better naturalness and speaker similarity compared with the result of conventional method.更多还原