HSMM-Based Model Adaptation Algorithms for Average-Voice-Based Speech Synthesis
HSMM-Based Model Adaptation Algorithms for Average-Voice-Based Speech Synthesis
复制标题
DOI：
10.1109/icassp.2006.1659961
复制
发表时间：
2006-05
期刊：
影响因子：
--
通讯作者：
J. Yamagishi;Katsumi Ogata;Yuji Nakano;Juri Isogai;Takao Kobayashi
中科院分区：
文献类型：
--
作者：
J. Yamagishi;Katsumi Ogata;Yuji Nakano;Juri Isogai;Takao Kobayashi
在基于隐马尔可夫模型的语音合成中，我们必须根据可用的语音数据量来选择语音合成单元的建模策略，以生成质量更好的合成语音。一般而言，说话人相关建模是大语音数据的理想选择，而当目标说话人的可用语音数据有限时，采用平均语音模型的说话人自适应变得很有希望。本文描述了几种说话人自适应算法和映射修改，以开发出统一的语音合成方法，以适应任意数量的语音数据。我们将这些自适应算法集成到我们的基于HsMM的语音合成系统中，并通过几个评估测试的结果表明了它的有效性
In HMM-based speech synthesis, we have to choose the modeling strategy for speech synthesis units depending on the amount of available speech data to generate synthetic speech of better quality. In general, speaker-dependent modeling is an ideal choice for a large speech data, whereas speaker adaptation with average voice model becomes promising when available speech data of a target speaker is limited. This paper describes several speaker adaptation algorithms and MAP modification to develop consistent method for synthesizing speech in a unified way for arbitrary amount of the speech data. We incorporate these adaptation algorithms into our HSMM-based speech synthesis system and show its effectiveness from results of several evaluation tests