汉语情感语音合成的研究
刘震;景新幸;
摘要(Abstract):
本文探讨了一种汉语情感语音合成的方案。首先,根据汉语韵律的分层特点,采用SFC基频时长韵律模型,从语料库中提取出反映汉语情感特征的基频参数和时长参数曲线;然后,采用STRAIGHT语音分析与合成算法,用提取出的反映情感特征的韵律参数控制合成过程,从而合成出带有情感的汉语语音。
关键词(KeyWords): 情感语音合成;韵律模型;基音同步叠加
基金项目(Foundation):
作者(Author): 刘震;景新幸;
Email:
DOI:
参考文献(References):
- [1]Bailly,G.and Holm,B.Learning the hidden structure of speech:from communicative functions to prosody,Cadernos de Estudos Linguisticos,43:p.37-54,2002;
- [2]Gaopeng Chen,A superposed prosodic model for Chinese text-to-speech synthesis,In the International Conference of Chinese Spoken Language Processing,p.177-180,2004;
- [3]Bailly,G.;Holm,B.:SFC:a trainable prosodic model.Speech Commun.46:364-384(2005).
- [4]后旗,俞振利,张礼和.基于TD_PSOLA算法的汉语普通话韵律合成[J].科技通报,18(1),2002:6-9.
- [5]Hideki Kawahara:STRAIGHT,Exploration of the other aspect of VOCODER:Perceptually isomorphic decomposition of speech sounds,Acoustic Science and Technology,Vol.27,No.6,pp.349-353(2006)
- [6]Hideki Kawahara,Ikuyo Masuda-Katsuse,Alain de Cheveigné,Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0extraction:possible role of a repetitive structure in sounds,Speech Communication,v.27n.3-4,p.187-207,April1999.