HMM Based Speech Synthesis with Global Variance Training Method
Although Hidden Markov Model based speech synthesis has been proved to have good performance, there are still some factors which degrade the quality of synthesized speech: vocoder, model accuracy and oversmoothing. Experimental results show that oversmoothing in frequency domain mainly affect the quality of synthesized speech whereas over-smoothing in time domain can nearly be ignored. Time domain over-smoothing is generally caused by model structure accuracy problem and frequency domain over-smoothing is caused by training algorithm accuracy problem. MLestimation based parameter training algorithm causes distortion of perception in speech synthesis. The talk will introduce a Global Variance (FV) based Training method into the HTS training structure. The new method tries to enlarge the variance of the spectrum and FO generation. The experiments show that the method improves the synthesizing performance both in voice quality and the expressiveness.
Jianhua Tao
Institute of Automation Chinese Academy of Sciences, China
国际会议
2010 4th International Universal Communication Symposium(第四届国际普遍交流学术研讨会 IUCS 2010)
北京
英文
47
2010-10-18（万方平台首次上网日期，不代表论文的发表时间）