Voice conversion using structured Gaussian mixture model in cepstrum eigenspace  

作　　者：LI Yangchun YU Yibiao 

机构地区：[1]School of Electronic and Information Engineering,Soochow University

出　　处：《Chinese Journal of Acoustics》2015年第3期325-336,共12页声学学报（英文版）

基　　金：supported by the Natural Science Foundation of China(61271360);the Application Fundamental Research Project of Suzhou(SYG201230)

摘　　要：A new methodology of voice conversion in cepstrum eigenspace based on structured Gaussian mixture model is proposed for non-parallel corpora without joint training. For each speaker, the cepstrum features of speech are extracted, and mapped to the eigenspace which is formed by eigenvectors of its scatter matrix, thereby the Structured Gaussian Mixture Model in the EigenSpace （SGMM-ES） is trained. The source and target speaker＇s SGMM-ES are matched based on Acoustic Universal Structure （AUS） principle to achieve spectrum transform function. Experimental results show the speaker identification rate of conversion speech achieves 95.25%, and the value of average cepstrum distortion is 1.25 which is 0.8% and 7.3% higher than the performance of SGMM method respectively. ABX and MOS evaluations indicate the conversion performance is quite close to the traditional method under the parallel corpora condition. The results show the eigenspace based structured Gaussian mixture model for voice conversion under the non-parallel corpora is effective.A new methodology of voice conversion in cepstrum eigenspace based on structured Gaussian mixture model is proposed for non-parallel corpora without joint training. For each speaker, the cepstrum features of speech are extracted, and mapped to the eigenspace which is formed by eigenvectors of its scatter matrix, thereby the Structured Gaussian Mixture Model in the EigenSpace （SGMM-ES） is trained. The source and target speaker＇s SGMM-ES are matched based on Acoustic Universal Structure （AUS） principle to achieve spectrum transform function. Experimental results show the speaker identification rate of conversion speech achieves 95.25%, and the value of average cepstrum distortion is 1.25 which is 0.8% and 7.3% higher than the performance of SGMM method respectively. ABX and MOS evaluations indicate the conversion performance is quite close to the traditional method under the parallel corpora condition. The results show the eigenspace based structured Gaussian mixture model for voice conversion under the non-parallel corpora is effective.

关 键 词：LPCC Voice conversion using structured Gaussian mixture model in cepstrum eigenspace ES GMM 

分 类 号：TN912.3[电子电信—通信与信息系统]