文献类型：期刊文献

中文题名：一种基于预测谱偏移的自适应高斯混合模型在语音转换中的应用

英文题名：An Adaptive Gaussian Mixed Model Based on Predictive Spectral Shift and Its Application in Voice Conversion

作者：沈惠玲[1];万永菁[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2017

卷号：43

期号：4

起止页码：546

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：北大核心:【北大核心2014】；CSCD:【CSCD_E2017_2018】；

语种：中文

中文关键词：语音转换;高斯混合模型;预测谱偏移;自适应

外文关键词：voice conversion;;Gaussian mixed model;;predictive spectral shift;;adaptive

摘要：基于高斯混合模型(GMM)的语音帧谱包络转换算法容易导致转换后的语音谱包络过平滑、语音细节特征受损。通过对GMM中协方差的准确性与谱包络过平滑现象的研究,提出了一种基于预测谱偏移的自适应GMM建模方法。该方法采用平滑加权算法对目标谱的偏移进行建模,并根据语音帧信息自适应调节预测谱偏移项的比例系数,结合高斯混合模型共同实现对谱包络的转换。实验结果表明,该建模方法能够有效抑制转换后语音谱包络的失真现象,提高转换后语音的清晰度、自然度和可懂度。
Voice conversion algorithm based on Gaussian mixture model(GMM)may result in the oversmoothing of spectral envelop and the damage of speech feature.By analyzing the relationship between covariance's accuracy and over-smoothed phenomena,this paper proposes an adaptive GMM conversion algorithm based on spectral shift,which uses the weighted average algorithm to predict the converted spectral shift.Both the proposed spectral shift and the GMM are adopted to realize the appropriate converted spectral sequence.Moreover,the spectral shift proportion and GMM correlation are adaptively adjusted by using the spectral parameter.The experiment results show that the proposed algorithm can effectively alleviate the over-smoothing and improve the clearness naturalness and intelligibility of converted voice.