Voice Conversion Based on Style and Content Separation with Dual Latent Variable Model

摘要：

This paper presents a novel method for voice conversion based on style and content separation, which is solved by using dual latent variable model (D-LVM). Based on D-LVM, the vocal tract spectrum of speech represented by line spectral frequencies (LSF) is explicitly decomposed into so-called style and content factors, which are used to represent the speech meaning and the speaker individuality respectively. On the basis of reasonable separation of style and content for speech, voice conversion is performed successfully by reproducing converted speech using the initial speech content and the target speaker style. The objective and subjective tests show that, under the condition of limited training dataset, the method proposed in the paper gets better conversion performance compared to the conventional mapping based GMM system and SVD based bilinear model.

关键词： voice conversion style and content separation latent variable model

作者: Xinjian Sun Xiongwei Zhang Jian Sun

作者单位: Institute of Communication Engineering PLA Univ. Of Sci. & Tech.Nanjing, China Institute of Command Automation PLA Univ. Of Sci. & Tech.Nanjing, China Institute of Communication Engineering PLA Univ. of Sci. & Tech. Nanjing, China

会议类型: 国际会议

会议名称: 2011年无线通信与信号处理国际会议(WCSP 2011)

会议地点: 南京

会议语种:英文

页码: 1-5

在线出版日期: 2011-11-09（万方平台首次上网日期，不代表论文的发表时间）