Quality of Arabic Utterances Transformed Using Different Residual Prediction Techniques

摘要：

Voice conversion (VC) is a process which modifies the speech signal produced by one source speaker so that it sounds like another target speaker. In this paper the transformation is determined by using equal Arabic utterances from source and target speakers; these utterances are time-aligned using dynamic time warping algorithm. A conversion function based on Gaussian mixture model (GMM) is used for transforming the spectral envelope described by line spectral frequencies (LSF) and the residuals are converted using three residual prediction techniques. We also compare between these techniques in the conversion of some Arabic utterances. The quality of the transformed utterances is measured using subjective and objective evaluations.

作者: Rania Elmanfaloty N. Korany El-Sayed A. Youssef

作者单位: Electrical Engineering Department Faculty of Engineering Alexandria, Egypt

会议类型: 国际会议

会议名称: 2010 International Conference on Signal and Information Processing(2010年IEEE信号与信息处理国际会议 ICSIP2010)

会议地点: 长沙

会议语种:英文

页码: 71-75

在线出版日期: 2010-12-14（万方平台首次上网日期，不代表论文的发表时间）