作者其他论文
文献详情
Exemplar-based sparse representation of timbre and prosody for voice conversion
文献类型:会议
作者:Ming, Huaiping[1]  Huang, Dongyan[2]  Xie, Lei[3]  Zhang, Shaofei[4]  Dong, Minghui[5]  Li, Haizhou[6]  
机构:[1]School of Computer Science, Northwestern Polytechnical University, Xi'an, China |Institute for Infocomm Research, ASTAR, Singapore, Singapore
[2]Institute for Infocomm Research, ASTAR, Singapore, Singapore
[3]School of Computer Science, Northwestern Polytechnical University, Xi'an, China
[4]School of Computer Science, Northwestern Polytechnical University, Xi'an, China
[5]Institute for Infocomm Research, ASTAR, Singapore, Singapore
[6]Institute for Infocomm Research, ASTAR, Singapore, Singapore
年:2016
会议名称:41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
页码范围:5175-5179
会议地点:Shanghai, China
会议开始日期:2016-05-18
会议结束日期:2016-03-25
收录情况:EI(20162402488689)  
所属部门:计算机学院
人气指数:1132
浏览次数:1112
语言:外文
摘要:
Voice conversion (VC) aims to make one speaker (source) to sound like spoken by another speaker (target) without changing the language content. Most of the state-of-the-art voice conversion systems focus only on timbre conversion. However, the speaker identity is characterized by the source-related cues such as fundamental frequency and energy as well. In this work, we propose an exemplarbased sparse representation of timbre and prosody for voice conversion that does not necessitate separately t ...More
0
评论(0 条评论)
登录