@inproceedings{69b4924e4abb4bfb92a9ca62d92eb440,
title = "Fundamental frequency modeling using wavelets for emotional voice conversion",
abstract = "This paper is to show a representation of fundamental frequency (F0) using continuous wavelet transform (CWT) for prosody modeling in emotion conversion. Emotional conversion aims at converting speech from one emotion state to another. Specifically, we use CWT to decompose F0 into a five-scale representation that corresponds to five temporal scales. A neutral voice is converted to an emotional voice under an exemplar-based voice conversion framework, where both spectrum and F0 are simultaneously converted. The simulation results demonstrate that the dynamics of F0 in different temporal scales can be well captured and converted using the five-scale CWT representation. The converted speech signals are evaluated both objectively and subjectively, that confirm the effectiveness of the proposed method.",
keywords = "emotion, prosody, sparse representation, Voice conversion",
author = "Huaiping Ming and Dongyan Huang and Minghui Dong and Haizhou Li and Lei Xie and Shaofei Zhang",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 International Conference on Affective Computing and Intelligent Interaction, ACII 2015 ; Conference date: 21-09-2015 Through 24-09-2015",
year = "2015",
month = dec,
day = "2",
doi = "10.1109/ACII.2015.7344665",
language = "英语",
series = "2015 International Conference on Affective Computing and Intelligent Interaction, ACII 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "804--809",
booktitle = "2015 International Conference on Affective Computing and Intelligent Interaction, ACII 2015",
}