@inproceedings{f6b207abd65e4573a2f1bc86736136b6,
title = "Exemplar-based sparse representation of timbre and prosody for voice conversion",
abstract = "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 timbre conversion and prosody conversions. The experiment results show that, in addition to the conversion of spectral features, the proper conversion of prosody features will improve the quality and speaker identity of the converted speech.",
keywords = "exemplar, prosody, sparse representation, timbre, Voice conversion",
author = "Huaiping Ming and Dongyan Huang and Lei Xie and Shaofei Zhang and Minghui Dong and Haizhou Li",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",
year = "2016",
month = may,
day = "18",
doi = "10.1109/ICASSP.2016.7472664",
language = "英语",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5175--5179",
booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",
}