@inproceedings{957f8b38ebd8490b92207b503c27320f,
title = "Pitch transformation in neural network based voice conversion",
abstract = "In voice conversion task, prosody conversion especially pitch conversion is a very challenging research topic because of the discontinuity property of pitch. Conventionally pitch conversion is always achieved by adjusting the mean and variance of the source pitch distribution to the target pitch distribution. This method removes most of the detailed information of the speaker's prosody and only maintains the global F0 contour. In this paper, we propose a neural network based pitch conversion system which converts F0 and spectral features all together frame by frame. Experimental results show that neural network based pitch conversion can significantly reduce the Unvoiced/Voiced error and RMSE of F0 between converted pitch and target pitch compared with the conventional Gaussian normalized transformation method. Wavelet decomposition for F0 can further improve the performance of voice conversion.",
keywords = "neural network, pitch, voice conversion",
author = "Xie, \{Feng Long\} and Yao Qian and Soong, \{Frank K.\} and Haifeng Li",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014 ; Conference date: 12-09-2014 Through 14-09-2014",
year = "2014",
month = oct,
day = "24",
doi = "10.1109/ISCSLP.2014.6936599",
language = "英语",
series = "Proceedings of the 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "197--200",
editor = "Minghui Dong and Jianhua Tao and Haizhou Li and Zheng, \{Thomas Fang\} and Yanfeng Lu",
booktitle = "Proceedings of the 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014",
address = "美国",
}