@inproceedings{fab89d5ce221455488a145f88bf3baf9,
title = "Improving voice quality of HMM-based speech synthesis using voice conversion method",
abstract = "HMM-based speech synthesis system (HTS) often generates buzzy and muffled speech. Such degradation of voice quality makes synthetic speech sound robotically rather than naturally. From this point, we suppose that synthetic speech is in a different speaker space apart from the original. We propose to use voice conversion method to transform synthetic speech toward the original so as to improve its quality. Local linear transformation (LLT) combined with temporal decomposition (TD) is proposed as the conversion method. It can not only ensure smooth spectral conversion but also avoid over-smoothing problem. Moreover, we design a robust spectral selection and modification strategy to make the modified spectra stable. Preference test shows that the proposed method can improve the quality of HMM-based speech synthesis.",
keywords = "HMM-based speech synthesis, local linear transformation, temporal decomposition, voice conversion",
author = "Yishan Jiao and Xiang Xie and Xingyu Na and Ming Tu",
year = "2014",
doi = "10.1109/ICASSP.2014.6855141",
language = "English",
isbn = "9781479928927",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "7914--7918",
booktitle = "2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014",
address = "United States",
note = "2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 ; Conference date: 04-05-2014 Through 09-05-2014",
}