We present a modification to the spectrum differential based direct waveform modification for voice conversion (DIFFVC) so that it can be directly applied as a waveform generation module to voice conversion models. The recently proposed DIFFVC avoids the use of a vocoder, meanwhile preserves rich spectral details hence capable of generating high quality converted voice. To apply the DIFFVC framework, a model that can estimate the spectral differential from the F0 transformed input speech needs to be trained beforehand. This requirement imposes several constraints, including a limitation on the estimation model to parallel training and the need of extra training on each conversion pair, which make DIFFVC inflexible. Based on the above motivations, we propose a new DIFFVC framework based on an F0 transformation in the residual domain. By performing inverse filtering on the input signal followed by synthesis filtering on the F0 transformed residual signal using the converted spectral features directly, the spectral conversion model does not need to be retrained or capable of predicting the spectral differential. We describe several details that need to be taken care of under this modification, and by applying our proposed method to a non-parallel, variational autoencoder (VAE)-based spectral conversion model, we demonstrate that this framework can be generalized to any spectral conversion model, and experimental evaluations show that it can outperform a baseline framework whose waveform generation process is carried out by a vocoder.
Cite as: Huang, W.-C., Wu, Y.-C., Kobayashi, K., Peng, Y.-H., Hwang, H.-T., Lumban Tobing, P., Tsao, Y., Wang, H.-M., Toda, T. (2019) Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion. Proc. 10th ISCA Workshop on Speech Synthesis (SSW 10), 57-62, doi: 10.21437/SSW.2019-11
@inproceedings{huang19_ssw,
author={Wen-Chin Huang and Yi-Chiao Wu and Kazuhiro Kobayashi and Yu-Huai Peng and Hsin-Te Hwang and Patrick {Lumban Tobing} and Yu Tsao and Hsin-Min Wang and Tomoki Toda},
title={{Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion}},
year=2019,
booktitle={Proc. 10th ISCA Workshop on Speech Synthesis (SSW 10)},
pages={57--62},
doi={10.21437/SSW.2019-11}
}