[1] T. Kaneko, H. Kameoka, “Non-Parallel voice conversion using cycle-consistent adversarial networks,” accepted for publication in Proc. 26th European Signal Processing Conference (EUSIPCO 2018).
[2]田中宏, 金子卓弘, 北条伸克, 亀岡弘和, "CycleGANを用いた合成音声から自然音声への波形変換," 日本音響学会2018年春季研究発表会講演論文集, 1-Q-32, pp. 285-286, Mar. 2018.
[3] K. Tanaka, H. Kameoka, Kazuho Morikawa, “VAE-SPACE: Deep generative model of voice fundamental frequency contours,” in Proc. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2018), pp. 5779-5783, Apr. 2018.