* PUBLICATIONS - 2020 [#oa1cc30b] #contents ** Journal [#rf3ae6e0] + Shuhei Kato, Yusuke Yasuda, Xin Wang, Erica Cooper, Shinji Takaki, and Junichi Yamagishi, ``Semi-supervised learning based on hierarchical generative models for end-to-end speech synthesis,'' IEEE Access, vol. 8, pp. 138149-1381612020, 27 July 2020. (Full paper peer reviewed) &publication(2020/20200727_Journal_IEEEAccess_Shuhei_Kato_paper, paper); [[link>https://ieeexplore.ieee.org/document/9149598]] ** International Conference [#ida171b8] + %%%Yukiya Hono%%%, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis,'' Interspeech 2020, pp. 3441–3445, Shanghai, China, October, 2020. (Full paper peer reviewed) &publication(2020/20201028_IConference_Interspeech_Yukiya_Hono_paper.pdf, paper); &publication(2020/20201028_IConference_Interspeech_Yukiya_Hono_highlight.pptx, slide (highligh)); &publication(2020/20201028_IConference_Interspeech_Yukiya_Hono_slide.pptx, slide (paper presentation)); &publication(2020/20201028_IConference_Interspeech_Yukiya_Hono_highlight.mp4, video (highlight)); &publication(2020/20201028_IConference_Interspeech_Yukiya_Hono_video.mp4, video (paper presentation); [[link (arXiv)>https://arxiv.org/abs/2009.08474]] + %%%Takato Fujimoto%%%, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Semi-supervised learning based on hierarchical generative models for end-to-end speech synthesis,'' 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 7644-7648, Barcelona, Spain, May, 2020. (Full paper peer reviewed) &publication(2020/20200508_IConference_ICASSP_Takato_Fujimoto_paper.pdf, paper); &publication(2020/20200508_IConference_ICASSP_Takato_Fujimoto_slide.pptx, slide); &publication(2020/20200508_IConference_ICASSP_Takato_Fujimoto_video.mp4, video); + %%%Kazuhiro Nakamura%%%, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Fast and high-quality singing voice synthesis system based on convolutional neural networks,'' 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 7239-7243, Barcelona, Spain, May, 2020. (Full paper peer reviewed) &publication(2020/20200507_IConference_ICASSP_Kazuhiro_Nakamura_paper.pdf, paper); **Past Publications [#m34a47b0] #ls2(HOME/PUBLICATIONS/,reverse);