H
Hirokazu Kameoka
Researcher at Nippon Telegraph and Telephone
Publications - 288
Citations - 6183
Hirokazu Kameoka is an academic researcher from Nippon Telegraph and Telephone. The author has contributed to research in topics: Spectrogram & Non-negative matrix factorization. The author has an hindex of 36, co-authored 272 publications receiving 4854 citations. Previous affiliations of Hirokazu Kameoka include NTT Communications Corp & University of Tokyo.
Papers
More filters
Journal ArticleDOI
Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization
TL;DR: This paper addresses the determined blind source separation problem and proposes a new effective method unifying independent vector analysis (IVA) and nonnegative matrix factorization (NMF) based on conventional multichannel NMF (MNMF), which reveals the relationship between MNMF and IVA.
Journal ArticleDOI
Multichannel Extensions of Non-Negative Matrix Factorization With Complex-Valued Data
TL;DR: Experimental results show that the derived multiplicative update rules exhibited good convergence behavior, and BSS tasks for several music sources with two microphones and three instrumental parts were evaluated successfully.
Proceedings ArticleDOI
CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks
Takuhiro Kaneko,Hirokazu Kameoka +1 more
TL;DR: A non-parallel voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data is proposed that is general purpose and high quality and works without any extra data, modules, or alignment procedure.
Proceedings ArticleDOI
StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks
TL;DR: StarGAN-VC as discussed by the authors uses a variant of a generative adversarial network (GAN) called StarGAN to learn many-to-many mappings across different attribute domains using a single generator.
Journal ArticleDOI
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Xin Wang,Junichi Yamagishi,Junichi Yamagishi,Massimiliano Todisco,Héctor Delgado,Andreas Nautsch,Nicholas Evans,Sahidullah,Ville Vestman,Tomi Kinnunen,Kong Aik Lee,Lauri Juvela,Paavo Alku,Yu-Huai Peng,Hsin-Te Hwang,Yu Tsao,Hsin-Min Wang,Sébastien Le Maguer,Markus Becker,Fergus Henderson,Robert A. J. Clark,Yu Zhang,Quan Wang,Ye Jia,Kai Onuma,Koji Mushika,Takashi Kaneda,Yuan Jiang,Li-Juan Liu,Yi-Chiao Wu,Wen-Chin Huang,Tomoki Toda,Kou Tanaka,Hirokazu Kameoka,Ingmar Steiner,Driss Matrouf,Jean-François Bonastre,Avashna Govender,Srikanth Ronanki,Jing-Xuan Zhang,Zhen-Hua Ling +40 more
TL;DR: The ASVspoof challenge as mentioned in this paper was created to foster research on anti-spoofing and to provide common platforms for the assessment and comparison of spoofing countermeasures, and the first edition focused on replay spoofing attacks and countermeasures.