Art

J-GLOBAL ID：202002261523928973   Reference number：20A1614274

Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks

畳込みニューラルネットワークに基づく高速で高品質歌声合成システム【JST・京大機械翻訳】

Author (6)： Nakamura Kazuhiro (Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan) ,  Takaki Shinji (Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan) ,  Hashimoto Kei (Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan) ,  Oura Keiichiro (Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan) ,  Nankaku Yoshihiko (Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan) ,  Tokuda Keiichi (Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan)
Material： IEEE Conference Proceedings  (IEEE Conf Proc)
Volume： 2020  Issue： ICASSP  Page： 7239-7243  Publication year： 2020 
JST Material Number： W2441A  Document type： Proceedings
Article type： 原著論文  Country of issue： United States (USA)  Language： ENGLISH (EN)

Abstract/Point： The present paper describes si...

Register(free) or Log In to access     To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=20A1614274&from=J-GLOBAL&jstjournalNo=W2441A") }}

Thesaurus term： algorithm ,  speech synthesis ,  Music ,  *Sound ,  Phenotype ,  computational complexity ,  speech synthesizer ,  high quality ,  *singing voice ,  deep neural network ,  *convolutional neuralnetwork
Semi thesaurus term： 自然性 ,  音響特徴 ,  *歌声合成 , 【Automatic Indexing@JST】

JST classification (1)： Graphic and image processing in general  (JE04010I)

Terms in the title (3)： 畳込みニューラルネットワーク ,  高品質 ,  歌声合成