Art

J-GLOBAL ID：201802248410290162   Reference number：18A0852239

Articulatory-to-acoustic conversion using BLSTM-RNNs with augmented input representation

拡張入力表現によるBLSTM-RNNを用いた調音-音響変換【JST・京大機械翻訳】

Author (3)： Liu Zheng-Chen (National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, AnHui 230027, PR China) ,  Ling Zhen-Hua (National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, AnHui 230027, PR China) ,  Dai Li-Rong (National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, AnHui 230027, PR China)
Material： Speech Communication  (Speech Commun)
Volume： 99  Page： 161-172  Publication year： 2018 
JST Material Number： W1590A  ISSN： 0167-6393  Document type： Article
Article type： 原著論文  Country of issue： Netherlands (NLD)  Language： ENGLISH (EN)

Abstract/Point： This paper presents a method t...

Register(free) or Log In to access     To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=18A0852239&from=J-GLOBAL&jstjournalNo=W1590A") }}

Thesaurus term： neural network (biomodel) ,  Language ,  phonation ,  vector (mathematics) ,  a posteriori probability ,  phoneme (morpheme) ,  forecast ,  sound wave signal ,  Data Collection ,  *articulation (voice) ,  *Sound ,  reconstitution ,  classifier (sorter)
Semi thesaurus term： Gauss混合モデル ,  音響特徴 , 【Automatic Indexing@JST】

Author keywords (5)： Articulatory-to-acoustic conversion ,  Gaussian mixture model ,  Deep neural network ,  Recurrent neural network ,  Long short-term memory

JST classification (2)： Speach processing  (JE05000E) ,  Pattern recognition  (JE07000S)

Terms in the title (5)： 拡張 ,  表現 ,  RNN ,  調音 ,  音響