Art

J-GLOBAL ID：202102266209211316   Reference number：21A0423764

深層パーセプトロンの単位初期化に基づく中間層の貢献度と尤度の解析

Author (4)： KUBOTA SHOHEI (九大) ,  HAYASHI HIDEAKI (九大) ,  HAYASE TOMOHIRO (富士通研究所 人工知能研) ,  UCHIDA SEIICHI (九大)
Material： 電子情報通信学会技術研究報告(Web)  (IEICE Technical Report (Web))
Volume： 120  Issue： 300(PRMU2020 38-68)  Page： 161-165 (WEB ONLY)  Publication year： Dec. 10, 2020 
JST Material Number： U2030A  ISSN： 2432-6380  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *multilayer perceptron ,...
Semi thesaurus term： deep neural network ,...

Register(free) or Log In to access     To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=21A0423764&from=J-GLOBAL&jstjournalNo=U2030A") }}

JST classification (2)： Pattern recognition  (JE07000S) ,  Brain and nervous system models  (EL02050C)

Reference (17)：

• Shiliang Zhang, Ming Lei, Bin Ma, and Lei Xie. Robust audio-visual speech recognition using bimodal DFSMN with multi-condition training and dropout regularization. In Proc. ICASSP, pages 6570-6574,2019.
• Stefan Braun and Shih-Chii Liu. Parameter uncertainty for end-to-end speech recognition. In Proc. ICASSP, pages 5636-5640, 2019.
• Shiliang Zhang, Ming Lei, Yuan Liu, and Wei Li. Investigation of modeling units for mandarin speech recognition using DFSMN-CTCSMBR. In Proc. ICASSP, pages 7085-7089, 2019.
• Qian-Bei Hong, Chung-Hsien Wu, Hsin-Min Wang, and Chien-Lin Huang. Combining deep embeddings of acoustic and articulatory features for speaker identification. In Proc. ICASSP, pages 7589-7593,2020.
• Srinidhi Hegde, Ranjitha Prasad, Ramya Hebbalaguppe, and Vishwajeet Kumar. Variational student: Learning compact and sparser networks in knowledge distillation framework. In Proc. ICASSP, pages 3247-3251, 2020.

Terms in the title (6)： 深層 ,  パーセプトロン ,  初期化 ,  中間層 ,  尤度 ,  解析