F
Fuji Ren
Researcher at University of Tokushima
Publications - 622
Citations - 6519
Fuji Ren is an academic researcher from University of Tokushima. The author has contributed to research in topics: Sentence & Machine translation. The author has an hindex of 30, co-authored 579 publications receiving 4966 citations. Previous affiliations of Fuji Ren include Hiroshima City University & Beijing University of Posts and Telecommunications.
Papers
More filters
Proceedings ArticleDOI
To define the feature function in extracting Japanese-Chinese bilingual word pairs using maximum entropy modeling
TL;DR: A learning and extracting method of bilingual word pairs from parallel corpora using the maximum entropy modeling is used to construct a translation dictionary used in multilingual natural language processing such as machine translation.
Proceedings Article
Construction and evaluation of Chinese emotion classification model
Yu Zhang,Fuji Ren,Shingo Kuroiwa +2 more
TL;DR: This study focuses on the semi-automatic acquisition technique to obtain the emotion information with the constructed emotion thesaurus and set up a model to recognize the object sentence including functions of lexical analysis syntax analysis, emotion sensing and emotion computing.
Proceedings ArticleDOI
Facial expression recognition based on multi-scale vector triangle
TL;DR: Experimental results indicate that this FER method based on multi-scale vector triangle has higher recognition rate and better real-time effect.
Proceedings ArticleDOI
Acoustic model adaptation for coded speech using synthetic speech.
TL;DR: A novel acoustic model adaptation technique which generates “speaker-independent” HMM for the target environment that improves speech recognition performance and does not require any speech data for adaptation.
Proceedings ArticleDOI
A Fusion Decision Method Based on the Dynamic Fuzzy Density Assignment
TL;DR: Experiments on JAFFE and CK databases show that the proposed method can effectively improve the decision performance of fuzzy integral and reduce the interference of unreliable output information to decision.