F
Fumitada Itakura
Researcher at Meijo University
Publications - 26
Citations - 668
Fumitada Itakura is an academic researcher from Meijo University. The author has contributed to research in topics: Speech enhancement & Speech processing. The author has an hindex of 10, co-authored 26 publications receiving 592 citations.
Papers
More filters
Journal ArticleDOI
Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification
Chiyomi Miyajima,Yoshihiro Nishiwaki,K. Ozawa,Toshihiro Wakita,Katsunobu Itou,Kazuya Takeda,Fumitada Itakura +6 more
TL;DR: In this article, the relationship between following distance and velocity mapped into a two-dimensional space is modeled for each driver with an optimal velocity model approximated by a nonlinear function or with a statistical method of a Gaussian mixture model (GMM).
Journal ArticleDOI
Driver Identification Using Driving Behavior Signals
Toshihiro Wakita,K. Ozawa,Chiyomi Miyajima,Kei Igarashi,Katsunobu Itou,Kazuya Takeda,Fumitada Itakura +6 more
TL;DR: A driver identification method based on the driving behavior signals that are observed while the driver is following another vehicle is proposed, and the driver's operation signals were found to be better than road environment signals and car behavior signals.
Journal ArticleDOI
Estimation of HRTFs on the horizontal plane using physical features
TL;DR: In this paper, a simpler and more useful method that investigates the relationship between HRTFs and physical size by multiple regression analysis was proposed, which is evaluated by objective and subjective measures.
Proceedings ArticleDOI
Driver identification using driving behavior signals
Toshihiro Wakita,K. Ozawa,Chiyomi Miyajima,Kei Igarashi,Katsunobu Itou,Kazuya Takeda,Fumitada Itakura +6 more
TL;DR: In this paper, a driver identification method is proposed based on the driving behavior signals that are observed while the driver is following another vehicle, such as the use of the accelerator pedal, brake pedal, vehicle velocity, and distance from the vehicle in front.
Proceedings ArticleDOI
Extracting speech features from human speech like noise
TL;DR: It is shown that the amplitude distribution of the difference signal of HSLN approaches the Gaussian distribution from the Gamma distribution as the number of superpositions increase, which clarifies that the temporal change of spectral envelope plays an important roll in discriminating speech from noise.