K
Kazuya Takeda
Researcher at Nagoya University
Publications - 546
Citations - 9667
Kazuya Takeda is an academic researcher from Nagoya University. The author has contributed to research in topics: Speech processing & Speech enhancement. The author has an hindex of 42, co-authored 495 publications receiving 7719 citations. Previous affiliations of Kazuya Takeda include Kobe Women's University & Nara Institute of Science and Technology.
Papers
More filters
Evaluation of Discriminant Analysis-based Feature Transformation and Discriminative Training for Speech Recognition
TL;DR: For feature transformation techniques, the traditional techniques used in speech recognition but also state-of-the-art techniques are evaluated, and the robustness of matched and mismatched noise conditions between training and evaluation environments is investigated.
Journal ArticleDOI
Estimation of speaker and listener positions in a car using binaural signals
Journal ArticleDOI
Flexible prediction of opponent motion with internal representation in interception behavior
TL;DR: In this paper, the response behavior of a pursuer to a sudden directional change of the evasive target was analyzed, and it was shown that the use of internal representations in predicting target motion was computationally feasible and useful even against unknown opponents.
Journal ArticleDOI
Two Cases of ALK Fusion Gene-positive Lung Adenocarcinoma Treated with Brigatinib After Alectinib-induced Interstitial Lung Disease
Yuta Nagahisa,Toshiyuki Sumi,M. Sekikawa,Kazuya Takeda,Keigo Matsuura,Hiroki Watanabe,Yuichi Yamada,Yoshiko Keira,Hirofumi Chiba +8 more
TL;DR: Alectinib is an effective and well-tolerated agent for treating anaplastic lymphoma kinase (ALK) fusion gene-positive lung adenocarcinoma as discussed by the authors .
Proceedings ArticleDOI
An acoustic measure for predicting recognition performance degradation
TL;DR: An acoustic measure for predicting the degradation of speech recognition performance due to noise contamination is developed that takes the spectral shape of the noise into account, and can predict recognition performance directly.