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
Proceedings Article
Intervention Force-based Imitation Learning for Autonomous Navigation in Dynamic Environments
TL;DR: In this article, the authors proposed an online sampling method for acquiring correction data that is safe and effective, which uses a device that detects the force applied a steering wheel and accelerator pedal during an intervention.
Journal Article
Investigation of DNN-Based Audio-Visual Speech Recognition (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Satoshi Tamura,Hiroshi Ninomiya,Norihide Kitaoka,Shin Osuga,Yurie Iribe,Kazuya Takeda,Satoru Hayamizu +6 more
TL;DR: In this paper, the authors investigated and compared several DNN-based audio-visual speech recognition (AVSR) methods to mainly clarify how we should incorporate audio and visual modalities using DNNs.
Proceedings ArticleDOI
Analyzing grasping for inferring cognitive states of users
TL;DR: The results show that the user's cognition for tasks reflects the grasp forms and the possible size of object movement.
R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut
TL;DR: In this paper , two modules are introduced to enhance the explainability of Transformer-based image classification models: Relationship Weighted Out and Cut modules, which extract class-specific information from intermediate layers, enabling them to highlight relevant features.
Proceedings ArticleDOI
SecretSign: A Method of Finding an Off-Line Target Object without Revealing the Target to Observers
TL;DR: An interactive system that allows only the owner of a target object to secretly find it among other similar or identical objects, which is called SecretSign, and experimentally evaluated the system and verified that SecretSign enabled users to quickly find their target objects without revealing the target to observers.