Taiki Tezuka
Papers
1
Total Citations
21
H-Index
1
About
Taiki Tezuka’s research centers on robot audition and signal processing, with a particular focus on enabling machines to hear clearly amidst their own operational noise. His major contribution lies in developing advanced noise suppression techniques that allow robots to perceive external sounds without relying on unreliable correlations between joint motion and ego-motion noise. In his seminal 2014 work, “Ego-motion noise suppression for robots based on Semi-Blind Infinite Non-negative Matrix Factorization,” Tezuka introduced a semi-blind approach that leverages non-negative matrix factorization to separate ego-motion noise from target sounds, even when motion data is ambiguous. This paper has garnered 21 citations, reflecting its influence in the field of robotic auditory perception. Tezuka’s work is notable for addressing a critical bottleneck in human-robot interaction: the challenge of a robot hearing its user while moving. By sidestepping traditional motion-based inference, his method offers a more robust solution for real-world applications, from service robots to autonomous systems. His contributions continue to inspire researchers seeking to improve robot listening in noisy, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1