Thomas Haubner
Papers
1
Total Citations
3
H-Index
1
About
Thomas Haubner is a researcher at the forefront of robot audition and acoustic signal processing, with a primary focus on ego-noise suppression—the challenge of canceling the noise a robot generates through its own movements. His most cited work, "Motor data-regularized nonnegative matrix factorization for ego-noise suppression" (2020), introduces a novel approach that leverages motor data to inform the noise model, enabling more robust and adaptive suppression of self-generated noise. This contribution is critical for enabling robots to interact seamlessly with their environment and humans, as it directly improves the quality of speech and sound captured during motion. While his citation count is still growing, Haubner’s work is foundational for advancing human-robot interaction, particularly in noisy, real-world settings. His research bridges robotics and signal processing, offering practical solutions for autonomous systems that must listen while moving.
Research Focus
Key Achievements
Top Papers
- 1