Yasuo Ariki
Papers
8
Total Citations
49
H-Index
5
About
Yasuo Ariki is a leading researcher in human-robot interaction, speech processing, and computer vision, whose work bridges the gap between natural communication and autonomous robotic systems. His most influential contributions focus on enabling robots to understand and respond to human speech in real-world environments. Ariki pioneered techniques for **system request utterance detection**, developing acoustic and linguistic feature-based methods that allow robots to distinguish commands from casual conversation—a critical capability for hands-free, intuitive interfaces. His work on multi-resolution Gabor wavelet features and acoustic analysis has been cited over 30 times, forming a foundation for non-expert robot control. In computer vision, Ariki advanced **generic object recognition** using Conditional Random Fields (CRF) and graph structural expressions, integrating bag-of-features models to improve robotic perception. He also explored multimodal integration, combining speech and image recognition for disambiguation in unknown object detection, with applications in assistive robotics. His research, spanning from 2008 to 2013, has directly influenced the development of mobile robots capable of serving people in dynamic settings like living rooms and parties. Ariki’s work remains essential for students and engineers building socially aware, speech-driven robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Generic object recognition by graph structural expression5 citations · 2012
- 6
- 7Object Recognition by Integrated Information Using Web Images3 citations · 2013
- 8