Roel Van De Laar
Papers
1
Total Citations
3
H-Index
1
About
Dr. Roel Van De Laar is a leading researcher at the intersection of human-robot interaction and multimodal perception, with a primary focus on audio-visual speech recognition (AVSR) for social robotics. His most notable contribution, detailed in his highly cited 2024 work "Audio-Visual Speech Recognition for Human-Robot Interaction: a Feasibility Study," addresses a critical gap in the field: while visual speech recognition (VSR) models have advanced significantly on standard datasets like LRS3 and LRS2, they have rarely been deployed on social robots operating in real-world, noisy environments. Van De Laar’s pioneering study demonstrates the feasibility of integrating AVSR into robotic platforms, showing how combining auditory and visual cues can dramatically improve speech recognition accuracy when audio is degraded—a common challenge for robots in dynamic social settings. This work has already garnered 3 citations in its first year, signaling its immediate impact. By bridging state-of-the-art machine learning with practical robotics, Van De Laar is paving the way for more robust, natural, and accessible human-robot communication, making him a key figure in the next generation of socially aware AI systems.
Research Focus
Key Achievements
Top Papers
- 1