Konstantin Mihhailov

Papers

Total Citations

H-Index

About

Konstantin Mihhailov is a pioneering researcher at the intersection of human-robot interaction and multimodal machine learning, with a primary focus on audio-visual speech recognition (AVSR). His work addresses a critical gap in social robotics: enabling robots to understand speech in noisy, real-world environments by integrating visual lip-reading cues with traditional audio signals. In his landmark 2024 feasibility study—which has already garnered early citations—Mihhailov demonstrated that state-of-the-art visual speech recognition models, typically validated on benchmark datasets like LRS3, can be effectively adapted for social robotic platforms. This contribution is foundational for making robots more robust and accessible in everyday settings, where background noise often degrades audio-only systems. By bridging the gap between controlled academic datasets and practical deployment, Mihhailov’s work has immediate implications for assistive technologies, service robots, and inclusive communication tools. His research not only advances the technical frontier of AVSR but also underscores the importance of human-centered design in robotics, positioning him as a key voice in the next generation of socially intelligent machines.