Max Robotics — Global Service Robot Directory + US Certification

About

Bogdan Mocanu is a rising researcher in affective computing and human-computer interaction, whose work focuses on teaching machines to understand human emotions through speech and facial expressions. His key research areas include multimodal emotion recognition, speech emotion recognition, and voice-based human-computer interaction. Mocanu’s most impactful contribution is his 2023 paper on “Multimodal emotion recognition using cross modal audio-video fusion with attention and deep metric learning,” which has already garnered 119 citations—a strong indicator of its influence in the field. This work pioneers a novel fusion technique that integrates audio and visual cues using attention mechanisms and deep metric learning, significantly improving emotion recognition accuracy. His earlier 2021 paper on “Utterance Level Feature Aggregation with Deep Metric Learning for Speech Emotion Recognition” (23 citations) laid foundational methods for extracting emotional cues from speech. Mocanu has also explored facial emotion recognition using video vision transformers and voice command recognition for human-computer interfaces. His research has practical implications for mental health diagnosis, audio surveillance, and e-learning. By advancing deep learning architectures for emotion understanding, Mocanu is contributing to more empathetic and intuitive human-machine interactions.