Kumoh National Institute of Technology

ML-based Emotion-aware Voice User Interface

Multimodal Emotion Recognition

Emotion recognition combining EEG, voice, and camera inputs.

Machine Learning
Data Fusion
Emotion Recognition
EEG
Voice Analysis

ML-based Emotion-aware Voice User Interface — conceptual technical overview — Conceptual overview based on the project description; not a production infrastructure diagram.

Project overview

Multimodal emotion recognition system combining EEG signals, voice analysis, and facial expression recognition. Features real-time emotion detection with edge-cloud processing architecture.

Technical highlights

EEG, voice, and camera data fusion
Real-time emotion detection
Edge-cloud processing architecture
Multimodal machine learning approach

Outcome

Advanced emotion recognition research

Project resources

This page summarizes the project. A public demo or source repository is not available here.

Discuss this project