• Dr. SK. Syed Basha
• B. Jaya Rajesh
• K. Jagan Sai
• B. Sujay Kiran
• D. VijayaSree

Abstract—Human emotion recognition is an important part of affective computing, which allows the interpretation of emo- tional states by intelligent systems for better human-computer interaction. Traditional systems of detecting emotions rely mostly on single modality inputs like facial expressions or speech signals which makes them less robust and accurate in real- world applications. This study propose an AI Based Human Emotion Detection system which combines audio based speech emotion recognition and video based facial expression analysis in multimodal way. A decision-level fusion strategy is employed to integrate the emotional information of both modalities to enhance the prediction accuracy and the deep learning method is applied to extract the discriminative features from the speech signals and the facial images. Real-time operation and unfet- tered environments are characteristics of the proposed system. Additionally, the system takes into consideration applications that are related to Autism Spectrum Disorder (ASD), in which a person can have unusual emotional expressions and finding reliable emotion detection may be difficult. Experimental results show that multimodal approach performs significantly better than unimodal approaches with regards to accuracy, stability and robustness. The proposed system has potential applications in education, healthcare, assistive technologies and autism support systems.

Human Emotion Detection, Multimodal Emo- tion Recognition, Facial Expression Analysis, Speech Emotion Recognition, Autism Spectrum Disorder, Deep Learning.

"AI BASED HUMAN EMOTION DETECTOR FOR REAL-TIME APPLICATIONS FACIAL EXPRESSION RECOGNITION USING DEEP LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.d677-d680, March-2026, Available :http://www.jetir.org/papers/JETIR2603384.pdf

"AI BASED HUMAN EMOTION DETECTOR FOR REAL-TIME APPLICATIONS FACIAL EXPRESSION RECOGNITION USING DEEP LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppd677-d680, March-2026, Available at : http://www.jetir.org/papers/JETIR2603384.pdf