Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/4627
Title: Fusion of Modalities for Emotion Recognition with Deep Learning
Authors: Gyanvarsha, Shourya
Mohanty, Swayamjit
Sahoo, Himanshu Sekhar
Patra, Dipti
Keywords: audio-visual emotion recognition
xlsrWav2Vec2.0 transformer
transfer learning
Action Units
RAVDESS
speech emotion recognition
facial emotion recognition
Issue Date: Jul-2024
Citation: IEEE International Conference on Smart Power Control and Renewable Energy ((ICSPCRE), NIT Rourkela, India, 19-21 July 2024
Abstract: The paper delineates a pioneering advancement in emotion recognition technology, showcasing a sophisticated multimodal system adept at discerning human emotions through the fusion of video, audio, and facial features, facilitated by state-of-the-art deep learning methodologies. By amalgamating information from diverse sensory modalities, the system attains remarkable precision in classifying emotions, surpassing the efficacy of unimodal approaches. Through a comprehensive array of experiments and evaluations, the study substantiates the system’s prowess in accurately deciphering emotional states. Notably, the fusion of multimodal cues enables nuanced insights into human affective responses, transcending the limitations of individual modalities and furnishing a holistic understanding of emotional dynamics.
Description: Copyright belongs to proceeding publisher
URI: http://hdl.handle.net/2080/4627
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2024_ICSPCRE_SGyanvarsha_Fusion.pdf776.6 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.