raja slot
raja slot
slot deposit pulsa tanpa potongan
slot gacor 2024
raja slot
raja slot
raja slot

REAL TIME EMOTION BASED MUSIC PLAYER USING CNN ARCHITECTURES


Asst Prof. Mrs. Indumathi S K, Sireesha K, Kavan MC
Student, Dr.Ambedkar Institute of technology
Abstract
Emotion detection is the process of detecting a human being’s emotions based on various facial cues and visual information. This field has gained much traction since the popularity of deep learning. Emotion detection has also given rise to many applications that had not been thought of before. One of the areas that are heavily associated with emotions is music. Music can invoke particular emotions of the listener, and a person feeling a certain emotion would look for a similar song. We use our emotion detection model to associate these emotions with a music player that plays music that accompanies user experiences. The model we designed includes two convolutional neural networks (CNN) models: a five-layer model and a global average pooling (GAP) model. We combined these CNN models with transfer-learning models. For our transfer-learning models, we used three pre-trained models: ResNet50; SeNet50; VGG16. Our results are comparable with the state-of-the-art models; however, our models are more efficient in performance.
Keywords: Class Weighting, Convolutional Neural Network, Emotion Detection, Ensemble, Global Average Pooling, Transfer Learning
Journal Name :
EPRA International Journal of Multidisciplinary Research (IJMR)

VIEW PDF
Published on : 2022-07-26

Vol : 8
Issue : 7
Month : July
Year : 2022
Copyright © 2024 EPRA JOURNALS. All rights reserved
Developed by Peace Soft raja slot