• ARSHID T M
• A. Selvakumar
• K. Aneesh

A crucial component of human-computer interaction is the capacity to reliably identify and interpret human emotions from audio recordings. The existing system solely relies on a deep learning approach CNN might lose some temporal information important for emotional context during convolution operations. This journal aims at understanding underlying patterns that can lead to resolve many real time problems with the help of hybrid models (CNN-RNN) for better capturing of both spatial and temporal information in audio data for more accurate emotion recognition. Affective computing, mental health, and human computer interaction are just a few of the areas where the broad application of audio signals to human emotion understanding has drawn a lot of interest. In addition, the journal will investigate cutting-edge feature engineering and data augmentation methodologies to improve model resilience and functionality in a variety of real-world scenarios. This project intends to push the boundaries of affective computing through rigorous testing and validation, providing new insights and useful solutions for applications ranging from virtual assistants and customer service bots to therapeutic and educational aids

CNN, RNN, MFCC, SER, LSTM

"Assessing Human Emotion Using Audio Recordings", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.f39-f44, March-2024, Available :http://www.jetir.org/papers/JETIR2403506.pdf

"Assessing Human Emotion Using Audio Recordings", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppf39-f44, March-2024, Available at : http://www.jetir.org/papers/JETIR2403506.pdf