• Zafeer Rangoonwala
• Jainam Patel
• Hirak Modi
• Dr. Sheetal Pandya

Speech emotion recognition has become a vital area in research, greatly impacting public health improvements and healthcare technology advancement. Recent progress involves innovative deep learning methods and unique audio features. A new study introduces a self-attention deep learning model merging a two-dimensional CNN with an LSTM network. It explores various spectral and rhythmic data combinations to identify effective features, identifying Mel Frequency Cepstral Coefficients (MFCCs) as highly efficient. Using a combined dataset and detecting eight emotional states, the proposed model achieved a remarkable 90% test accuracy, surpassing existing models. This model holds promise for enhancing automated mental health monitoring. In the realm of Human-Computer Interaction and speech processing, Speech Emotion Recognition (SER) has gained prominence. SER systems aim to identify emotions in speech by analyzing key features, but differences in human and machine interpretation pose challenges. A thorough review of recent SER literature in this paper provides insights into design elements and methodologies. The paper also emphasizes research gaps, urging further exploration by researchers, institutions, and regulatory bodies.

Speech Emotion Recognition (SER), Machine Learning (ML), Deep Learning, Emotion Classification, Acoustic Features, Natural Language Processing (NLP), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Mel-frequency Cepstral Coefficients (MFCCs)

"USING MACHINE LEARNING TO RECOGNIZE EMOTIONS CONVEYED THROUGH SPEECH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 12, page no.b322-b336, December-2023, Available :http://www.jetir.org/papers/JETIR2312138.pdf

"USING MACHINE LEARNING TO RECOGNIZE EMOTIONS CONVEYED THROUGH SPEECH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 12, page no. ppb322-b336, December-2023, Available at : http://www.jetir.org/papers/JETIR2312138.pdf