• sandeep koro
• p.gayatri

Speech Emotion Recognition (SER) is a developing research area aimed at classifying emotional states of speakers using their speech signals. CNNs have been widely applied in SER due to their ability to automatically extract relevant features from raw speech data. This paper presents a convolutional neural network model for speech emotion recognition. The proposed system consists of four main elements: emotion classification, data augmentation, model training, and feature extraction. Data augmentation involves applying various signal processing methods, such as pitch shifting, time stretching, noise addition, and dynamic range alteration, to the original speech signals. To capture the spectral information of the speech signals, the feature extraction module utilizes Mel-Frequency Spectral Coefficients (MFCCs) and their first and second-order derivatives. The proposed system is trained and evaluated using two datasets, namely RAVDESS and TESS. The emotion classification module employs a CNN architecture to categorize emotions into seven basic emotion categories: sad, fear, surprise, angry, happy, neutral, and disgust.

: Speech Emotion Recognition, Data Augmentation, MFCC, CNN, RAVDESS, TESS.

" SPEECH EMOTION RECOGNITION SYSTEM USING CNN ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.k344-k349, June-2023, Available :http://www.jetir.org/papers/JETIR2306A42.pdf

" SPEECH EMOTION RECOGNITION SYSTEM USING CNN ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. ppk344-k349, June-2023, Available at : http://www.jetir.org/papers/JETIR2306A42.pdf