• RAVI PRABHAT SHARMA
• Ritu Kadyan

Speech emotion recognition is essential for understanding and responding to human emotions in human-computer interaction.In this study, a2D convolutional neural network(CNN) is proposed as anoval method for speech emotion recognition.The objective is to accurately classify emotionsfrom speech signals by leveraging hierarchical and spatial information in the spectrogram representation. The research beings with audio data pre-processing, incuding noise removal and normalization. Features are then extracted, specifically Mel-frequency cepstral coefficient(MFCCs) capturing spectral characteristics. These MFCC features are transformed into a 2D spectrogram representation. A 2D-CNN architwcture is designed and trained to learn discriminative features from the spectrograms.The proposed model employs multiple convolutional layers with varying filter size to capture local and global patterns. Max-poolinglayers down-sample feature maps, improving generalization and information extraction. Performance evaluation uses publicly available speech emotion datasets ( RAVDESS, SAVEE, TESS, and CREMA-D) showcasing the effectiveness of the 2D-CNN model in emotion recoginition. This research contributes a novel approach that demonstrates accurate emotion classification, outperforming traditional methods and enhancing emotional intelligence in machines.

"ADVANCING SPEECH EMOTION RECOGNITION THROUGH HIERARCHICAL ANALYSIS AND 2D-CONVOLUTIONAL NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.e199-e207, July-2023, Available :http://www.jetir.org/papers/JETIR2307422.pdf

"ADVANCING SPEECH EMOTION RECOGNITION THROUGH HIERARCHICAL ANALYSIS AND 2D-CONVOLUTIONAL NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppe199-e207, July-2023, Available at : http://www.jetir.org/papers/JETIR2307422.pdf