Enhanced Speech Emotion RecognitionUsing AudioSignal Processing with CNN Assistance

The important form human communicating is speech, which can also be used as a potential means of human-computer interaction (HCI) with the use of a microphone sensor. An emerging field of HCI research uses these sensors to detect quantifiable emotions from speech signals. This study has implications for human-reboot interaction, the experience of virtual reality, actions assessment, Health services, and Customer service centres for emergencies, among other areas, to ascertain the speaker's emotional state as shown by their speech. We present significant contributions for; in this work. (i) improving Speech Emotion Recognition (SER) accuracy in comparison in the most advanced; and (ii) lowering computationally complicated nature of the model SER that is being given. We present a plain nets strategy convolutional neural network (CNN) architecture with artificial intelligence support to train prominent and distinguishing characteristics from speech signal spectrograms were improved in previous rounds to get better performance. Rather than using a pooling layer, convolutional layers are used to learn local hidden patterns, whereas Layers with complete connectivity are utilized to understand global discriminative features and Speech emotion categorization is done using a soft-max classifier. The suggested method reduces the size of the model by 34.5 MB while improving the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and Interactive Emotional Dyadic Motion Capture (IEMDMC) datasets, respectively, increasing accuracy by 4.5% and 7.85%. It shows how the proposed SER technique can be applied in real-world scenarios and proves its applicability and efficacy.