• Dr.R.N.Devendra kumar
• Mugilan M
• Mukunth K
• Prasannakumar E

The objective of this project is to create a Speech Emotion Recognition (SER) classifier utilising sophisticated machine learning methods in Python. The main objective is to identify and categorise human emotions expressed via speech, with possible uses in better customer service and strengthening driving safety. The project comprises the use of four different datasets, namely Crema-D, Ravdess, Savee, and Tess. It includes careful organisation of data, use of data augmentation techniques, extraction of pertinent audio characteristics, and the utilisation of a Convolutional Neural Network (CNN) for training. The results demonstrate potential, as the model achieved an accuracy of about 60.74% on the validation dataset and 72.94% on the training dataset. This showcases the effectiveness of deep learning in recognising spoken emotions in real-world situations. The success of the SER project underscores the need of meticulous data organisation, visualisation, and investigation. Data augmentation methods, such as injecting noise, extending time, and varying pitch, have played a vital role in improving the model's capacity to handle the natural fluctuations in speech patterns. Essential audio characteristics such as Zero Crossing Rate, Chroma_stft, MFCCs, RMS, and MelSpectrogram are crucial in converting intricate audio signals into a format that can be comprehended by machines. This project lays the groundwork for technology that can understand and respond to emotions. It highlights the growing importance of Speech Emotion Recognition in various fields, such as customer service and driver safety. This work contributes to a future where computing systems that can understand emotions will be crucial.

Speech Emotion Recognition , Chroma_stft, MFCCs, RMS, and MelSpectrogram

"speech emotion detection using python", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.g139-g142, March-2024, Available :http://www.jetir.org/papers/JETIR2403620.pdf

"speech emotion detection using python", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppg139-g142, March-2024, Available at : http://www.jetir.org/papers/JETIR2403620.pdf