• K Madhan Sesha Sai
• D. Sri Laksh
• K. Kranthi Kumar
• B. Hema Kumari

Pitch, timbre, loudness, and vocal tone are just a few characteristics that may be used to describe the human voice. Many times, it has been noted that as individuals produce speech, their vocal characteristics change to reflect their emotions. The algorithm method for emotion recognition in humans using speech is presented in this research. This paper's main goal is to identify speech feelings and divide them into 6 emotion output classes: frustrated, terror, dissatisfaction, joyous, sorrowful, and silent. The suggested method relies on the Crema-D database of emotional speech using Mel Frequency Cepstral coefficients (MFCC). Data Augmentation is performed on input data audio file, such as Noise, High Speed, Low Speed etc. are added, thus more the varied data is available to the model better the model understands. Feature extraction is done using MFCC and then the extracted features are Normalised (for Independent Variable), Label Encoding (for Dependent Variable (SVM, RF)),One Hot Encoding(for Dependent Variable(for CNN)) is done. After this the dataset is divided into Train, Test and given to different models such as CNN, SVM for Emotion prediction. For each of the several tests, we provide accuracy, f-score, precision, and recall. The results showed that CNN had the best accuracy and correctly identified emotion 88.21% of the time.

Mel Frequency Cepstral coefficients, convolutional neural network , Machine Learning

"Speech Emotion Recognition Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.a225-a231, June-2023, Available :http://www.jetir.org/papers/JETIR2306031.pdf

"Speech Emotion Recognition Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. ppa225-a231, June-2023, Available at : http://www.jetir.org/papers/JETIR2306031.pdf