Enhancing the Technique of Speech Emotion recognition using Feature Learning
Year: 2025
Type: article
Abstract: The human voice can be characterized by several attributes such as pitch, timbre,loudness, and vocal tone. It has often been observed that humans express their emotions byvarying different vocal attributes during speech generation. This paper presents an algorithmicapproach for detection of human emotions with the help speech .The prime objective of thispaper isto recognize emotionsin speech and classify them in 6 emotion output classes namelyangry, fear, disgust, happy, sad and neutral. The proposed approach is based upon the MelFrequency Cepstral coefficients (MFCC) uses Crema-D database of emotional speech. DataAugmention is perfomed on input data audio file,such as Noise, High Speed, Low Speed etc. areadded, thus more the varied data is available to the model better the model understands. Featureextraction is done using MFCC and then the extracted features are Normalized(for IndependentVariable), Label Encoding(for Dependent Variable(for SVM,RF)),One Hot Encoding(forDependent Variable(for CNN))is done. After thisthe datasetis divided into Train, Test and givento different models such as Convolutional Neural Network(CNN),Support VectorMachine(SVM), Random Forest(RF) for Emotion prediction. We report accuracy, f-score,precision and recall for the different experiment settings we evaluated our models in.Convolutional Neural Network(CNN) was found to have the highest accuracy and predictedcorrect emotion 88.21%ofthe time. Hence, deduction of human emotionsthrough speech analysishas a practical plausibility and could potentially be beneficial for improving humanconversational and persuasion skills.
Authors: Mrs. T. Sunitha, K. Poojitha, S. Venkata Rakesh, G. Bhanu Swetha, B. Kasi Priyanka
Language: English
Topic: Emotion and Mood Recognition
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6968609586
FWCI:
Cites:
Cited by:
Related to: