PENGENALAN EMOSI BERDASARKAN SUARA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)

WARMAN, IKHSAN and Fachrurrozi, Muhammad and Rachmatullah, Muhammad Naufal (2022) PENGENALAN EMOSI BERDASARKAN SUARA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281722037.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_55201_09021281722037_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
Preview	Text RAMA_55201_09021281722037_0222058001_0001129204_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (805kB) | Preview
	Text RAMA_55201_09021281722037_0222058001_0001129204_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (461kB) | Request a copy
	Text RAMA_55201_09021281722037_0222058001_0001129204_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (347kB) | Request a copy
	Text RAMA_55201_09021281722037_0222058001_0001129204_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021281722037_0222058001_0001129204_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021281722037_0222058001_0001129204_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (112kB) | Request a copy
	Text RAMA_55201_09021281722037_0222058001_0001129204_07_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (128kB) | Request a copy
	Text RAMA_55201_09021281722037_0222058001_0001129204_08_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (163kB) | Request a copy

Abstract

Speaking is not only used to convey information but can also show a person's emotional state. Emotion recognition aims to help the machine to recognize emotions based on speech patterns issued by a person. Some of the problems found are how to find effective voice features and build a good model for emotion recognition. This study aims to identify seven types of emotions, namely anger, disgust, fear, happy, surprise, sad, and neutral by using the Support Vector Machine (SVM) classification method and Mel-Frequency Cepstral Coefficient (MFCC) feature extraction. The SVM method was chosen because this method is often used in classification cases and gives good performance results. In its implementation, voice data is subjected to a feature extraction process using the MFCC method and followed by a classification process using SVM. The test cases in this study are divided into three scenarios, namely the first scenario (70% training data and 30% test data), the second scenario (50% training data and 50% test data) and the third scenario is divided based on speaker's age, the aged 64 as training, and aged 26 as testing. Each Scenario was tested using several SVM kernels including linear, polynomial, and Radial Basis Function (RBF). Based on the test results in scenario one, the linear kernel gets an accuracy of 97.02% while in scenario two, the linear kernel gets an accuracy of 96.64%. But testing in the third scenario, the linear kernel gets an accuracy of 40.0%. This is because the features distribution in the data shows a different pattern from what happened in the first and second scenarios which are shown in the analysis by using Principal Component Analysis (PCA).

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Support Vector Machine (SVM), Mel-Frequency Cepstral Coefficient (MFCC), Pengenalan emosi berdasarkan suara
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Ikhsan Warman
Date Deposited:	27 Jan 2023 07:43
Last Modified:	27 Jan 2023 07:43
URI:	http://repository.unsri.ac.id/id/eprint/88094

Actions (login required)

View Item