IMPLEMENTASI METODE LONG SHORT-TERM MEMORY DAN SUPPORT VECTOR MACHINE DENGAN EKSTRAKSI FITUR MFCC UNTUK KLASIFIKASI EMOSI SUARA

NAFSYI, DHIAZ RUSYDA (2025) IMPLEMENTASI METODE LONG SHORT-TERM MEMORY DAN SUPPORT VECTOR MACHINE DENGAN EKSTRAKSI FITUR MFCC UNTUK KLASIFIKASI EMOSI SUARA. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (354kB) | Preview
	Text (BAB I) 02 BAB 1.pdf Restricted to Registered users only Download (40kB)
	Text (BAB II) 03 BAB 2.pdf Restricted to Registered users only Download (462kB)
	Text (BAB III) 04 BAB 3.pdf Restricted to Registered users only Download (200kB)
	Text (BAB IV) 05 BAB 4.pdf Restricted to Registered users only Download (502kB)
	Text (BAB V) 06 BAB 5.pdf Restricted to Registered users only Download (28kB)
	Text (DAFTAR PUSTAKA) 07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (164kB)
	Text (LAMPIRAN) 08 LAMPIRAN.pdf Restricted to Registered users only Download (1MB)

Abstract

Interactions between people are often influenced by emotions, which are biological and psychological conditions and can be expressed through sound signals. This study aims to detect sound-based emotions by utilizing digital signal processing techniques. In this study, a performance comparison was conducted between two machine learning models, namely Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) to complete the classification task of seven classes of emotions. This study used Toronto Emotional Speech Set (TESS) dataset, with MelFrequency Cepstral Coefficients (MFCC) feature extraction. The Data were divided into 2240 train data (80%) and 560 test data (20%). The test results showed that the LSTM model achieved superior performance with an accuracy of 98%, while the SVM model obtained an accuracy of 88%. It was concluded that the architecture on the LSTM is significantly more effective in capturing dynamic patterns of MFCC features. However, this study has one important limitation. Since the dataset used only comes from two speakers, the ability of the model to work well on more diverse sounds is still an area that needs to be proven in future studies . Kata kunci: Speech Emotion Recognition, MFCC, Long Short-Term Memory, Support Vector Machine. nteraksi antar manusia sering kali dipengaruhi oleh emosi, yang merupakan kondisi biologis dan psikologis serta dapat diekspresikan melalui sinyal suara. Penelitian ini bertujuan untuk mendeteksi emosi berbasis suara dengan memanfaatkan teknik pemrosesan sinyal digital. Dalam penelitian ini, dilakukan perbandingan kinerja antara dua model machine learning yaitu Long Short-Term Memory (LSTM) dan Support Vector Machine (SVM) untuk menyelesaikan tugas klasifikasi tujuh kelas emosi. Penelitian ini menggunakan dataset Toronto Emotional Speech Set (TESS), dengan ekstraksi fitur Mel-Frequency Cepstral Coefficients (MFCC). Data dibagi menjadi 2240 data latih 80% dan 560 data uji 20%. Hasil pengujian menunjukkan bahwa model LSTM mencapai kinerja superior dengan akurasi sebesar 98%, sementara model SVM memperoleh akurasi 88%. Disimpulkan bahwa arsitektur pada LSTM secara signifikan lebih efektif dalam menangkap pola dinamis dari fitur MFCC. Namun, penelitian ini memiliki satu batasan penting. Karena dataset yang digunakan hanya berasal dari dua pembicara, kemampuan model untuk bekerja dengan baik pada suara yang lebih beragam masih menjadi area yang perlu dibuktikan dalam penelitian selanjutnya. Kata kunci: Emosi, Klasifikasi, Long Short-Term Memory, Support Vector Machine, Mel Frequency Cepstral Coefficients

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 25 106
NIM/NIDN Creators:	41521010163
Uncontrolled Keywords:	Emosi, Klasifikasi, Long Short-Term Memory, Support Vector Machine, Mel Frequency Cepstral Coefficients
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika > 004.5 Storage/Penyimpanan > 004.53 Internal Storage (Main Memory)/Penyimpanan Internal I(Memory Utama) 100 Philosophy and Psychology/Filsafat dan Psikologi > 120 Epistemology/Epistemologi > 128 Humankind/Filsafat Kehidupan Manusia > 128.3 Attributes and Faculties/Atribut dan Fakultas > 128.37 Emotion/Emosi 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 152 Sensory Perception, Movement, Emotions, Physiological Drives/Psikologi Fisiologis 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 153 Conscious Mental Process and Intelligence/Intelegensia, Kecerdasan Proses Intelektual dan Mental > 153.1 Memory and Learning/Memori dan Pembelajaran > 153.13 Types of Memory/Jenis-jenis Memori > 153.132 Visual Memory/Memori Visual
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	04 Aug 2025 02:22
Last Modified:	04 Aug 2025 02:22
URI:	http://repository.mercubuana.ac.id/id/eprint/96504

Actions (login required)

View Item