Skripsi

IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN EKSTRAKSI FITUR MFCC DAN CHROMA FEATURES DALAM KLASIFIKASI GENRE MUSIK

---

Penilaian

---

Music is an important part of human life and continues to evolve with the advancement of information technology. The diversity of music genres that emerge due to differences in instruments, rhythm, technique, and lyrics presents a unique challenge in accurately classifying genres. This study aims to develop a music genre classification system using the Convolutional Neural Network (CNN) method with a Resnet-50 architecture and additional extraction of MFCC and Chroma Features, as well as to evaluate the accuracy achieved by various model configurations. The data used consists of 30-second .wav audio files from the GTZAN dataset. This dataset contains 1,000 audio files divided into 10 genre classes: blues, classical, country, disco, hip hop, jazz, metal, pop, reggae, and rock. Audio samples are extracted for their MFCC and Chroma features, which are then represented as 2D arrays that can be visualized as spectrograms and processed by the CNN model. The results of the study show that the CNN with the Resnet-50 architecture achieved fairly good performance, with an accuracy of 66%, precision of 68.86%, recall of 66%, and F1 score of 65.86%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003566	T176161	T1761612025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1761612025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xiv, 87 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment