• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Master Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Master Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Analisis Algoritma MFCC untuk Pengenalan Pola Kunci Gitar Melalui Suara

    View/Open
    Fulltext (6.829Mb)
    Date
    2016
    Author
    Situmeang, Matra Prima
    Advisor(s)
    Efendi, Syahril
    Iryanto
    Metadata
    Show full item record
    Abstract
    The complexity of MFCC computation result in the decrease of its computation speed. This fact has coused the emergence of researchest that are related to its computation’s acceleration of computing. Among these studies, Efficient MFCC algorithm in which the efficiency of this study performed on stage hamming window. Other study is MFCC Enhancement offers some studies on the opportunities to improve the MFCC algorithm. This study is included as an effort to accelerate the MFCC algorithm computation, where the acceleration of parallelization of computing is done in stages with Fast Fourier Transform (FFT). Logically, FFT parallelization will speed up the computation. This study has found that in the trials for each chord A-Major, B-Major, C-Major, D-Major, E-Major, F-Major and G-Major with the variation of pulse code modulation (PCM) 16 bit, and 32-bit, as well as the number of frames per second, 48,000, 88,200, and 96,000, the FFT-Parallel can speed up MFCC by 3 times faster (on average) than the MFCC which uses FFT-Serial.
     
    Rumitnya komputasi MFCC sehingga memberikan pengaruh pada kecepatan komputasi. Hal ini mendorong munculnya penelitian yang berkaitan dengan percepatan komputasi. Di antaranya adalah studi algoritma Efficient MFCC di mana pada penelitian ini efisiensi dilakukan pada tahapan hamming window. Studi lainnya yaitu MFCC Enhancement menawarkan beberapa kajian – kajian tentang peluang untuk dapat meningkatkan algoritma MFCC. Penelitian ini adalah termasuk sebagai upaya percepatan komputasi algoritma MFCC, di mana percepatan komputasi dilakukan dengan paralelisasi pada tahapan Fast Fourier Transform (FFT). Sehingga paralelisasi FFT secara logis akan menambah kecepatan komputasi (speed up, SU). Hasil penelitian ini mendapatkan bahwa pada percobaan untuk masing chord A-Major, B-Major, C-Major, D-Major, E-Major, F-Major, dan G-Major dengan variasi pulse code modulation (PCM) 16 bit, dan 32 bit, serta jumlah frame per detik 48.000, 88.200, dan 96.000 menunjukkan bahwa FFT-Paralel dapat mempercepat waktu eksekusi MFCC dengan rerata 3 kali lebih cepat dibandingkan dengan MFCC yang menggunakan FFT-Serial.

    URI
    http://repositori.usu.ac.id/handle/123456789/2771
    Collections
    • Master Theses [621]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV