Fast Independent Component Analysis (FastICA) in Separating Vocals and Instruments in the Art of Geguntangan

2020 ◽  
Vol 8 (3) ◽  
pp. 219
Author(s):  
Angga Pramana Putra ◽  
I Gede Arta Wibawa
Keyword(s):  
Independent Component Analysis ◽  
Component Analysis ◽  
Independent Component ◽  
Blind Signal Separation ◽  
Sound Sources ◽  
Blind Signal ◽  
Fast Independent Component Analysis ◽  
Fastica Algorithm ◽  
Mixing Matrix ◽  
Sound Separation

Geguntangan is pesantian in religious ceremonies in Bali accompanied by gamelan music. The human sense of hearing tends to have limitations, which causes not all vocals mixed with gamelan to be heard clearly. Therefore we need a system that can be used to separate vocals with gamelan in the geguntangan. Separation of sound sources is categorized as Blind Source Separation (BSS) or also called Blind Signal Separation, which means an unknown source. The algorithm used to handle BSS is the Fast Independent Component Analysis (FastICA) algorithm with a focus on separating the sound signal in a wav-format sound file. FastICA algorithm is used for the sound separation process with the value parameter used is Mean Square Error (MSE). From the simulation results show the results of MSE calculations using the mixing matrix [0.3816, 0.8678], [0.8534, -0.5853] obtained the results for the FastICA method, the MSE value is 3.60 x 10-5 for the vocal and 1.71 x 10-6 for the instrument.

INDEPENDENT COMPONENT ANALYSIS (ICA) DAN SPARSE COMPONENT ANALYSIS (SCA) DALAM PEMISAHAN VOKAL DAN INSTRUMEN PADA SENI GEGUNTANGAN

2019 ◽  
Vol 8 (1) ◽  
pp. 105
Author(s):  
Angga Pramana Putra ◽  
Ni Wayan Wiantari ◽  
Putu Mira Novita Dewi ◽  
I Dewa Made Bayu Atmaja Darmawan
Keyword(s):  
Independent Component Analysis ◽  
Mean Square Error ◽  
Blind Source Separation ◽  
Component Analysis ◽  
Independent Component ◽  
Signal Separation ◽  
Blind Signal Separation ◽  
Mean Square ◽  
Blind Signal ◽  
Sparse Component Analysis

Geguntangan adalah pesantian dalam upacara keagamaan yang diiringi dengan gamelan. Indra  pendengaran manusia cenderung memiliki keterbatasan, yang menyebabkan tidak semua vokal yang  tercampur dengan gamelan bisa didengar jelas. Oleh karena itu diperlukan suatu sistem yang dapat digunakan untuk memisahkan vokal dengan gamelan pada geguntangan. Pemisahan sumber suara ini dikategorikan sebagai Blind Source Separation (BSS) atau disebut juga Blind Signal Separation yang  artinya sumber tidak dikenal. Algoritma yang digunakan untuk menangani BSS adalah algoritma Independent Component Analysis (ICA) dan Sparse Component Analysis (SCA) dengan berfokus  pada pemisahan sinyal suara pada file suara berformat *.wav. Algoritma SCA dan ICA digunakan  untuk proses pemisahan suara dengan parameter nilai yang digunakan adalah Mean Square Error (MSE) dan Signalto Interference Ratio(SIR). Dari hasil simulasi menunjukkan Hasil perhitungan MSE dan SIR dengan dengan menggunakan mixing matriks [0.3816, 0.8678], [0.8534, -0.5853] didapatkan untuk metode ICA nilai MSE sebesar 4.169380402433175 x 10-6 untuk instrumennya dan 2.884749383815846 x 10-5 untuk vokalnya dan didapatkan nilai SIR sebesar 53.79928479270223 untuk instrumennya dan 45.39891910741724 untuk vokalnya. Selanjutnya untuk metode SCA, nilai MSE sebesar 3.382207103335018 x 10-5 untuk instrumennya dan 3.099942460987607 x 10-5 untuk vokalnya dan didapatkan nilai SIR sebesar 44.707998026869014 untuk instrumennya dan 45.08646367168143 untuk vokalnya.

Independent Component Analysis and Blind Signal Separation: Theory, Algorithms and Applications

2012 ◽  
Vol 10 (1) ◽  
pp. 51-69 ◽  
Author(s):  
Eduardo F. Simas Filho ◽  
José M. de Seixas ◽  
Natanael N. Moura ◽  
Diego B. Haddad ◽  
José M. Faier ◽  
...  
Keyword(s):  
Independent Component Analysis ◽  
Component Analysis ◽  
Independent Component ◽  
Signal Separation ◽  
Blind Signal Separation ◽  
Blind Signal ◽  
Separation Theory

scholarly journals Source Separation using ICA

2013 ◽  
pp. 51-53
Author(s):  
P.Shivani Sahoo ◽  
A. Barik ◽  
Padmini Mishra
Keyword(s):  
Independent Component Analysis ◽  
Statistical Signal Processing ◽  
Component Analysis ◽  
Processing Technique ◽  
Independent Component ◽  
Blind Signal Separation ◽  
Signal Processing Technique ◽  
Fast Independent Component Analysis ◽  
Mixed Voices ◽  
Ica Algorithm

Independent Component Analysis (ICA) is a statistical signal processing technique having emerging new practical application areas, such as blind signal separation such as mixed voices or images, analysis of several types of data or feature extraction. Fast independent component analysis (Fast ICA ) is one of the most efficient ICA technique. Fast ICA algorithm separates the independent sources from their mixtures by measuring non-gaussianity.In this paper we present a method that can separate the signals as individual channels from other channels and also remove the noise using fast ica algorithm. The method is to decompose a multi channel signal into statistically independent components.

Sign in / Sign up

Export Citation Format

Share Document