A separating method using orthogonal properties between audio sources in frequency domain

Authors:
HyukJoon Jang;Hong Jeong
Affiliations:
Postech, Dept. of Info. Technology, Pohang, Republic of Korea;Postech, Dept. of EEE, Pohang Republic of Korea
Venue:
ASMCSS'09 Proceedings of the 3rd International Conference on Applied Mathematics, Simulation, Modelling, Circuits, Systems and Signals
Year:
2009

Citing 3
Cited 0

Matrix analysis

Matrix analysis
Natural gradient works efficiently in learning

Neural Computation
Blind separation of speech mixtures via time-frequency masking

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, we investigate the orthogonal properties between independent audio sources in time-frequency domain and suggest a separation algorithm using the property. The proposed algorithm adaptively uses some existing techniques including Frequency Domain-Independent Component Analysis (FD-ICA) in hybrid manner. The experimental section represents that our algorithm is better than the conventional methods compared in this paper.