For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Effective Frame Selection for Blind Source Separation Based on Frequency Domain Independent Component Analysis
Yusuke MIZUNO Kazunobu KONDO Takanori NISHINO Norihide KITAOKA Kazuya TAKEDA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2014/03/01
Online ISSN: 1745-1337
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Engineering Acoustics
dodecahedral microphone array, frequency domain independent component analysis, computational complexity reduction, signal to interference ratio improvement,
Full Text: PDF>>
Blind source separation is a technique that can separate sound sources without such information as source location, the number of sources, and the utterance content. Multi-channel source separation using many microphones separates signals with high accuracy, even if there are many sources. However, these methods have extremely high computational complexity, which must be reduced. In this paper, we propose a computational complexity reduction method for blind source separation based on frequency domain independent component analysis (FDICA) and examine temporal data that are effective for source separation. A frame with many sound sources is effective for FDICA source separation. We assume that a frame with a low kurtosis has many sound sources and preferentially select such frames. In our proposed method, we used the log power spectrum and the kurtosis of the magnitude distribution of the observed data as selection criteria and conducted source separation experiments using speech signals from twelve speakers. We evaluated the separation performances by the signal-to-interference ratio (SIR) improvement score. From our results, the SIR improvement score was 24.3dB when all the frames were used, and 23.3dB when the 300 frames selected by our criteria were used. These results clarified that our proposed selection criteria based on kurtosis and magnitude is effective. Furthermore, we significantly reduced the computational complexity because it is proportional to the number of selected frames.