A New Reduced-Interference Source Separation Method Based on a Complementary Combination of Masking Algorithm and Mixing
- PDF / 2,893,024 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 5 Downloads / 141 Views
RESEARCH PAPER
A New Reduced-Interference Source Separation Method Based on a Complementary Combination of Masking Algorithm and Mixing Matrix Estimation Sayyed Ali Rafiei1
•
Hamid Sheikhzadeh1 • Mohammad Sabbaqi1
Received: 12 February 2019 / Accepted: 10 February 2020 Shiraz University 2020
Abstract Array signal processing, as a versatile approach, can be used in both source separation and source localization applications. In the realm of the multi-channel blind source separation, time–frequency masking methods and data-dependent beamforming algorithms are commonly used, and the proposed approach in this paper employs a complementary combination of the two methods. Most mask-based approaches suffer from a basic problem: the use of a real-valued mask is not justified in some time–frequency blocks. Thus, we use both mask and spatial information of sources simultaneously to reduce interference and distortion in the separated sources. Moreover, a novel mixing matrix estimation is introduced in this paper that employs information extracted from binary/fuzzy clustering of a high-performance feature set. To employ the complementary combination in source separation approach, a criterion is used that splits time–frequency points into two groups. For the first group, masking method is used for separation, whereas for the second one, mixing matrix is employed. Experimental results show that the proposed source separation method is very promising in anechoic conditions, as well as in the low-reverberant ones. In comparison with other masking-based approaches, especially for the anechoic case, the results get much closer to the best theoretically achievable signal to distortion ratio. Keywords Array signal processing Blind source separation Data-dependent beamforming Fuzzy mask Binary mask Mixing matrix estimation
1 Introduction Array signal processing is a fundamental problem in multidimensional parameter estimation. Radar, biomedical imaging, mobile communications, beamforming, and blind source separation (BSS) are some of its applications (Steinwandt 2018; Wang et al. 2018). Data-dependent beamforming is a state-of-the-art way that finds some weight vectors which are used to extract signal(s) of interest among interferences and noise (Li and Stoica 2005). Delay and sum algorithm and minimum variance/ power distortionless response method, to name just a few, are some well-known approaches in beamforming (Zhao
& Sayyed Ali Rafiei [email protected] 1
Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
et al. 2017). One of the two suggestions made in this paper is a new beamforming method for the mixing matrix estimation. The method uses the proposed feature of Araki et al. (2007), clustering with three different types of algorithms. The proposed mixing matrix estimation approach can be used for source localization applications, but this paper focuses on only the application of BSS. BSS deals with estimation of original source signals from a set of mixed signals, w
Data Loading...
