Bin-Wise Combination of Time-Frequency Masking and Beamforming for Convolutive Source Separation

Bella, Mostafa; Saylani, Hicham; Hosseini, Shahram; Deville, Yannick

doi:10.1109/mmsp55362.2022.9949527

Cited by 2 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Blind Source Separation (BSS) is a very active research field that aims at recovering a set of N unknown signals 1 , called sources and denoted s j (t) or their contributions on sensors, called source images and denoted s img ij (t), knowing only a set of M mixtures of these sources, called observations and denoted x i (t). This field has gained significant attention due to its wide range of applications in various domains.…”

Section: Introductionmentioning

confidence: 99%

“…This field has gained significant attention due to its wide range of applications in various domains. Among these domains we can mention those of audio [1]- [7], telecommunications [8], [9], biomedical applications [10], [11] and astrophysics [12], [13]. BSS methods have been used in the literature to handle several types of linear mixtures.…”

Section: Introductionmentioning

confidence: 99%

“…BSS methods have been used in the literature to handle several types of linear mixtures. In 1 In this paper, we suppose that the number of sources N is known.…”

Section: Introductionmentioning

confidence: 99%

“…this work, we are interested in the case of convolutive mixtures, which represent the most general and realistic case of linear mixtures and for which each mixture x i (t) is expressed as follows [1]:…”

Section: Introductionmentioning

confidence: 99%

“…for M < N ) [5], [7], [14], the case of convolutive mixtures remains of interest in BSS research. These techniques can be split into two main categories: frequency-domain methods [1], [3], [7], [14], [15], which mainly handle mixtures in the time-frequency (TF) domain, and time-domain methods [6], [16], [17], which handle mixtures in the time domain.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multi-Channel Bin-Wise Speech Separation Combining Time-Frequency Masking and Beamforming

Bella,

Saylani,

Hosseini

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper presents a novel Blind Source Separation method that can handle convolutive mixtures that may be underdetermined. Our method combines TF masking and beamforming and exploits the source signals sparsity in the Time-Frequency (TF) domain. Remarkable performance can be achieved by TF maskingbased methods, even in the underdetermined case, although they tend to generate unwanted artifacts at the level of the separated signals. Besides, beamforming techniques can achieve satisfactory performance only in the overdetermined and determined cases without distorting the estimated signals. By combining these two approaches, we can leverage their respective strengths. Firstly, we exploit the source signals sparsity in the TF domain to estimate probabilistic "bin-wise" masks by modeling the frequency observation vectors with a complex Gaussian Mixture Model and using an EM algorithm. However, due to the sensitivity of the EM algorithm to initialization, we propose properly selecting the initial values of the model parameters using Hermitian angles between the frequency observation vectors and a reference vector. Then, we utilize the estimated TF masks to estimate the Relative Transfer Functions of each source. Finally, we propose a new technique to obtain an estimate of the spatial images of the separated sources, which can be regarded as an underdetermined extension of the Linearly Constrained Minimum Power beamformer. Good performance was observed in test results for our method, both in the determined and underdetermined cases, compared to various existing methods with similar working hypotheses.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…BSS methods have been used in the literature to handle several types of linear mixtures. In 1 In this paper, we suppose that the number of sources N is known.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%