On sparse beamformer design with reverberation

Li, Zhibao; Yiu, Ka Fai Cedric; Dai, Yu‐Hong

doi:10.1016/j.apm.2017.10.035

Cited by 2 publications

(5 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the space-frequency region Ω is continuous, (2.2) is semi-infinite. To solve it numerically, the discretization methods and reduction based approaches are usually introduced to transform it into the finite numerical problem approximately [43]. We approximate the space-frequency domain Ω by Ω N , which is a multi-dimensional grid region with a uniform grid containing N mesh points in each dimension.…”

Section: Beamformer Design Problemmentioning

confidence: 99%

“…The beamformer design with the sparse FIR filters can simplify the arithmetic operations and speed up the time of output. [43] also proposed 2 − p (0 < p < 1) minimization model…”

Section: Beamformer Design Problemmentioning

confidence: 99%

“…Due to the nonconvexity of the model, the SBBG method is far inferior to the tailed methods proposed in this paper. The performance of the SBBG method in detail can be found in [43]. Iter.…”

Section: Numerical Experimentsmentioning

confidence: 99%

“…- The overall performance of least squares beamformer design is shown in Figure 2. The performance of sparse beamformer design in [43] and proximal sparse beamformer design are plotted in Figure 3 and Figure 4, respectively. From the results shown in the above figures, we can conclude that the performance of proximal sparse beamformer design is more close to the performance of least squares beamformer design than the one of sparse beamformer design.…”

Section: Numerical Experimentsmentioning

confidence: 99%

See 3 more Smart Citations

Sparse broadband beamformer design via proximal optimization Techniques

2023

J. Nonlinear Var. Anal.

View full text Add to dashboard Cite

Beamforming is one of the most important techniques to enhance the quality of signal in array sensor signal processing, and the performance of a beamformer is usually related to the design of array configuration and beamformer weight. Recently, it was realized that the sparsity of the filter coefficients can reduce the cost of signal acquisition and communication, and as a consequence, the sparse broadband beamformer design attracts more and more attentions. In this paper, we first propose a proximal sparse beamformer design model which obtains the sparse and robust filter coefficients through solving a composite optimization problem. The objective function of the model is the sum of a least squares term, a proximal term, and an 1 -regularization term. The least squares term reflects the data fidelity; the proximal term, whose center is predetermined via a simple least squares, enhances the robustness; while the 1 term ensures the sparsity of the solution. This model not only maintains the authenticity of the least squares solution, but also ensures the sparsity of the filter coefficients. A significant feature of the model is that we use 'partial' data to obtain the least squares solution and use another 'partial' data to construct the data fidelity term, which can evidently decrease the computational cost. For solving the composite optimization problem, we tailor several popular algorithms, such as the alternating direction method of multipliers, the forward-backward splitting method, and the Douglas-Rachford splitting method. Numerical results observably exhibit the improvements of the proposed approach over existing works in both effectiveness and efficiencies.

show abstract

Section: Beamformer Design Problemmentioning

confidence: 99%

“…The beamformer design with the sparse FIR filters can simplify the arithmetic operations and speed up the time of output. [43] also proposed 2 − p (0 < p < 1) minimization model…”

Section: Beamformer Design Problemmentioning

confidence: 99%

Section: Numerical Experimentsmentioning

confidence: 99%

Section: Numerical Experimentsmentioning

confidence: 99%

See 2 more Smart Citations

Sparse broadband beamformer design via proximal optimization Techniques

2023

J. Nonlinear Var. Anal.

View full text Add to dashboard Cite

show abstract

“…More recent attempts can be found in [17,18,19,20]. At the same time, many blockwise techniques and splitting methods for solving the constrained composite optimization problem have also been developed for separable optimization problems with applications in signal and imaging processing, machine learning, statistics, and engineering [21,14,22,23,24,25,26,27,28]. Indeed, numerous experiments have demonstrated that they are powerful for solving large-scale optimization problems arising in machine learning [15,16,29].…”

Section: Introductionmentioning

confidence: 99%