An evolutionary algorithm to optimize the microphone array configuration for speech acquisition in vehicles

On sparse beamformer design with reverberation

“…Therefore, the optimal beamformer coefficients can be obtained by solving the above least squares problem (7), that is…”

“…It is noted that optimal beamforming arrays are usually achieved at non-uniformly configurations as indicated by the placement design problems [5,6,7,8,9,10], and the increase of microphone elements is usually not as flexible as the filter length. Indeed, most studies on beamformer design have been focused on the optimization of the filter coefficients.…”

Detection and Classification of Measurement Errors in Bioimpedance Spectroscopy

“…The solution proposed in this work is based on evolutionary algorithms (EA), which are iterative methods inspired in natural evolution laws [ 31 ]. An EA is commonly build by 3 functional blocks [ 32 ]: 1)generation of candidate solutions (CSs), 2) evaluation of a fitness function (FF), and 3) the evolution of the population. The definition of CS is problem specific and they are built by a set of components that can have binary, discrete or continuous values.…”

Beamformer configuration design in reverberant environments

“…For example, if microphones are displaced linearly in a one-dimensional manner, it essentially reduces to the array thinning technique (Mayhan, 1980;Sarajedini, 1999;Oliveri et al, 2009;Rocca and Haupt, 2010); different algorithms have been developed, including evolutionary programming (Kumar et al, 1998;Delgado et al, 2010), genetic algorithm (Haupt, 1994;Chen et al, 2007), simulated annealing algorithm (Trucco and Murino, 1999;Trucco, 2002;Doblinger, 2008) and pattern search algorithm (Razavi and Forooraghi, 2008). For applications inside a vehicle, microphones are restricted to be in several dedicated areas and an evolutionary algorithm has been proposed in Ayllón et al (2014). In formulating the general multi-dimensional design problem, a nonlinear optimization problem using the L 2 -norm was proposed in Feng et al (2012), which allows microphones to move around in a multi-dimensional solution space in search of better configurations.…”