Time filter

Source Type

Kunche P.,Andhra University | Sasi Bhushan Rao G.,Andhra University | Reddy K.V.V.S.,Andhra University | Uma Maheswari R.,Vignan Institute of Information Technology
International Journal of Speech Technology

A new approach to dual channel speech enhancement is proposed based on a recently introduced meta-heuristic optimization algorithm called hybrid PSOGSA. It is a novel algorithm which combines the ability of exploration in gravitational search algorithm (GSA) and the exploitation capability of particle swarm optimization (PSO) to offer a better local search process along with the social thinking. This paper aims to present such a hybrid combination as a promising and powerful technique to adaptive noise cancellation in speech enhancement and it is compared with the standard PSO (SPSO) and GSA based speech enhancement algorithms. Simulation results prove that the performance of PSOGSA is superior to SPSO and GSA algorithms, in the context of speech enhancement. © 2014, Springer Science+Business Media New York. Source

Prajna K.,Andhra University | Rao G.S.B.,Andhra University | Reddy K.V.V.S.,Andhra University | Maheswari R.U.,Vignan Institute of Information Technology
International Journal of Speech Technology

This paper proposes novel heuristic algorithm called gravitational search algorithm (GSA) to speech enhancement. Stochastic and heuristic algorithms like particle swarm optimization (PSO) and some of its variants have been adapted to the field of speech enhancement in recent years. Although standard PSO (SPSO) finds good solutions, it suffers from the premature convergence by getting trapped into local optimum. In order to increase the diversity in search space and to improve the local searching capability, another recently developed heuristic algorithm GSA is proposed to speech enhancement in this paper. GSA is mainly constructed on the basis of law of gravity and the notion of mass interactions.The proposed algorithm is studied for real world noise condition called babble noise, at three different input SNR levels. To the best of our knowledge, there is no analysis about the intelligibility of enhanced speech using optimization techniques. In the present study, the proposed algorithm is compared with the standard PSO (SPSO) algorithm for dual channel speech enhancement, and the intelligibility analysis is also reported. Simulation results indicate that GSA-based algorithm outperforms the particle swarm optimization in adaptive noise cancellation with an improved speech quality and intelligibility. © 2014, Springer Science+Business Media New York. Source

Ramana P.,GMR Institute of Technology | Alice Mary K.,Vignan Institute of Information Technology | Surya Kalavathi M.,Jawaharlal Nehru Technological University | Phani Kumar M.,GMR Institute of Technology
World Academy of Science, Engineering and Technology

This paper discusses two observers, which are used for the estimation of parameters of PMSM. Former one, reduced order observer, which is used to estimate the inaccessible parameters of PMSM. Later one, full order observer, which is used to estimate all the parameters of PMSM even though some of the parameters are directly available for measurement, so as to meet with the insensitivity to the parameter variation. However, the state space model contains some nonlinear terms i.e. the product of different state variables. The asymptotic state observer, which approximately reconstructs the state vector for linear systems without uncertainties, was presented by Luenberger. In this work, a modified form of such an observer is used by including a non-linear term involving the speed. So, both the observers are designed in the framework of nonlinear control; their stability and rate of convergence is discussed. Source

Potnuru D.,GMR Institute of Technology | Chandra K.P.B.,University of Exeter | Arasaratnam I.,Apple Inc | Gu D.-W.,University of Leicester | And 2 more authors.
IET Electric Power Applications

This paper presents a non-linear square-root estimation scheme for brushless DC (BLDC) motors. The cubature Kalman filter (CKF) is the main estimation tool for the presented approach. The CKF is a recently proposed estimator for highly non-linear systems and its efficacy has been verified on several applications. The square-root version of the CKF is preferred over the conventional CKF for real-time applications. Despite of having several advantages over other non-linear filters, the CKF has not yet been explored for state estimation of electric drives in the electric drives community. In this study, the authors present a square-root CKF for the speed and rotor position estimation of a highly non-linear and high fidelity BLDC motor, these estimated speed and rotor position are then fed back to control the speed of the BLDC motor. The efficacy of the presented approach for low and high reference speeds, and in the presence of parametric uncertainties, is demonstrated by real-time experiments. © The Institution of Engineering and Technology. Source

Prajna K.,Andhra University | Reddy K.V.V.S.,Andhra University | Rao G.S.B.,Andhra University | Maheswari R.U.,Vignan Institute of Information Technology
International Journal of Speech Technology

The present paper focuses on the suppression of background noise in speech signal by utilizing a powerful heuristic optimization algorithm called Bat algorithm (BA) for adaptive filtering in dual channel enhancement systems. Bat algorithm is a recently developed population based meta heuristic approach which is inspired by the hunting behavior of the bats. It is developed by Yang (2010). As a novel feature Bat algorithm is based on the echo location behavior of micro bats. BA uses the frequency tuning technique to increase the diversity of the solutions in the population, while at the same time it uses the automatic zooming and tries to balance the exploration and exploitation. A few studies have been carried out on the use of heuristics for ANC in speech enhancement by using standard particle swarm optimization (SPSO) and some of its variants till 2010. In order to extend these heuristic approaches to speech, accelerated particle swarm optimization (APSO) based enhancement approach has been proposed (Prajna et al. in Int J Speech Technol 17(4):341–351, 2014a; Prajna et al. in IJISA 6(4):1–10, 2014b, doi:10.5815/ijisa.2014.04.01; Prajna et al. in IEEE international conference on communications and signal processing (ICCSP), April 2014, pp 1457–1461, 2014c, doi:10.1109/ICCSP.2014.6950090). To overcome the problem of poor exploitation ability of APSO, another approach is proposed based on gravitational search algorithm (GSA) (Prajna et al. 2014a, b, c). To combine both the abilities of PSO and GSA algorithms, Hybrid PSOGSA algorithm is also proposed to ANC (Prajna et al. 2014a, b, c). To further improve the efficiency of adaptive filtering in ANC, by providing a dynamic balance between exploration and exploitation, BA is proposed to speech enhancement. This paper intends to present the Bat algorithm as an improved approach to ANC in speech enhancement when compared with that of SPSO, APSO, GSA and Hybrid PSOGSA based speech enhancement algorithms. The performance of all the algorithms is evaluated by computing four objective measures SNRI, PESQ, FAI and WSS, in two real world noise conditions Babble and Factory, at three different input SNR levels set at −10, 0 and 5 dB. Simulation results prove that BA is the most successful algorithm of all the algorithms studied in this work, to suppress the background noise more effectively. © 2015, Springer Science+Business Media New York. Source

Discover hidden collaborations