Hyung-Min Park

FPGA implementation of ICA algorithm for blind signal separation and adaptive noise canceling

An field programmable gate array (FPGA) implementation of independent component analysis (ICA) algorithm is reported for blind signal separation (BSS) and adaptive noise canceling (ANC) in real time. In order to provide enormous computing power for ICA-based algorithms with multipath reverberation, a special digital processor is designed and implemented in FPGA. The chip design fully utilizes modular concept and several chips may be put together for complex applications with a large number of noise sources. Experimental results with a fabricated test board are reported for ANC only, BSS only, and simultaneous ANC/BSS, which demonstrates successful speech enhancement in real environments in real time.

A filter bank approach to independent component analysis for convolved mixtures

Abstract We present a filter bank approach to perform independent component analysis (ICA) for convolved mixtures. Input signals are split into subband signals and subsampled. A simplified network performs ICA on the subsampled signals, and finally independent components are synthesized. The proposed approach achieves superior performance than the frequency domain approach and faster convergence with less computational complexity than the time domain approach. Furthermore, it requires shorter unmixing filter length and less computational complexity than other filter bank approaches by designing efficient filter banks. Also, a method is proposed to resolve the permutation and scaling problems of the filter bank approach.

Top-down attention to complement independent component analysis for blind signal separation

Abstract For robust speech recognition in real-world noisy environments, we present an algorithm to incorporate blind signal separation based on independent component analysis (ICA) and top-down attention processing. While ICA-based unmixing networks learn the inverse of mixing characteristics in frequency domain, their performance is limited by mismatches between the real-world mixing characteristics and assumptions of the ICA algorithm. The top-down process from a multiplayer Perceptron (MLP) classifier provides additional information on the speech signal, and fine-tunes the networks to compensate for the mismatches. For noisy speech signals recorded in a real office environment, the developed algorithm demonstrated great improvements on recognition performance.

A modified infomax algorithm for blind signal separation

Abstract We present a new algorithm to perform blind signal separation (BSS), which takes a trade-off between the ordinary gradient infomax algorithm and the natural gradient infomax algorithm. Analyzing the algorithm, we show that desired equilibrium points are locally stable by choosing appropriate score functions and step sizes. The algorithm provides better performance than the ordinary gradient algorithm, and it is free from approximation error and the small-step-size restriction of the natural gradient algorithm. In simulations on convolved mixtures, the algorithm provides much better performance than the other algorithms while requiring less computation.

A filter bank approach to independent component analysis and its application to adaptive noise cancelling

Abstract We present a filter bank (FB) approach to perform independent component analysis for adaptive noise cancelling. This approach is based on FBs, and its decimation provides much less computational complexity and faster convergence speed than the time-domain approach. In addition, the approach does not have a performance limitation unlike the frequency-domain approach. One can select the number of filters in the FB regardless of reverberation and implement the method to fit for parallel processing. We verify the effectiveness of the FB approach through simulations on adaptive noise cancelling.

Swarm intelligence-based sensor network deployment strategy

The wireless sensor network is a decentralized and self-organized system. Each sensor node in the sensor network should be intelligent enough to carry out its task of monitoring the environment. There would be numerous ways for deploying the sensor nodes in the environment. In this paper, swarm intelligence-based sensor network deployment strategy is proposed. To make a reference point for each sensor node, fuzzy integral is utilized as a multi-criteria decision making process. Three criteria, such as sensor value, crowdedness and confidence, are used for partial evaluation and the degree of consideration for each criterion is represented by fuzzy measure. Global evaluation by fuzzy integral determines the best position for each sensor node independently. To show the effectiveness of the proposed strategy, it is compared with the SPSO07-based deployment strategy through computer simulations in a simulation environment. The results show that the proposed strategy covers much wider area with sensor nodes than the SPSO07-based one.

Potential and dynamics-based Particle Swarm Optimization

The particle swarm optimization (PSO) algorithm is a robust stochastic evolutionary computation technique based on the movement and intelligence of swarms. This paper proposes a novel PSO algorithm, based on the potential field and the motion dynamics model. It is assumed that particles form potential fields and each particle has its own mass. The potential filed and mass are modeled by the particlespsila fitness value. By using these fitness based models, the proposed algorithm performs well, in particular, in avoiding the local minima compare to the original PSO. The proposed PD-PSO successfully solves minimization problems of complex test functions.

Auditory pathway model and its VLSI implementation for robust speech recognition in real-world noisy environment

A robust speech recognition system is reported based on mathematical models of auditory pathway and also their VLSI implementations. The developed auditory model consists of 3 components, i.e., nonlinear feature extraction at cochlea, binaural processing at superior olivery complex, and top-down attention through backward path. The feature extraction is based on cochlear filter bank and time-frequency masking, which is modeled with lateral inhibition in both time and frequency domain. Unlike the popular binaural processing models based on simple interaural time delay and interaural intensity difference our model incorporates hundreds of time-delays for noisy reverberated signals. The top-down (TD) attention comes from familiarity and/or importance of the sound, and a simple but efficient TD attention model had been developed based on error backpropagation algorithm. These auditory models require intensive computing, and special hardwares had been developed for real-time applications. Experimental results demonstrate much better recognition performance in real-world noisy environments.

On subband-based blind separation for noisy speech recognition

A method for denoising noisy speech signals in the feature extraction process for robust speech recognition is proposed. The method uses independent component analysis, in which a noise signal is linearly separated from two noisy speech microphone recordings. In addition, the method is optimized by computing a modified band that sums up FFT point values in several divided ranges of one band, and computes each band energy using the summed values. Thus, the number of unmixing networks is reduced. For instantaneous mixtures of speech and noise, the method showed the same recognition performance as for the clean speech signal case. For noisy speech signals recorded in real environments, the recognition rate was considerably increased after separation and the methods was particularly effective for a very low signal to noise ratio.

Design and Implementation of an Augmented Reality System Using Gaze Interaction

An interactive optical see-through HMD (head-mounted device) which makes use of a users gaze information for the interaction in the AR (augmented reality) environment. In particular, we propose a method to employ a users half-blink information for more efficient interaction. As the interaction is achieved by using a users eye gaze and half-blink information, the proposed system can provide more efficient computing environment. In addition, the proposed system can be quite helpful to those who have difficulties in using conventional interaction methods which use hands or feet. The experimental results present the robustness and efficiency of the proposed system.