Koeng-Mo Sung

Modified K-means algorithm for vector quantizer design

The K-means algorithm is widely used in vector quantizer (VQ) design and clustering analysis. In VQ context, this algorithm iteratively updates an initial codebook and converges to a locally optimal codebook in certain conditions. It iteratively satisfies each of the two necessary conditions for an optimal quantizer; the nearest neighbor condition for the partition and centroid condition for the codevectors. In this letter, we propose a new algorithm for both vector quantizer design and clustering analysis as an alternative to the conventional K-means algorithm. The algorithm is almost the same as the K-means algorithm except for a modification at codebook updating step. It does not satisfy the centroid condition iteratively, but asymptotically satisfies it as the number of iterations increases. Experimental results show that the algorithm converges to a better locally optimal codebook with an accelerated convergence speed.

A fast encoding algorithm for vector quantization

In this letter, we present a fast encoding algorithm for vector quantization that uses two characteristics of a vector, mean, and variance. Although a similar method using these features was already proposed, it handles these features separately, On the other hand, the proposed algorithm utilizes these features simultaneously to save computation time all the more. Since the proposed algorithm rejects those codewords that are impossible to be the nearest codeword, it produces the same output as the conventional full search algorithm. The simulation results confirm the effectiveness of the proposed algorithm.

Channel estimation for OFDM with fast fading channels by modified Kalman filter

In OFDM systems, time-varying channels destroy the orthogonality between subchannels and cause interchannel interference (ICI) in conventional frequency-domain channel estimation approaches. To compensate for this ICI, we propose a new channel estimator for OFDM systems in a fast and frequency-selective Rayleigh fading channel. The proposed method is based on a new modified Kalman filter (MKF). The time-varying channel is modeled as an autoregressive (AR) process and the proposed MKF is used to estimate this AR parameter. In addition, to track the time-varying channel, a channel predictor using regression analysis and the minimum mean-squared error (MMSE) time-domain equalizer are also proposed. The simulation results show that the proposed channel estimator can effectively compensate for ICI.

A multi-channel audio compression method with virtual source location information for MPEG-4 SAC

Binaural cue coding (BCC) was introduced as an efficient representation method for MPEG-4 SAC (spatial audio coding). However, in a low bit-rate environment, the spectrum of BCC output signals degrades with respect to the perceptual level. The proposed system in this paper estimates VSLI (virtual source location information) as the side information. The VSLI is the angle representation of spatial images between channels on playback layout. The subjective assessment results show that the proposed method provides better audio quality than the BCC method for encoding multi-channel signals.

Variable forgetting factor linear least squares algorithm for frequency selective fading channel estimation

In this article, the variable forgetting factor linear least squares algorithm is presented to improve the tracking capability of channel estimation. A linear channel model with respect to time change describes a time-varying channel more accurately than a conventional stationary channel model. To reduce the estimation error due to model mismatch, we incorporate the modified variable forgetting factor into the proposed algorithm. Compared to the existing algorithms-exponentially windowed recursive least squares algorithm with the optimal forgetting factor and linear least squares algorithm-the proposed method makes a remarkable improvement in a fast fading environment. The effects of channel parameters such as signal-to-noise ratio and fading rate are investigated by computer simulations.

On robust Kalman filtering with forgetting factor for sequential speech analysis

Abstract We propose a robust Kalman filter with forgetting factor to estimate the time-varying parameters of speech signals. The proposed robust Kalman filter is based on a modified least-squares criterion with forgetting factor. The input signal is assumed to have a heavy-tailed non-Gaussian nature with outliers due to spiky excitation. To alleviate the effects of outliers, this algorithm extends the concept of Hubers min-max approach, named M-estimation , to the Kalman filtering. The introduction of forgetting factor enables the time-varying speech parameters to be estimated, giving more weight on the most recent portion of the data. Experimental results show that the proposed algorithm achieves more accurate estimation and provides improved tracking performance.

The blind widely linear minimum output energy algorithm for DS-CDMA systems

A novel blind widely linear (WL) minimum output energy (MOE) algorithm is proposed for the code-division multiple-access (CDMA) receiver. Whereas the recently proposed WL-MOE algorithm is only applicable to real-valued modulation, the proposed receiver is applicable to complex-valued modulation as well. In this correspondence, the blind WL-MOE filter is analyzed, and the convergence properties of an adaptive implementation are derived. The proposed algorithm dramatically outperforms nonwidely linear MOE algorithms when at least one of the signals (desired or interference) is improper, i.e., real-valued. While there is a small performance and complexity penalty relative to the previous WL-MOE algorithm when only real-valued modulation is employed, the great advantage of the proposed algorithm in being able to handle complex valued modulation (such as the popular QAM) in most cases should outweigh this slight penalty.

Extended generalized total least squares method for the identification of bilinear systems

The extended generalized total least squares (e-GTLS) method (that consider the special structure of the data matrix) is proposed as one of the bilinear system parameters. Considering that the input is noise free and that bilinear system equation is linear with respect to the output, we extend the GTLS problem. The extended GTLS problem is reduced to an unconstrained minimization problem and is then solved by the Newton-Raphson method. We compare the GTLS method and the extended GTLS method as far as the accuracy of the estimated system parameters is concerned.

Time-varying signal frequency estimation by VFF Kalman filtering

Abstract In this paper, a new algorithm is proposed for estimating a time-varying signal frequency. The proposed method introduces a variable forgetting factor (VFF) into Kalman filter so that this approach does not require any pre-determined forgetting factor. The proposed method is tested on two nonstationary signals. Results show that the proposed algorithm offers a more accurate estimation of signal frequency and faster convergence speed than conventional Kalman filtering algorithm.

A fast vector quantization encoding algorithm using multiple projection axes

Computation of nearest neighbor generally requires a large number of expensive distance calculations. In this paper, we present an algorithm which uses multiple projection axes to accelerate the encoding process of VQ by eliminating the necessity of calculating many distances. Since the proposed algorithm rejects those codewords that are impossible to be the nearest codeword, it produces the same output as a conventional full search algorithm. The simulation results confirm the effectiveness of the proposed algorithm.