Fundamentals of speech recognition
Fundamentals of speech recognition
Statistical methods for speech recognition
Statistical methods for speech recognition
System identification (2nd ed.): theory for the user
System identification (2nd ed.): theory for the user
Blind equalization of IIR channels using hidden Markov models andextended least squares
IEEE Transactions on Signal Processing
Blind identification of FIR systems driven by Markov-like inputsignals
IEEE Transactions on Signal Processing
Robust switching blind equalizer for wireless cognitive receivers
IEEE Transactions on Wireless Communications - Part 1
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Expectation-Maximization (EM) algorithms have been widely adopted in a variety of areas such as clustering, hidden Markov modeling, channel estimation and equalization, etc. The EM-based approaches to resolve the likelihood maximization involving latent variables are usually very complicated for signal processing and communication applications. To combat this problem, we construct an alternative metric for likelihood or log-likelihood, namely auxiliary function, which results in a novel EM hill-climbing (EM-HC) optimization procedure. We extend our previous efforts along this line of the auxiliary function research to generalize the EM-HC scheme and solve the blind equalization for the complex-valued signals. In this paper, our new EM-HC method, namely efficient Iterative Weighted Least-Mean Squared (IWLMS) algorithm is extended for QPSK and QAM signals. The new version of the IWLMS algorithm greatly outperforms the prevalent blind equalization algorithms based on the constant-modulus and kurtosis criteria according to Monte Carlo simulations.