A constrained sequential EM algorithm for speech enhancement

Authors:
Sunho Park;Seungjin Choi
Affiliations:
Department of Computer Science, Pohang University of Science and Technology, San 31 Hyoja-dong, Nam-gu, Pohang 790-784, Republic of Korea;Department of Computer Science, Pohang University of Science and Technology, San 31 Hyoja-dong, Nam-gu, Pohang 790-784, Republic of Korea
Venue:
Neural Networks
Year:
2008

Citing 6
Cited 2

Flexible Independent Component Analysis

Journal of VLSI Signal Processing Systems
On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks

UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
A signal subspace approach for speech enhancement

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Recursive expectation-maximization (EM) algorithms for time-varyingparameters with applications to multiple target tracking

IEEE Transactions on Signal Processing
Iterative and sequential algorithms for multisensor signalenhancement

IEEE Transactions on Signal Processing

A fast algorithm for AR parameter estimation using a novel noise-constrained least-squares method

Neural Networks
A Novel Expectation-Maximization Framework for Speech Enhancement in Non-Stationary Noise Environments

IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Speech enhancement is a fundamental problem, the goal of which is to estimate clean speech s"t, given a noise-contaminated signal s"t+n"t, where n"t is white or colored noise. This task can be viewed as a probabilistic inference problem which involves estimating the posterior distribution of hidden clean speech, given a noisy observation. Kalman filter is a representative method but is restricted to Gaussian distributions only. We consider the generalized auto-regressive (GAR) model in order to capture the non-Gaussian characteristics of speech. Then we present a constrained sequential EM algorithm where Rao-Blackwellized particle filters (RBPFs) are used in the E-step and model parameters are updated in a sequential manner in the M-step under positivity constraints for noise variance parameters. Numerical experiments confirm the high performance of our proposed method, compared to Kalman filter-based methods, in the task of sequential speech enhancement.