Showing papers by "Goutam Saha published in 2011"

Reduction of heart sound interference from lung sound signals using empirical mode decomposition technique.

Abstract: During the recording time of lung sound (LS) signals from the chest wall of a subject, there is always heart sound (HS) signal interfering with it. This obscures the features of lung sound signals and creates confusion on pathological states, if any, of the lungs. A novel method based on empirical mode decomposition (EMD) technique is proposed in this paper for reducing the undesired heart sound interference from the desired lung sound signals. In this, the mixed signal is split into several components. Some of these components contain larger proportions of interfering signals like heart sound, environmental noise etc. and are filtered out. Experiments have been conducted on simulated and real-time recorded mixed signals of heart sound and lung sound. The proposed method is found to be superior in terms of time domain, frequency domain, and time-frequency domain representations and also in listening test performed by pulmonologist.

Bayesian marginal statistics for speech enhancement using log Gabor wavelet

Abstract: This paper deals with single-channel speech enhancement technique. Initially, the suitability of Log Gabor Wavelet (LGW) is investigated in speech enhancement approach and a novel speech enhancer by Bayesian Maximum a Posteriori (MAP) based Marginal Statistical Characterization (MSC) is developed. The LGW filters are traditional choice for obtaining localized frequency information and these offer the best simultaneous localization of time and frequency information. The MSC is applied in each scale of the LGW, that means a level dependent shrinkage rule is taken to suppress the background perturbations. The pdf of the LGW filtered speech coefficient is modeled with Generalized Laplacian Distribution (GLD), which allows a high approximation accuracy for Laplace distributed real and imaginary parts of the speech coefficients. The robustness of the proposed framework is tested on NOIZEUS speech corpus against seven different established speech enhancement algorithms. Experimental results show that the proposed estimator yield a higher improvement in Segmental SNR (S-SNR), lower Log Area Ratio (LAR) and Weighted Spectral Slope (WSS) distortion compared to existing speech enhancement algorithms.