Author
Goutam Saha
Other affiliations: Indian Institutes of Technology
Bio: Goutam Saha is an academic researcher from Indian Institute of Technology Kharagpur. The author has contributed to research in topics: Speaker recognition & Phonocardiogram. The author has an hindex of 24, co-authored 73 publications receiving 1996 citations. Previous affiliations of Goutam Saha include Indian Institutes of Technology.
Papers published on a yearly basis
Papers
More filters
TL;DR: The study indicates that liking influences classification performance and also the temporal dynamics of emotional experience across these scales, and observes an inverted U relationship between the level of liking and arousal and dominance classification performance.
38 citations
Posted Content•
TL;DR: In this paper, a speaker verification system using different SAD technique are experimentally evaluated on NIST speech corpora using Gaussian mixture model-universal background model (GMM-UBM) based classifier for clean and noisy conditions.
Abstract: Speech activity detection (SAD) is an essential component for a variety of speech processing applications. It has been observed that performances of various speech based tasks are very much dependent on the efficiency of the SAD. In this paper, we have systematically reviewed some popular SAD techniques and their applications in speaker recognition. Speaker verification system using different SAD technique are experimentally evaluated on NIST speech corpora using Gaussian mixture model- universal background model (GMM-UBM) based classifier for clean and noisy conditions. It has been found that two Gaussian modeling based SAD is comparatively better than other SAD techniques for different types of noises.
37 citations
TL;DR: A new HS localization algorithm is proposed which is based on Hilbert transform (HT) and Heron’s formula and shows a better performance than the comparative Singular Spectrum Analysis (SSA) based method in terms of accuracy, detection error rate (DER), false negative rate (FNR), and execution time (ET).
Abstract: The primary problem with lung sound (LS) analysis is the interference of heart sound (HS) which tends to mask important LS features. The effect of heart sound is more at medium and high flow rate than that of low flow rate. Moreover, pathological HS obscures LS in a higher degree than normal HS. To get over this problem, several HS reduction techniques have been developed. An important preprocessing step in HS reduction is localization of HS components. In this paper, a new HS localization algorithm is proposed which is based on Hilbert transform (HT) and Heron’s formula. In the proposed method, the HS included segment is differentiated from the HS excluded segment by comparing their area with an adaptive threshold. The area of a HS component is calculated from the Hilbert envelope using Heron’s triangular formula. The method is tested on real recorded and simulated HS corrupted LS signals. All the experiments are conducted under low, medium and high breathing flow rates. The proposed method shows a better performance than the comparative Singular Spectrum Analysis (SSA) based method in terms of accuracy (ACC), detection error rate (DER), false negative rate (FNR), and execution time (ET).
36 citations
TL;DR: The proposed filterbank has more speaker discriminative power than commonly used mel filterbank as well as existing data-driven filterbank and it is shown that the acoustic features created with proposed filter bank are better than existing mel-frequency cepstral coefficients (MFCCs) and speech-signal-based Frequency Warping Scale (SFCC) in most cases.
33 citations
TL;DR: A novel method to extract robust features for automatic classification of heart sounds based on Empirical Mode Decomposition (EMD) is presented and it is found that the EMD based feature extraction always performs better than benchmark waveletbased feature extraction technique.
Abstract: A novel method is presented to extract robust features for automatic classification of heart sounds based on Empirical Mode Decomposition (EMD). The work decomposes segmented heart sound cycles with EMD to generate certain intrinsic mode functions (IMFs). It is seen that the first IMF contains mostly high frequency noise, the second and third IMFs carry higher frequency components of our signal of interest and residue contains its low frequency components. A twenty five dimensional feature vector is generated from average energy of the segmented IMFs and residue which serve as input to classifier models. Two different classifiers, Artificial Neural Network (ANN) and Grow and Learn (GAL) network, are used to show the performance of the proposed feature extraction technique. Experiments are conducted on 104 different recordings of heart sound comprising of normal and 12 different pathological cases against three different additive background noises – white Gaussian, hospital and body noise. It is found that the EMD based feature extraction always performs better than benchmark wavelet based feature extraction technique.
33 citations
Cited by
More filters
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.
10,141 citations
01 May 1981
TL;DR: This chapter discusses Detecting Influential Observations and Outliers, a method for assessing Collinearity, and its applications in medicine and science.
Abstract: 1. Introduction and Overview. 2. Detecting Influential Observations and Outliers. 3. Detecting and Assessing Collinearity. 4. Applications and Remedies. 5. Research Issues and Directions for Extensions. Bibliography. Author Index. Subject Index.
4,948 citations
TL;DR: In this paper, the performance of wavelet decomposition-based de-noising and wavelet filter based denoising methods are compared based on signals from mechanical defects, and the comparison result reveals that wavelet filters are more suitable and reliable to detect a weak signature of mechanical impulse-like defect signals, whereas the wavelet transform has a better performance on smooth signal detection.
1,104 citations
1,008 citations
TL;DR: Various procedures used in the analysis of circadian rhythms at the populational, organismal, cellular and molecular levels are reviewed.
Abstract: This article reviews various procedures used in the analysis of circadian rhythms at the populational, organismal, cellular and molecular levels. The procedures range from visual inspection of time plots and actograms to several mathematical methods of time series analysis. Computational steps are described in some detail, and additional bibliographic resources and computer programs are listed.
583 citations