Glottal Closure Instants (GCIs) correspond to the temporal locations of significant excitation to the vocal tract occurring during the production of voiced speech. GCI detection from speech signals is a well-studied problem given its importance in speech processing. Most of the existing approaches for GCI detection adopt a two-stage approach (i) Transformation of speech signal into a representative signal where GCIs are localized better, (ii) extraction of GCIs using the representative signal obtained in first stage. The former stage is accomplished using signal processing techniques based on the principles of speech production and the latter with heuristic-algorithms such as dynamicprogramming and peak-picking. These methods are thus taskspecific and rely on the methods used for representative signal extraction. However in this paper, we formulate the GCI detection problem from a representation learning perspective where appropriate representation is implicitly learned from the rawspeech data samples. Specifically, GCI detection is cast as a supervised multi-task learning problem solved using a deep convolutional neural network jointly optimizing a classification and regression cost. The learning capability is demonstrated with several experiments on standard datasets. The results compare well with the state-of-the-art algorithms while performing better in the case of presence of real-world non-stationary noise.
Sodium aryltellurolate (ArTe-Na', where Ar = 4-MeOC,H4 or 4-EtOC,H4) reacts with 2-bromoethylamine resulting in the (Te, N) ligands 2-aryltelluroethylamine (ArTeCH,CH NH2, 1) which have been characterized by elemental analyses, molecular weight, IR, 'H and "C NMR spectra. With HgCI,, they form HgC12.1 type of complexes. IR, 'H and I3C NMR spectra of the complexes suggest that 1 ligates as a bidentate ligand with respect to Hg(l1). Osmometric molecular weight measurements suggest that on heating the mercury complex HgCl,.lb (Ar = 4-EtOC,H4) in solution, relatively less soluble species result. It seems to have two Hg atoms bridged by two (Te, N) ligands. The HgCI,.ln (Ar = 4-MeOC,H4) has very low solubility in organic solvents and. therefore, seems to be dimerized or polymerized during the synthesis. Analysis of CH2 rocking bands in IR spectra suggests that two CH2 groups of the ligands are most probably in a gauche conformation in the mercury complexes.
This paper presents a two-dimensional wavelet based decomposition algorithm for classification of biomedical images. The twodimensional wavelet decomposition is done up to five levels for the input images. Histograms of decomposed images are then used to form the feature set. This feature set is further reduced using probabilistic principal component analysis. The reduced set of features is then fed into either nearest neighbor algorithm or feed-forward artificial neural network, to classify images. The algorithm is compared with three other techniques in terms of accuracy. The proposed algorithm has been found better up to 3.3%, 12.75%, and 13.75% on average over the first, second, and third algorithm, respectively, using KNN and up to 6.22%, 13.9%, and 14.1% on average using ANN. The dataset used for comparison consisted of CT Scan images of lungs and MR images of heart as obtained from different sources.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.