Compressing the speech reduces the data storage requirements, leading to reducing the time of transmitting the digitized speech over long-haul links like internet. To obtain best performance in speech compression, wavelet transforms require filters that combine a number of desirable properties, such as orthogonality and symmetry.The MCT bases functions are derived from GHM bases function using 2D linear convolution .The fast computation algorithm methods introduced here added desirable features to the current transform. We further assess the performance of the MCT in speech compression application. This paper discusses the effect of using DWT and MCT (one and two dimension) on speech compression. DWT and MCT performances in terms of comp

In this paper, a fusion of K models of full-rank weighted nonnegative tensor factor two-dimensional deconvolution (K-wNTF2D) is proposed to separate the acoustic sources that have been mixed in an underdetermined reverberant environment. The model is adapted in an unsupervised manner under the hybrid framework of the generalized expectation maximization and multiplicative update algorithms. The derivation of the algorithm and the development of proposed full-rank K-wNTF2D will be shown. The algorithm also encodes a set of variable sparsity parameters derived from Gibbs distribution into the K-wNTF2D model. This optimizes each sub-model in K-wNTF2D with the required sparsity to model the time-varying variances of the sources in the s

Recently, Image enhancement techniques can be represented as one of the most significant topics in the field of digital image processing. The basic problem in the enhancement method is how to remove noise or improve digital image details. In the current research a method for digital image de-noising and its detail sharpening/highlighted was proposed. The proposed approach uses fuzzy logic technique to process each pixel inside entire image, and then take the decision if it is noisy or need more processing for highlighting. This issue is performed by examining the degree of association with neighboring elements based on fuzzy algorithm. The proposed de-noising approach was evaluated by some standard images after corrupting them with impulse

In this paper, an algorithm through which we can embed more data than the
regular methods under spatial domain is introduced. We compressed the secret data
using Huffman coding and then this compressed data is embedded using laplacian
sharpening method.
We used Laplace filters to determine the effective hiding places, then based on
threshold value we found the places with the highest values acquired from these filters
for embedding the watermark. In this work our aim is increasing the capacity of
information which is to be embedded by using Huffman code and at the same time
increasing the security of the algorithm by hiding data in the places that have highest
values of edges and less noticeable.
The perform

Text based-image clustering (TBIC) is an insufficient approach for clustering related web images. It is a challenging task to abstract the visual features of images with the support of textual information in a database. In content-based image clustering (CBIC), image data are clustered on the foundation of specific features like texture, colors, boundaries, shapes. In this paper, an effective CBIC) technique is presented, which uses texture and statistical features of the images. The statistical features or moments of colors (mean, skewness, standard deviation, kurtosis, and variance) are extracted from the images. These features are collected in a one dimension array, and then genetic algorithm (GA) is applied for image clustering.

Future wireless communication systems must be able to accommodate a large number of users and simultaneously to provide the high data rates at the required quality of service. In this paper a method is proposed to perform the N-Discrete Hartley Transform (N-DHT) mapper, which are equivalent to 4-Quadrature Amplitude Modulation (QAM), 16-QAM, 64-QAM, 256-QAM, … etc. in spectral efficiency. The N-DHT mapper is chosen in the Multi Carrier Code Division Multiple Access (MC-CDMA) structure to serve as a data mapper instead of the conventional data mapping techniques like QPSK and QAM schemes. The proposed system is simulated using MATLAB and compared with conventional MC-CDMA for Additive White Gaussian Noise, flat, and multi-path selective fa

Quantitative analysis of human voice has been subject of interest and the subject gained momentum when human voice was identified as a modality for human authentication and identification. The main organ responsible for production of sound is larynx and the structure of larynx along with its physical properties and modes of vibration determine the nature and quality of sound produced. There has been lot of work from the point of view of fundamental frequency of sound and its characteristics. With the introduction of additional applications of human voice interest grew in other characteristics of sound and possibility of extracting useful features from human voice. We conducted a study using Fast Fourier Transform (FFT) technique to analy