Voice Activity Detection (VAD) is considered as an important pre-processing step in speech processing systems such as speech enhancement, speech recognition, gender and age identification. VAD helps in reducing the time required to process speech data and to improve final system accuracy by focusing the work on the voiced part of the speech. An automatic technique for VAD using Fuzzy-Neuro technique (FN-AVAD) is presented in this paper. The aim of this work is to alleviate the problem of choosing the best threshold value in traditional VAD methods and achieves automaticity by combining fuzzy clustering and machine learning techniques. Four features are extracted from each speech segment, which are short term energy, zero-crossing rate, autocorrelation, and log energy. A modified version of fuzzy C-Means is then used to cluster speech segments into three clusters; two clusters for voice and one for unvoiced. After that, three feed forward neural networks are trained to adjust their weights, in which each network represents one cluster. To make the final decision regarding the class type of a given speech segment, the membership degrees of this segment in all clusters along with neural networks' decisions are given to a defuzzification step which finally gives the class type of that segment. The proposed FN-AVAD is tested on the public multimodal emotion database, Surrey AudioVisual Expressed Emotion (SAVEE), and the error rate was 2.08%. The achieved results are comparable to the results achieved by the current published works in the literature.
With the revolutionized expansion of the Internet, worldwide information increases the application of communication technology, and the rapid growth of significant data volume boosts the requirement to accomplish secure, robust, and confident techniques using various effective algorithms. Lots of algorithms and techniques are available for data security. This paper presents a cryptosystem that combines several Substitution Cipher Algorithms along with the Circular queue data structure. The two different substitution techniques are; Homophonic Substitution Cipher and Polyalphabetic Substitution Cipher in which they merged in a single circular queue with four different keys for each of them, which produces eight different outputs for
... Show MoreThere many methods for estimation of permeability. In this Paper, permeability has been estimated by two methods. The conventional and modified methods are used to calculate flow zone indicator (FZI). The hydraulic flow unit (HU) was identified by FZI technique. This technique is effective in predicting the permeability in un-cored intervals/wells. HU is related with FZI and rock quality index (RQI). All available cores from 7 wells (Su -4, Su -5, Su -7, Su -8, Su -9, Su -12, and Su -14) were used to be database for HU classification. The plot of probability cumulative of FZI is used. The plot of core-derived probability FZI for both modified and conventional method which indicates 4 Hu (A, B, C and D) for Nahr Umr forma
... Show MoreSemi-parametric regression models have been studied in a variety of applications and scientific fields due to their high flexibility in dealing with data that has problems, as they are characterized by the ease of interpretation of the parameter part while retaining the flexibility of the non-parametric part. The response variable or explanatory variables can have outliers, and the OLS approach have the sensitivity to outliers. To address this issue, robust (resistance) methods were used, which are less sensitive in the presence of outlier values in the data. This study aims to estimate the partial regression model using the robust estimation method with the wavel
... Show MoreThe Web Design Quality Index, known as WDQI, was applied to assess the quality of websites for six Iraqi universities, namely Basra University, Mosul, Muthanna, Samarra, Dijla University College, and Al-Isra University College. The results of the index showed that the universities of Basra and Dijla University College had the highest value, at 71.07 and 70.39, respectively. Its final evaluation metric was that the website of these two universities needed a slight improvement. As for the rest of the other universities, the final values of the index ranged from 64.72-69.71. When the final values of the index are displayed on the final evaluation scale, it appears that the websites of the four universities need many improvements. The study
... Show MoreThe microstructure and wear properties of 392 Al alloy with different Mg contents were studied using centrifugal casting. All melted alloys were heated to 800 ºC and poured into the preheated centrifugal casting mold (200-250 ºC) at different mould rotational speeds (1500, 1900 and 2300 r.p.m). It is clear from the results obtained that wear rate was dependent on the Mg content, applied load and mould rotational speed. Furthermore, wear test showed that the minimum wear rate was found in the inner layer of produced rings at mould rotational speed of 1900 r.p.m and Mg content of 5%.
This research paper aimed to quantitively characterize the pore structure of shale reservoirs. Six samples of Silurian shale from the Ahnet basin were selected for nitrogen adsorption-desorption analysis. Experimental findings showed that all the samples are mainly composed of mesopores with slit-like shaped pores, as well as the Barrett-Joyner-Halenda pore volume ranging from 0.014 to 0.046 cm3/ 100 g, where the lowest value has recorded in the AHTT-1 sample, whereas the highest one in AHTT-6, while the rest samples (AHTT-2, AHTT-3, AHTT-4, AHTT-5) have a similar average value of 0.03 cm3/ 100 g. Meanwhile, the surface area and pore size distribution were in the range of 3.8 to 11.1 m2 / g and 1.7 to 40 nm, respectively.
... Show MoreIn this article, the research presents a general overview of deep learning-based AVSS (audio-visual source separation) systems. AVSS has achieved exceptional results in a number of areas, including decreasing noise levels, boosting speech recognition, and improving audio quality. The advantages and disadvantages of each deep learning model are discussed throughout the research as it reviews various current experiments on AVSS. The TCD TIMIT dataset (which contains top-notch audio and video recordings created especially for speech recognition tasks) and the Voxceleb dataset (a sizable collection of brief audio-visual clips with human speech) are just a couple of the useful datasets summarized in the paper that can be used to test A
... Show MoreWind energy is considered one of the most important sources of renewable energy in the world, because it contributes to reducing the negative effects on the environment. The most important types of wind turbines are horizontal and vertical axis wind turbines. This work presents the full details of design for vertical axis wind turbine (VAWT) and how to find the optimal values of necessary factors. Additionally, the results shed light on the efficiency and performance of the VAWT under different working conditions. It was taken into consideration the variety of surrounding environmental conditions (such as density and viscosity of fluid, number of elements of the blade, etc.) to simulate the working of vertical wind turbines under di
... Show More