The speaker identification is one of the fundamental problems in speech processing and voice modeling. The speaker identification applications include authentication in critical security systems and the accuracy of the selection. Large-scale voice recognition applications are a major challenge. Quick search in the speaker database requires fast, modern techniques and relies on artificial intelligence to achieve the desired results from the system. Many efforts are made to achieve this through the establishment of variable-based systems and the development of new methodologies for speaker identification. Speaker identification is the process of recognizing who is speaking using the characteristics extracted from the speech's waves like pitch, tone, and frequency. The speaker's models are created and saved in the system environment and used to verify the identity required by people accessing the systems, which allows access to various services that are controlled by voice, speaker identification involves two main parts: the first part is the feature extraction and the second part is the feature matching.
An experimental and theoretical study has been done to investigate the thermal performance of different types of air solar collectors, In this work air solar collector with a dimensions of (120 cm x90 cm x12 cm) , was tested under climate condition of Baghdad city with a (43° tilt angel) by using the absorber plate (1.45 mm thickness, 115 cm height x 84 cm width), which was manufactured from iron painted with a black matt.
The experimental test deals with five types of absorber:-
Conventional smooth flat plate absorber , Finned absorber , Corrugated absorber plate, Iron wire mesh on absorber And matrix of porous media on absorber .
The hourly and average efficiency of the collectors
... Show MoreFour rapid, accurate and very simple derivative spectrophotometric techniques were developed for the quantitative determination of binary mixtures of estradiol (E2) and progesterone (PRG) formulated as a capsule. Method I is the first derivative zero-crossing technique, derivative amplitudes were detected at the zero-crossing wavelength of 239.27 and 292.51 nm for the quantification of estradiol and 249.19 nm for Progesterone. Method II is ratio subtraction, progesterone was determined at λmax 240 nm after subtraction of interference exerted by estradiol. Method III is modified amplitude subtraction, which was established using derivative spectroscopy and mathematical manipulations. Method IIII is the absorbance ratio technique, absorba
... Show MoreThis research develops a new method based on spectral indices and random forest classifier to detect paddy rice areas and then assess their distributions regarding to urban areas. The classification will be conducted on Landsat OLI images and Landsat OLI/Sentinel 1 SAR data. Consequently, developing a new spectral index by analyzing the relative importance of Landsat bands will be calculated by the random forest. The new spectral index has improved depending on the most three important bands, then two additional indices including the normalized difference vegetation index (NDVI), and standardized difference built-up index (NDBI) have been used to extract paddy rice fields from the data. Several experiments being
... Show MoreIn this paper, a subspace identification method for bilinear systems is used . Wherein a " three-block " and " four-block " subspace algorithms are used. In this algorithms the input signal to the system does not have to be white . Simulation of these algorithms shows that the " four-block " gives fast convergence and the dimensions of the matrices involved are significantly smaller so that the computational complexity is lower as a comparison with " three-block " algorithm .
Audio classification is the process to classify different audio types according to contents. It is implemented in a large variety of real world problems, all classification applications allowed the target subjects to be viewed as a specific type of audio and hence, there is a variety in the audio types and every type has to be treatedcarefully according to its significant properties.Feature extraction is an important process for audio classification. This workintroduces several sets of features according to the type, two types of audio (datasets) were studied. Two different features sets are proposed: (i) firstorder gradient feature vector, and (ii) Local roughness feature vector, the experimentsshowed that the results are competitive to
... Show MoreAlthough the Wiener filtering is the optimal tradeoff of inverse filtering and noise smoothing, in the case when the blurring filter is singular, the Wiener filtering actually amplify the noise. This suggests that a denoising step is needed to remove the amplified noise .Wavelet-based denoising scheme provides a natural technique for this purpose .
In this paper a new image restoration scheme is proposed, the scheme contains two separate steps : Fourier-domain inverse filtering and wavelet-domain image denoising. The first stage is Wiener filtering of the input image , the filtered image is inputted to adaptive threshold wavelet
... Show MoreIn some cases, surgeons need to navigate through the computer system for reconfirmation patients’ details and unfortunately surgeons unable to manage both computer system and operation at the same time. In this paper we propose a solution for this problem especially designed for heart surgeon, by introducing voice activation system with 3D visualization of Angiographic images, 2D visualization of Echocardiography processed video and selected patient’s details. In this study, the processing, approximation of the 3D angiography and the visualization of the 2D echocardiography video with voice recognition control are the most challenging work. The work involve with predicting 3D coronary three from 2D angiography image and also image enhan
... Show MoreMonaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achi
... Show MoreThe aim of this stud to isolate and identified of A. fumigatus from different sources and study the genetic diversity among these isolates by using RAPD and ISSR markers.Collected 20 samples from 7samples were isolated A. fumigatusisolates were characterized depending on its morphological, then extracted DNA from its.RAPD markersrandomly bandingwith sitesof genome more than ISSR markers where the primer OPN-07 achieved discriminative power (19.1) and 43 bands, while ISSR6 achieved discriminative power (17.1) with 32 bands.ISSR were more efficiency in specific binding then RAPD, ISSR primers has great a binding to production unique band, when 9 primers from 01 primers, ISSR9 was produce (5) unique bands, while RAPD markers was low ability
... Show More