Monaural 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 achieves (4.81) dB GNSDR gain, (7.28) dB GSIR gain, and (3.39) dB GSAR gain in comparison to current approaches
Background: The pandemic crisis prompted the world to adopt unexpected approaches to continue life as normally as possible. The education sector, including professors, students, and the overall teaching system, has been particularly affected. Objective: This study seeks to evaluate the benefits, challenges, and strategies related to COVID-19 from the perspectives of college students, particularly those in higher education in Iraq. Method: The online survey questionnaire was distributed via Google Forms and specifically aimed at undergraduate dental students. Results: A total of 348 students participated in the survey. There was a significant correlation (P > 0.01) between student satisfaction with hybrid learning and their experi
... Show MoreThe use of deep learning.
This paper presents a hybrid genetic algorithm (hGA) for optimizing the maximum likelihood function ln(L(phi(1),theta(1)))of the mixed model ARMA(1,1). The presented hybrid genetic algorithm (hGA) couples two processes: the canonical genetic algorithm (cGA) composed of three main steps: selection, local recombination and mutation, with the local search algorithm represent by steepest descent algorithm (sDA) which is defined by three basic parameters: frequency, probability, and number of local search iterations. The experimental design is based on simulating the cGA, hGA, and sDA algorithms with different values of model parameters, and sample size(n). The study contains comparison among these algorithms depending on MSE value. One can conc
... Show MoreThe 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 pi
... Show MoreThe Umayyad era is characterized by the diversity of the subjects and their multiplicity in the literary phenomena. These phenomena are singing phenomena, although they were known in previous eras, they took a distinctive form in the era.
In this light, the researcher tried to prove that singing theory in the Umayyad period was characterized by development and renewal. The research was entitled (evolution and renewal in the theory of singing in the Umayyad era).
In this study, nano TiO2 was prepared with titanium isopropoxide (TTIP) as a resource to titanium oxide. The catalyst was synthesized using phosphotungstic acid (PTA) and, stearyl trimethyl ammonium bromide (STAB) was used as the structure-directing material. Characterization of the product was done by the X-ray diffraction (XRD), X-ray fluorescent spectroscopy (XRF), nitrogen adsorption/desorption measurements, Atomic Force Microscope (AFM) and Fourier transform infrared (FTIR) spectra, were used to characterize the calcined TiO2 nanoparticles by STAB and PWA. The TiO2 nanomaterials were prepared in three crystalline forms (amorphous, anatase, anatase-rutile). The results showed that the
... Show MoreIn this study, nano TiO2 was prepared with titanium isopropoxide (TTIP) as a resource to titanium oxide. The catalyst was synthesized using phosphotungstic acid (PTA) and, stearyl trimethyl ammonium bromide (STAB) was used as the structure-directing material. Characterization of the product was done by the X-ray diffraction (XRD), X-ray fluorescent spectroscopy (XRF), nitrogen adsorption/desorption measurements, Atomic Force Microscope (AFM) and Fourier transform infrared (FTIR) spectra, were used to characterize the calcined TiO2 nanoparticles by STAB and PWA. The TiO2 nanomaterials were prepared in three crystalline forms (amorphous, anatase, anatase-rutile). The results showed that the nanoparticles of anatase TiO2 have good cata
... Show More