In 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 AVSS systems. In its basic form, this review aims to highlight the growing importance of AVSS in improving the quality of audio signals.
This study aimed to assess orthodontic postgraduate students’ use of social media during the COVID-19 lockdown. Ninety-four postgraduate students (67 master’s students and 27 doctoral students) were enrolled in the study and asked to fill in an online questionnaire by answering questions regarding their use of social media during the COVID-19 lockdown. The frequency distributions and percentages were calculated using SPSS software. The results showed that 99% of the students used social media. The most frequently used type of social media was Facebook, 94%, followed by YouTube, 78%, and Instagram, 65%, while Twitter and Linkedin were used less, and no one used Blogger. About 63% of the students used elements of social media to l
... Show MoreThere is no doubt that development is a human necessity and an urgent technical imperative that science imposes on all aspects of societal life. Especially in the field of graphic design, as logos are among the most prominent graphic achievements of an interactive nature with the requirements of the technical and functional era to serve the recipient and the continuity of interaction with him through a visual message sent to him constantly to remind him of what he interacted with in advance, which is known as visual identity, and during the process of developing logos especially And by providing designs that suit the contemporary technical and functional development, we often see the logo lose its visual identity. Therefore, the research
... Show MoreThe speech recognition system has been widely used by many researchers using different
methods to fulfill a fast and accurate system. Speech signal recognition is a typical
classification problem, which generally includes two main parts: feature extraction and
classification. In this paper, a new approach to achieve speech recognition task is proposed by
using transformation techniques for feature extraction methods; namely, slantlet transform
(SLT), discrete wavelet transforms (DWT) type Daubechies Db1 and Db4. Furthermore, a
modified artificial neural network (ANN) with dynamic time warping (DTW) algorithm is
developed to train a speech recognition system to be used for classification and recognition
purposes. T
The enhancement of heat exchanger performance was investigated using dimpled tubes tested at different Reynolds numbers, in the present work four types of dimpled tubes with a specified configuration manufactured, tested and then compared performance with the smooth tube and other passive techniques performance. Two dimpled arrangements along the tube were investigated, these are inline and staggered at constant pitch ratio X/d=4, the test results showed that Nusselts number (heat transfer) of the staggered array is higher than the inline array by 13%. The effect of different depths of the dimple (14.5 mm and 18.5 mm) has been also investigated; a tube with large dimple diameter enhanced the Nusselts number by about 25% for the ran
... Show More
Abstract: Narrow laser pulses have been essential sources in optical communication system. High data rate optical communication network system demands compressed laser source with unique optical property. In this work using pulsed duration (9) ns, peak power 1.2297mW, full width half maximum (FWHM) 286 pm, and wavelength center 1546.7 nm as compression laser source. Mach Zehnder interferometer (MZI) is built by considering two ways. First, polarization maintaining fiber (PMF) with 10 cm length is used to connect between laser source and fiber brag grating analysis (FBGA). Second, Nested Mach Zehnder interferometer (NMZI) was designed by using three PMFs with 10 cm length. These three Fibers are splicing to sing
... Show MoreThe study is based on the selective binding ability of the drug compound procaine (PRO) on a surface imprinted with nylon 6 (N6) polymer. Physical characterization of the polymer template was performed by X-ray diffraction and DSC thermal analysis. The imprinted polymer showed a high adsorption capacity to trap procaine (237 µg/g) and excellent recognition ability with an imprinted factor equal to 3.2. The method was applied to an extraction column simulating a solid-phase extraction to separate the drug compound in the presence of tinoxicam and nucleosimide separately and in a mixture of them with a recovery rate more than the presence of tinoxicam and nucleosimide separately and in a mixture of them with a recovery rate of more t
... Show MoreData hiding is the process of encoding extra information in an image by making small modification to its pixels. To be practical, the hidden data must be perceptually invisible yet robust to common signal processing operations. This paper introduces a scheme for hiding a signature image that could be as much as 25% of the host image data and hence could be used both in digital watermarking as well as image/data hiding. The proposed algorithm uses orthogonal discrete wavelet transforms with two zero moments and with improved time localization called discrete slantlet transform for both host and signature image. A scaling factor ? in frequency domain control the quality of the watermarked images. Experimental results of signature image
... Show More