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.
compound [1] was formed from the reaction of benzoin and benzaldehyde in the presence of ammonia, which was reacted with sodium hydride in DMF to obtain imidazole salt. This salt was reacted with adipoyl chloride to give compound [2]. Acid hydrazide derivative [3] was obtained from the reaction of compound [2] with hydrazine hydrate. After that Shiff bases [4-9] have been synthesized from the reaction of compound [3] with different aromatic aldehydes. These new formed compounds were diagnosed by 13C-NMR, 1H-NMR for some of them (in Ahl-Albate University in Jordan) and FT-IR spectroscopy (In Baghdad University). All of the prepared products have been studied their biological activities toward two kinds of bacteria. These products show
... Show MoreA new series of Sulfamethoxazole derivatives was prepared and examined for antifibrinolytic and antimicrobial activities. Sulfamethoxazole derivatives bear heterocyclic moieties such as 1,3,4-thiadiazine {3}, pyrazolidine-3,5-diol {4} 6-hydroxy-1,3,4-thiadiazinane-2-thione {5} and [(3-methyl-5-oxo-4,5-dihydro-1H-pyrazol-4-yl)diazenyl] {8}. Their structures were elucidated by spectral methods (FT-IR, H1-NMR). Physical properties are also determined for all compound derivatives. Recently prepared compounds were tested for their antimicrobial activity in the laboratory. Each screened compound showed good tendency to moderate antimicrobial activity.
Synthesis of 2-mercaptobenzothiazole (A1) is performed from the reaction of o-aminothiophenol and carbon disulfide CS2 in ethanol under basic condition. Compound (A1) is reacted with chloro acetyl chloride to give compound (A2). Hydrazide acid compound (A3) is obtained from the reaction of compound (A2) with hydrazine hydrate in ethanol under reflux in the presence of glacial acetic acid .The reaction of hydrazide acid compound (A3) with ethyl acetoacetate gives pyrazole compound (A4). The new hydrazone compound (A5) was prepared from the reaction of compound (A3) with benzaldehyde. Reaction of compound
... Show MoreThis study including synthesis of some new Schiff bases compounds [1‐6] from the reaction of Sulfamethoxazole drug with some aromatic aldehydes in classical Schiff base method then treatment Schiff bases with succinic anhydride to get oxazepines rings [7-11]These derivatives were characterized by melting point, FT‐IR, 1H NMR and mass spectra. Some of synthesized compounds were evaluated in vitro for their antibacterial activities against three kinds of pathogenic strains Staphylococcus aureus, Escherichia coli
During COVID-19, wearing a mask was globally mandated in various workplaces, departments, and offices. New deep learning convolutional neural network (CNN) based classifications were proposed to increase the validation accuracy of face mask detection. This work introduces a face mask model that is able to recognize whether a person is wearing mask or not. The proposed model has two stages to detect and recognize the face mask; at the first stage, the Haar cascade detector is used to detect the face, while at the second stage, the proposed CNN model is used as a classification model that is built from scratch. The experiment was applied on masked faces (MAFA) dataset with images of 160x160 pixels size and RGB color. The model achieve
... Show MoreBackground: The figure for the clinical application of computed tomography have been increased significantly in oral and maxillofacial field that supply the dentists with sufficient data enables them to play a main role in screening osteoporosis, therefore Hounsfield units of mandibular computed tomography view used as a main indicator to predict general skeleton osteoporosis and fracture risk factor. Material and Methods: Thirty subjects (7 males &23 females) with a mean age of (60.1) years underwent computed tomographic scanning for different diagnostic assessment in head and neck region. The mandibular bone quality of them were determined through Hounsfield units of CT scan images and were correlated with the bone mineral density v
... Show MoreA nano-sensor for nitrotyrosine (NT) molecule was found by studying the interactions of NT molecule with new B24N24 nanocages. It was calculated using density functionals in this case. The predicted adsorption mechanisms included physical and chemical adsorption with the adsorption energy of −2.76 to −4.60 and −11.28 to −15.65 kcal mol−1, respectively. The findings show that an NT molecule greatly increases the electrical conductivity of a nanocage by creating electronic noise. Moreover, NT adsorption in the most stable complexes significantly affects the Fermi level and the work function. This means the B24N24 nanocage can detect NT as a Φ–type sensor. The recovery time was determined to be 0.3 s. The sensitivity of pure BN na
... Show More