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.
In the present study, mixed ligand compounds of Mn(II), Ni(II), Co(II), Cu(II), Cd(II) and Hg(II) were synthesized using new Ligand N1,N4-bis (pyrimidin-2-ylcarbamothioyl) succinimide (NPS) derived from [Butanedioyl diisothiocyanate with 2- aminipyridine] as first ligand, proline (pro) as second ligand and evaluation of their antioxidant activities for ligand, nickel and cobalt complex towards 1.1-Di-phenyl-2picrylhydrazyl (DPPH) will be compared to the standard anti-oxidants (i.e. the ascorbic acid). Those materials that have been prepared provided results are a result of exhibiting different activities of the radical scavenging for all of the compounds. Compounds were observed then confirmed through the Fourier-tra
... Show MorePolymer metal complexes of poly ethylene glycol acetal and Ag (I), Cu (II), Ni (II), Mn (II), Co (III) and Hg (II) were prepared from the reaction of PEG with aldehyde derived from Erythro-ascorbic acid (pentulosono-ɣ-lactone-2, 3- enedianisoate). All these compounds were characterized by Thin Layer Chromatography (TLC) and FTIR spectra and aldehyde was also characterized by (U.V-Vis), 1HNMR,13CNMR, and mass spectra. It has been established that, the polymer and its metal complexes showed good activities against four pathogenic bacteria (Escherichia coli ,Klebsiellapneumonae, Staphylococcusaureus, Staphylococcus Albus) and two fungal (Aspergillus Niger,Yeast). The polymer metal complexes showed higher activity than the free polymer. The
... Show MoreNew bidentate dithiocarbamate ligand (NaL) namely [Sodium-2-(((3-methyl -4- “(2,2,2-tri fluoro ethoxy) pyridin-2â€-yl) methyl) sulfinyl)-1H-benzoimidazole -1-carbodithioate] was prepared. This free ligand was synthesized from the reaction of a (RS)-2-([3-methyl -4-(2,2,2-tri fluoroethoxy) pyridin-2-yl] methyl sulfinyl)-1H benzoimidazole, CS2 and NaOH in methanol as solvent. From reaction of dithiocarbamate salt (NaL) with metal ions (M); Co(II), Ni(II), Cu(II), Zn(II), Cd(II) and Pd(II)â€, have obtained the DTC complexes at general molecular formula [M(L)2(H2O)2] and [Pd(L)2]. To characterize the ligand and its complexes, used different analyses methods such FTIR, UV-Vis, elemental microanalysis, atomic absor
... Show MoreThe aim of this work is the synthesis of new grafted PVA polymer with a derivative of Erythro-ascorbic acid (pentulosono-ɣ -lactone-2, 3-enedianisoate). All synthesized compounds were characterized by thin layer chromatography (TLC) and FTIR spectra and aldehyde was also characterized by (U.V-Vis), 1HNMR, 13CNMR and mass spectra. They were also evaluated for antimicrobial properties by dilute method against four pathogenic bacteria (Escherichia coli ,Klebsiella pneumonae, Staphylococcus aureus, Staphylococcus Albus) and two fungal (Aspergillus Niger, Yeast). All polymer metal complexes showed good activities against the various microbial isolates. The polymer metal complexes showed higher activity than the free polymer. The order of increa
... Show MoreThe novel heterocyclic organozinc compounds were prepared from the reaction of diazonum salt cytosine zinc chloride with thymol and vanilin as coupler components. The prepared compounds were characterized by elemental analysis and UV-Vis, FTIR and 1HMNR spectroscopic techniques. The biological activity was also studied for all prepared compounds.
Synthesis of 2-(4-Acetyl-phenyl)-4-nitro-isoindole-1, 3-dione chalcones were performed by fusion of 3-nitro phthalic anhydride with p-aminoacetophenone. Then the later was grinded with different aromatic aldehydes in the presence of sodium hydroxide to produce new chalcones derivatives A3-10 without using any solvent formation of new N- arylphthailimide chalcones were confirmed by FT-IR,1HNMR, 13CNMR spectroscopy and all final compounds were tested for their antifungal and antibacterial activity some of them showed more biological activity than the standard drugs
Information processing has an important application which is speech recognition. In this paper, a two hybrid techniques have been presented. The first one is a 3-level hybrid of Stationary Wavelet Transform (S) and Discrete Wavelet Transform (W) and the second one is a 3-level hybrid of Discrete Wavelet Transform (W) and Multi-wavelet Transforms (M). To choose the best 3-level hybrid in each technique, a comparison according to five factors has been implemented and the best results are WWS, WWW, and MWM. Speech recognition is performed on WWS, WWW, and MWM using Euclidean distance (Ecl) and Dynamic Time Warping (DTW). The match performance is (98%) using DTW in MWM, while in the WWS and WWW are (74%) and (78%) respectively, but when using (
... Show MoreArgumentation is not a contemporary, yet a deep rooted intellectual phenomenon dates back to Romans and Greeks times. The argumentative elements ,the author is trying to convey to the reader, are linguistic procedures aim at persuading and being persuaded of what is true. The present study traces, through Camus’ novel The plague, the best method to construct argumentative techniques used to express the author’s deep philosophies.
Résumé
L’argumentation n’est pas un phénomène intellectuel nouveau, ses origines reviennent aux savants grecs et romains. Elle est une act
... Show MoreThe influence of an aortic aneurysm on blood flow waveforms is well established, but how to exploit this link for diagnostic purposes still remains challenging. This work uses a combination of experimental and computational modelling to study how aneurysms of various size affect the waveforms. Experimental studies are carried out on fusiform-type aneurysm models, and a comparison of results with those from a one-dimensional fluid–structure interaction model shows close agreement. Further mathematical analysis of these results allows the definition of several indicators that characterize the impact of an aneurysm on waveforms. These indicators are then further studied in a computational model of a systemic blood flow network. This demonstr
... Show MoreMalware represents one of the dangerous threats to computer security. Dynamic analysis has difficulties in detecting unknown malware. This paper developed an integrated multi – layer detection approach to provide more accuracy in detecting malware. User interface integrated with Virus Total was designed as a first layer which represented a warning system for malware infection, Malware data base within malware samples as a second layer, Cuckoo as a third layer, Bull guard as a fourth layer and IDA pro as a fifth layer. The results showed that the use of fifth layers was better than the use of a single detector without merging. For example, the efficiency of the proposed approach is 100% compared with 18% and 63% of Virus Total and Bel
... Show More