Beyond the immediate content of speech, the voice can provide rich information about a speaker's demographics, including age and gender. Estimating a speaker's age and gender offers a wide range of applications, spanning from voice forensic analysis to personalized advertising, healthcare monitoring, and human-computer interaction. However, pinpointing precise age remains intricate due to age ambiguity. Specifically, utterances from individuals at adjacent ages are frequently indistinguishable. Addressing this, we propose a novel, end-to-end approach that deploys Mozilla's Common Voice dataset to transform raw audio into high-quality feature representations using Wav2Vec2.0 embeddings. These are then channeled into our self-attention-based convolutional neural network (CNN) model. To address age ambiguity, we evaluate the effects of different loss functions such as focal loss and Kullback-Leibler (KL) divergence loss. Additionally, we evaluate the accuracy of the estimation at different durations of speech. Experimental results from the Common Voice dataset underscore the efficacy of our approach, showcasing an accuracy of 87% for male speakers, 91% for female speakers and 89% overall accuracy, and an accuracy of 99.1% for gender prediction.
In this work, animal bones with different shapes and sizes were used to study the characteristics of the ground penetrating Radar system wares reflected by these bones. These bones were buried underground in different depths and surrounding media. The resulting data showed that the detection of buried bones with the GPR technology is highly dependent upon the surrounding media that the bones were buried in. Humidity is the main source of signal loss in such application because humidity results in low signal-to-noise ratio which leads to inability to distinguish between the signal reflected by bones from that reflected by the dopes in the media such as rock .
In this publication, several six coordinate bridged-polymeric metal complexes are reported. The reaction of 4,4`-dipyridine with ethyl chloroacetate in mole ratio of 1:2 gave the multidentate carboxylate ligand bis(N-carboxylatomethyl)-4,4`-dipyridinium). The reaction of the ligand with metal chloride and sodium azide resulted in the formation of the required polymeric complexes. Upon complex formation, the carboxylato ligand behaves as a neutral multidantate species. The mode of bonding and overall geometry of the complexes were determined through physicochemical and spectroscopic methods. These studies revealed octahedral geometry about metal centres and complexes of the general formula [Cr2(L)(N3)4]Cl2.H2O, Na2[Ag2(L)(N3)4].H2O and [M2(L
... Show MorePregnancy pose an additional burden on the body of the mother so as to meet their needs and the needs of the fetus and the body's need to iron increases excessively during pregnancy and iron is an essential element for the formation of hemoglobin blood Either hemoglobin is the key ingredient for red blood cells which carries oxygen to parts of the body, alas, most of the pregnant women begin their pregnancy inadequate stocks of iron in their bodies, which does not cover their need and requirement of the fetus, especially in the second and third trimesters of pregnancy When you reach the mother to the period in which they did not have the adequate amount of iron to produce hemoglobin become the mother was anemic So emerged the problem of
... Show MoreThe research aimed at designing teaching sessions using the self-scheduling strategy with a competitive style in learning handball as well as identifying differences between pre and post tests in both groups in learning short and long passes in handball. The researchers used the experimental method on 2nd-grade secondary school students. The researchers concluded using the self-scheduling strategy due to its positive effect on learning short and long handball passes in handball. Finally, the researchers recommended applying strategies and styles in teaching different school levels as well as making similar studies using teaching strategies and styles for learning handball skills in students.
Modify Multi-Connect Architecture (MMCA) associative memory
Recently new trends of mosques’ architecture have appeared. These trends differed from those of traditional ones in charictaristics which include two and three dimentional level. The traditional mosques' architecture are affected by several factors, so the research problem is (lack of knoweledge about factors forming traditional mosques' architecture and its effect on contemporary trends of mosques' architecture).The hypotheses of research is (the functional, aesthetic and symbolic religious factors of style are the most active factors in forming contemporary trends of mosques' architecture than religious and environmental factor).The research conclusion is that the symbolic functional factor is most effective factor i
... Show MoreMechanism of Arbitration in the Stock Exchange Disputes
A total of 90 stool sample was collected from patients with gastroenteritis to
detect adenovirus antigen among diarrhea cases. They were tested by general stool
examination (GSE), rapid immunochromatographic test and Enzyme Linked
Immunosorbent Assay (ELISA). GSE showed that adenovirus gastroenteritis
infection resulted in non-bloody diarrhea, the existence of RBCs in 7% and Pus in
37% of the samples, Entamoeba histolytica trophozoite and cyst were seen in 3%
and 2% of the samples respectively. The rapid test showed that 21% of samples
were positive for rotavirus, 8% for adenovirus and 3% for astrovirus. Meanwhile,
the ELISA test showed that adenovirus was positive in 9% of the samples. These
findings establish
Human skin detection, which usually performed before image processing, is the method of discovering skin-colored pixels and regions that may be of human faces or limbs in videos or photos. Many computer vision approaches have been developed for skin detection. A skin detector usually transforms a given pixel into a suitable color space and then uses a skin classifier to mark the pixel as a skin or a non-skin pixel. A skin classifier explains the decision boundary of the class of a skin color in the color space based on skin-colored pixels. The purpose of this research is to build a skin detection system that will distinguish between skin and non-skin pixels in colored still pictures. This performed by introducing a metric that measu
... Show More