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.
Value Engineering is an analytical study on projects or services using a specific procedure and a multidisciplinary working group, works for the identification and classification of the project functions; either for a better perfuming of these functions or to lessen the total project cost or the two together. Value Engineering main aim is on finding innovative alternatives, without effecting the basic requirements of the project, its methodology based on the functional balancing between the three elements of production "performance, quality and cost". This methodology based on the "functional analysis", had shown high possibilities in solving any problem facing the production procedure , achieve better investment for available re
... Show MoreThe sound in the cinema and television occupies a large space in the level of use and expression. In addition to the functional aspect of the elements of the sound such as the dialogue, music, effects and silence, in shaping and supporting the narrative structure of the image in the dramatic work, it has today become and in light of the technical developments of the sound, an aesthetic value in the structure and formulation of the contents and ideas presented in the work. The sound also created a variety of forms before the work-factories in the artistic functioning, which enhances the emotional and expressive dimension of the image, and the researcher, as a result of many new developments in the expression o
... Show MoreThe Sound of the letter (ق) in the Contemporary Arabic Dialects
DBN Rashid, International Journal of English Linguistics, 2019 - Cited by 2
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 MoreThe aim of this study is to utilize the behavior of a mathematical model consisting of three-species with Lotka Volterra functional response with incorporating of fear and hunting cooperation factors with both juvenile and adult predators. The existence of equilibrium points of the system was discussed the conditions with variables. The behavior of model referred by local stability in nearness of any an equilibrium point and the conditions for the method of approximating the solution has been studied locally. We define a suitable Lyapunov function that covers every element of the nonlinear system and illustrate that it works. The effect of the death factor was observed in some periods, leading to non-stability. To confirm the theore
... Show MoreECG is an important tool for the primary diagnosis of heart diseases, which shows the electrophysiology of the heart. In our method, a single maternal abdominal ECG signal is taken as an input signal and the maternal P-QRS-T complexes of original signal is averaged and repeated and taken as a reference signal. LMS and RLS adaptive filters algorithms are applied. The results showed that the fetal ECGs have been successfully detected. The accuracy of Daisy database was up to 84% of LMS and 88% of RLS while PhysioNet was up to 98% and 96% for LMS and RLS respectively.