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.
Experienced economic environmentRadical changes at the end of the last century and the beginning of the present century, resulting in new concepts and expectations in all aspects of economic, political, social and even behavioral.Each of these concepts is the result of rapid developments in the intangible space. Competition is no longer limited to the mere possession of tangible material resources, but because of its link to knowledge and technology content and to the comprehensive quality standards and efficient and effective policies of States. With the increasing pace of growth and interdependence among the global economies, this resulted in the birth of a new economic system led by technological development and financial liberalizati
... Show MoreResearchers employ behavior based malware detection models that depend on API tracking and analyzing features to identify suspected PE applications. Those malware behavior models become more efficient than the signature based malware detection systems for detecting unknown malwares. This is because a simple polymorphic or metamorphic malware can defeat signature based detection systems easily. The growing number of computer malwares and the detection of malware have been the concern for security researchers for a large period of time. The use of logic formulae to model the malware behaviors is one of the most encouraging recent developments in malware research, which provides alternatives to classic virus detection methods. To address the l
... Show MoreTested effective Alttafaria some materials used for different purposes, system a bacterial mutagenesis component of three bacterial isolates belonging to different races and materials tested included drug Briaktin
The concept of self is considered one of the important dimensions in the human personality, because feeling of self is an important characteristic in this phase from the psychological point of view.
The first source which forms the concept of self is the physical image, where the built and appearance of the body is considered among the vital matters which determine the person's image of himself/herself.
The current research aims to:
1) Identify the level of physical self concept at the kindergarten children.
2) Identify the level of psychological self concept at the kindergarten children.
3) Iden
... Show MoreThis research includes the use of CdTe in the design of a solar cell. The SCAPS-1D computer program was used to simulate thin cell capacity of CdTe/CdS by numerical analysis with the addition of a buffer layer (Zn2SnO4) to enhance cell efficiency. The thickness of the window layer (n-CdS) was reduced to 25nm with the inclusion of an insulating layer of 50 nm thickness to prevent leakage towards the forward bias with respect to the lower charge carriers. As for the absorber layer thickness (p-CdTe), it varied between 0.5µm and 6µm. The preferable thickness in the absorbent layer was 1.5µm. Different operating temperatures (298K-388K) were used, while the highest conversion efficiency (η=18.43%) was obtain
... Show MoreBackground: Diabetes mellitus a major factor that has adverse effects on the vascular system and the heart. It causes an increase in cardiac muscle thickness, resulting in decreased compliance and increased peripheral arterial stiffness. This study aims to assess the left ventricular mass (LVM) and left ventricular hemodynamic changes in diabetic patients measured by Doppler echocardiography. Patients and Methods: The study included 50 diabetic patients ranging in age between 25 and 80 years, (mean age: 54.1 ± 15.10, 19 males, 31 females) and 50 healthy subjects, aged 25 to 80 years (mean age: 48.52 ± 14.45, 11 males, 39 females). Doppler echocardiography was used to assess left ventricular function. The measurements included
... Show MorePulsar stars are rotating Neutron stars can be divided into two types Millisecond and Normal Pulsars. In this work the magnetic field are concentrated depends on the period (P), and Period derivative (P) for a sample Normal, Millisecond and Radio stars which adopted. In addition, the values of spin down luminosity and Heating rate are determined by depending on (Ostriker and Gunn) model. The results showed that older Millisecond define as having greater ages specified how long pulsars lives at that ages very long period pulsars to be observable have particularly large surface magnetic field. The results indicate that spin down of luminosity for Millisecond and Normal star must due to the main energy loss rotation axis to align with magne
... Show MoreObjective(s): To evaluate teachers’ performance of counseling for pupils with Attention Deficit and Hyperactivity Disorder, to identify the relationship between Teachers’ Performance of Counselling for Pupils with Attention Deficit and Hyperactivity Disorder and their demographic.
Methodology: A quasi-experimental (pre-posttest) design was carried out to evaluate teachers’ performance of counseling for pupils with Attention Deficit and Hyperactivity Disorder, at Al-Firdous mixed primary School and to find out the association between teachers' performance about Attention Deficit and Hyperactivity Disorder and their socio-demographic characteristic. The study was started from 18th September 2
... Show MoreTarget tracking is a significant application of wireless sensor networks (WSNs) in which deployment of self-organizing and energy efficient algorithms is required. The tracking accuracy increases as more sensor nodes are activated around the target but more energy is consumed. Thus, in this study, we focus on limiting the number of sensors by forming an ad-hoc network that operates autonomously. This will reduce the energy consumption and prolong the sensor network lifetime. In this paper, we propose a fully distributed algorithm, an Endocrine inspired Sensor Activation Mechanism for multi target-tracking (ESAM) which reflecting the properties of real life sensor activation system based on the information circulating principle in the endocr
... Show More