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.
The present search aims to develop a test for selective attention, cognitive load and thinking mistakes and measuring these concepts among Baghdad university students. To make a comparison between the selective attention, cognitive load, and the mistakes of thinking among students in term of gender. To identify the relationship among the selective attention, cognitive load and the mistakes of thinking of university students. To achieve these purposes, the searcher has developed a test for selective attention, cognitive load, and the mistakes of thinking. Then, these tools were applied to a sample of (200) university students were selected from (21) college. The researcher used t-test of one sample, t-test of two independent
... Show MoreInvestigating the strength and the relationship between the Self-organized learning strategies and self-competence among talented students was the aim of this study. To do this, the researcher employed the correlation descriptive approach, whereby a sample of (120) male and female student were selected from various Iraqi cities for the academic year 2015-2016. the researcher setup two scales based on the previous studies: one to measure the Self-organized learning strategies which consist of (47) item and the other to measure the self-competence that composed of (50) item. Both of these scales were applied on the targeted sample to collect the required data
This work implements the face recognition system based on two stages, the first stage is feature extraction stage and the second stage is the classification stage. The feature extraction stage consists of Self-Organizing Maps (SOM) in a hierarchical format in conjunction with Gabor Filters and local image sampling. Different types of SOM’s were used and a comparison between the results from these SOM’s was given.
The next stage is the classification stage, and consists of self-organizing map neural network; the goal of this stage is to find the similar image to the input image. The proposal method algorithm implemented by using C++ packages, this work is successful classifier for a face database consist of 20
... Show MoreThe main objective of this work was to adopt an environmentally friendly technology with enhanced results. The technology of magnetic water (MW) treatment system can be used in concrete mixture production instead of potable water (PW) to improve both workability and strength. Two types of concrete were adopted: normal concreter production with two grades 25 and 35 MPa and the self-compacted concrete (SCC) with 35 MPa grade. The concrete mixes containing MW instead of PW results showed that, for 25 MPa grade, an improvement in a compressive strength of 15.1, 14.8, and 10.2% was achieved for 7, 28, and 90 days, respectively. For 35 MPa grade, an improvement of 13.6, 11.5, and
The main objective of this work was to adopt an environmentally friendly technology with enhanced results. The technology of magnetic water (MW) treatment system can be used in concrete mixture production instead of potable water (PW) to improve both workability and strength. Two types of concrete were adopted: normal concreter production with two grades 25 and 35 MPa and the self-compacted concrete (SCC) with 35 MPa grade. The concrete mixes containing MW instead of PW results showed that, for 25 MPa grade, an improvement in a compressive strength of 15.1, 14.8, and 10.2% was achieved for 7, 28, and 90 days, respectively. For 35 MPa grade, an improvement of 13.6, 11.5, and
Abstract The study aimed at reviewing translation theories proposed to address problems in translation studies. To the end, translation theories and their applications were reviewed in different studies with a focus on issues such as critical discourse analysis, cultural specific items and collocation translation.
In the name of God, the Most Gracious, the Most Merciful
Praise be to God who revived Balu. And the good word brought hard hearts after removing from them what had almost killed them of ignorance, injustice, hatred, hostility, estrangement, and irritation... So God replaced for them what was best with what was best in terms of knowledge and fairness, and what was corrupt, love, and altruism. So the example of a believer and a good word is like a tree with good roots and branches. Then I pray and greet the one who watered it from the pure and inexhaustible spring of Islam, our Master Muhammad, so that the valleys flowed in their capacity, and the crops grew, then they became thicker and became even, and their good fruits in behavi
... Show MoreSelf-compacting concrete (SCC) has undergone a remarkable evolution recently based on the results from several studies that have indicated the chain of benefits SCC provides. Micro and nano materials used as mineral additives in SCC offer several high-performance properties, and this research studies the effects of micro silica (MS) (10%, used as a reference) and colloidal nano-silica (CNS) (2.5%, 5%, 7.5%, and 10%) on the fresh and hardened properties of SCC. All mixtures were estimated using flow, L-box, and V-funnel tests to examine workability and compressive strength, modulus of elasticity and tensile strength as hardened properties. The use of CNS increased the overall compressi
Research aims to know the impact beyond the defined in the collection. The research community is the second school students at Baghdad University and a research sample (63) students, the number of experimental group (27) students and a control group (30) students. The researcher was rewarded in variable lifetime for students and educational attainment and educational level of the parents and the educational level of mothers. The researcher has developed a test took the number of paragraphs (20). A test was true after it has been submitted to the Group of arbitrators. The test was consistent with test method used and the reliability coefficient (0, 88). Either the statistical methods used by the researcher are: Pearson correla
... Show More