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, the effect of different particle size on the nonlinear optical properties of silver nanoparticles in de-ionized water was studied. The experimental observation of the far field diffraction patterns by CCD camera in two and three dimensions. The maximum change of nonlinear refractive index and the relative phase shift were calculated. The self-defocusing technique was used with a continuous-wave radiation from DPSS Blue laser .The wavelength is 473 nm with an output power of 270 mW. All the Ag colloids samples containing the sizes 15, 30, 50, and 70 nm of silver nanoparticles used in the study were chemically prepared. It was found that the nonlinear refractive index is a particle size dependent and of the order of 10-7 cm2/
... Show MorePolitical speeches are represented in different shapes as political forum, events or as inaugural speech. This research critically analyzes the inaugural Speech of the President Donald Trump which was delivered on 20th ,January, 2017 from the site<www.cnn.com> retrieved on 10th ,May,2017. The objectives of the study are: First: classifying and discussing well known micro structures (linguistic feature) of the speech, and second: classifying the macro structures i.e. the delivered political inaugural speech in which he includes social structures. To reach to the objectives of the study, the researcher will adopt Norman Fairclough’s three dimensional Analytical Model(
... Show MorePolitical speeches are represented in different shapes as political forum, events or as inaugural speech. This research critically analyzes the inaugural Speech of the President Donald Trump which was delivered on 20th ,January, 2017 from the site<www.cnn.com> retrieved on 10th ,May,2017. The objectives of the study are: First: classifying and discussing well known micro structures (linguistic feature) of the speech, and second: classifying the macro structures i.e. the delivered political inaugural speech in which he includes social structures. To reach to the objectives of the study, the researcher will adopt Norman Fairclough’s three dimensional Analytical Model(1989). Tracing the model, the speech was subm
... Show MoreSpeech is the essential way to interact between humans or between human and machine. However, it is always contaminated with different types of environment noise. Therefore, speech enhancement algorithms (SEA) have appeared as a significant approach in speech processing filed to suppress background noise and return back the original speech signal. In this paper, a new efficient two-stage SEA with low distortion is proposed based on minimum mean square error sense. The estimation of clean signal is performed by taking the advantages of Laplacian speech and noise modeling based on orthogonal transform (Discrete Krawtchouk-Tchebichef transform) coefficients distribution. The Discrete Kra
Considering the science of speech in the light of its purposes is an accurate scientific study that looks at it from its reality in which it originated, and its topic that it dealt with and its goals that it sought, and it follows its main course in the directions of approving the belief and inferring it, and repelling the objections to it, and this study comes to show the realism of the science of speech in its emergence Its subject and method, since its launch was from the reality of the Islamic nation and based on its intellectual needs, so its presence was necessary in the life of the Islamic nation because of its role in facing the challenges faced by the Islamic faith, and the dangers it was exposed to as a result of the intellectu
... Show MoreDeep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to
... Show MoreThis study has been developed axes of the search, including: Search (deliberative) language and idiomatically, and Description Language (b social phenomenon), and the definition of the theory of (acts of speech), and discussed the problem of the conflict between tradition and innovation, as defined objectively have a target aimed at reviving the deliberative thought when Arab scholars , and the balance between the actual done Arab and Western rhetoric, but Meet in intellectual necessity, a sober reading that preserve the Arab language prestige, and its position in the light of the growing tongue Sciences, as long as we have inherited minds unique, and heritage huge able to consolidate the Arab theory lingual in linguistics.
Hemogloin (Hb) and serum ferritin levels are used to assess anemia in pregnancy. Some studies referred to the influence of maternal age, body mass index (BMI) and parity on Hb and serum ferritin levels. The study aimed to examine the possible association of maternal Hb and serum ferritin with maternal age, parity, and BMI in a sample of pregnant women in Baghdad.
Ninety healthy pregnant women, grouped in three equal groups according to the pregnancy trimester, and thirty apparently healthy non-pregnant women from Baghdad were enrolled in this observational study. Blood and serum samples were obtained for the estimation of Hb and serum ferritin levels.
The pooled data of participants showed a n
... Show MoreMaking the data secure is more and more concerned in the communication era. This research is an attempt to make a more secured information message by using both encryption and steganography. The encryption phase is done with dynamic DNA complementary rules while DNA addition rules are done with secret key where both are based on the canny edge detection point of the cover image. The hiding phase is done after dividing the cover image into 8 blocks, the blocks that are used for hiding selected in reverse order exception the edge points. The experiments result shows that the method is reliable with high value in PSNR