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 ideas and information obtained by the viewer in the cinema have always been the source of the visual image, but that doesn’t negate the fact that the mental image can produce a lot of the information and ideas in the cinematic art and the most important means to achieve this mental image in the film is the eloquent cinematic sound. This research is conducted to show this important and effective contribution of the sound in the production of the mental image. Hence the importance of this research is in that it addresses an important issue which is the eloquent performance of the sound and its role in the production of the mental image inside the space of the feature film. This research concerns those working the field of cinema and
... Show MoreThis study focused on the various forms of violence that aged people encounter in their late life, the significance of taking measures that enhance not only the welfare for aged people but also the influence of early stage of life and how the old age effects on people experience throughout their live. Further, the importance of raising the awareness among communities to the extent of seriousness of old age in order to teach children the right habits and traditions, which are faded away over time. The researcher indicated that raising the avenues of collaboration among home members, social organization, and all governmental facilities will support and provide a good treatment for this group of people.
Rap songs often feature artists who utilize explicit language to convey feelings such as happiness, sorrow, and anger, reflecting audience expectations and trends within the music industry. This study intends to conduct a socio-pragmatic analysis of explicit, derogatory, and offensive language in the songs of the American artist Doja Cat, employing Hughes’ (1996) Swearing Word Theory, Jay’s (1996) Taboo Words Theory, Luhr’s (2002) classification of social factors for sociolinguistic examination, Salager’s (1997) categories of hedges for pragmatic assessment, and Austin’s (1965, 1989) theory of speech acts. The researchers collected the data using the AntConc corpus analysis tool. The data shows the singer’s frequent use
... Show MoreTo study the site of placentae and the umbilical artery blood flow of different age groupsand relate that to the newborn baby and the mother. 117 placentae samples were investigatedusing ultrasound and 30 placentae samples were studied using Doppler ultrasound during theperiod from August 2007 to August 2008 for full term placentae of mothers aged 15- > 45 yearsold. By ultrasound; there was detection of good pe rcentage of the placental site to be on theposterior wall of the uterus in case of male babies, while it was anterior in case of female babiesand it was previa and fundal in females more than in the males. The Doppler ultrasound revealedthat the mother in any age group can conceive and have a healthy placenta because the readings ina
... Show MoreMost intrusion detection systems are signature based that work similar to anti-virus but they are unable to detect the zero-day attacks. The importance of the anomaly based IDS has raised because of its ability to deal with the unknown attacks. However smart attacks are appeared to compromise the detection ability of the anomaly based IDS. By considering these weak points the proposed
system is developed to overcome them. The proposed system is a development to the well-known payload anomaly detector (PAYL). By
combining two stages with the PAYL detector, it gives good detection ability and acceptable ratio of false positive. The proposed system improve the models recognition ability in the PAYL detector, for a filtered unencrypt
Background: Sprite coding is a very effective technique for clarifying the background video object. The sprite generation is an open issue because of the foreground objects which prevent the precision of camera motion estimation and blurs the created sprite. Objective: In this paper, a quick and basic static method for sprite area detection in video data is presented. Two statistical methods are applied; the mean and standard deviation of every pixel (over all group of video frame) to determine whether the pixel is a piece of the selected static sprite range or not. A binary map array is built for demonstrating the allocated sprite (as 1) while the non-sprite (as 0) pixels valued. Likewise, holes and gaps filling strategy was utilized to re
... Show MoreThe Internet of Things (IoT) has significantly transformed modern systems through extensive connectivity but has also concurrently introduced considerable cybersecurity risks. Traditional rule-based methods are becoming increasingly insufficient in the face of evolving cyber threats. This study proposes an enhanced methodology utilizing a hybrid machine-learning framework for IoT cyber-attack detection. The framework integrates a Grey Wolf Optimizer (GWO) for optimal feature selection, a customized synthetic minority oversampling technique (SMOTE) for data balancing, and a systematic approach to hyperparameter tuning of ensemble algorithms: Random Forest (RF), XGBoost, and CatBoost. Evaluations on the RT-IoT2022 dataset demonstrat
... Show More