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 determination of manganese (II) using flow injection analysis with chemiluminescence detection was investigated. Mn2+ in sample solutions injected into a carrier stream of sodium bismuthate (NaBiO3) were oxidised to form MnO4- ions which were capable of producing luminescence after reaction with luminol/KOH in a flow cell. The linear range of the system is from 20 to 80 mg/L with a detection limit 8 mg/L. The proposed system is suitable for determination of Mn2+ in steel alloys after dissolution, filtration and dilution at a rate of approximately 60 samples per hour with a relative standard deviation (RSD)1.2%. Statistical comparison between the proposed system and standard spectrophotometric method revealed that there is no signific
... Show MoreThe increase in the Iraqi population put pressure on urban cities as there were no new cities built since the 1980s due to the wars and the economic blockade imposed in 1991 and the deteriorating security situation after 2003, where the population in 2018 reached about forty million people. Iraq also suffered during the past decades from problems and challenges in many respects that affected the local environment, and the constructed buildings had a role in increasing these impacts, so the Ministry of Housing worked to issue the Iraqi Green Architecture Code in 2019 to reduce damage to the environment and use resources more efficiently. And because the constructed buildings were not constructed according to green standards, including Bas
... Show MoreSpeech is the ability of communication or expression of thoughts among people in spoken words. Human communication via speech is essential since any impairment in this process may have serious social and occupational consequences. Malocclusion is a possible cause of speech impairment in addition to many other etiological factors like hearing loss, neurological disorders, physical disorders, and drug abuse. This article throws light upon the association between speech disorders and malocclusion.
Objectives: to evaluate patient knowledge with hemodialysis and to determine the effectiveness of Self-regulation Fluid Program on Patients with hemodialysis self-efficacy for fluid adherence in Al-Diwaniyah Teaching Hospital.
Methodology: A quasi-experimental design (two group design: pre-test and post-test) was used. This study was conducted in Al-Diwaniya Teaching Hospital for the period from (15th of October 2018 to 20th of May 2019) on a non-probability (purposive) sample consisting of (60 patients) treatment in hemodialysis units. A questionnaire was built as a data collection tool and consisted of four parts:
First part: Demographic characteristics of the pati
... Show More"Watermarking" is one method in which digital information is buried in a carrier signal;
the hidden information should be related to the carrier signal. There are many different types of
digital watermarking, including traditional watermarking that uses visible media (such as snaps,
images, or video), and a signal may be carrying many watermarks. Any signal that can tolerate
noise, such as audio, video, or picture data, can have a digital watermark implanted in it. A digital
watermark must be able to withstand changes that can be made to the carrier signal in order to
protect copyright information in media files. The goal of digital watermarking is to ensure the
integrity of data, whereas stegano
Alms (or Zakat) is one of the Pillar of Islam and it was atask imposed on
Muslims. Becomes of the importance of this task and its influence on the human
Psychic in particular and on the Society in general this study aims at Studying the
words that it refers to in the Holy Quran, At the beginning the researcher has
introduced the words it refers to, and the significance of each in the Holy Quran and
the Speciality of each one of such words, then the Structures they donet have been
also introduced, whether such structures are descriptive, adverbial or verbal.This was
introduced in addition to explaining the influence of changing the Shape of such
words in emphasizing the meaning and the influence of Portraiting styl
How I was eager to research the ruling on three of the most dangerous types to Islam and Muslims (the heretic, the sorcerer, the innovator, and related terms).
Because it is the most dangerous deadly disease that destroys the hearts of Muslims, and may even expel a Muslim from the circle of Islam, and how many Muslims have done or committed such a thing without knowing it. Indeed, how many Muslims have left Islam and whose wife has abandoned him without realizing it, and among them are those who have committed it without knowing it. As well as related words associated with heresy.( )
Because people debated such matters between extremists and lenient ones, most of whom were extremists, and they did not reach a conclusion. So I decid
Many approaches of different complexity already exist to edge detection in
color images. Nevertheless, the question remains of how different are the results
when employing computational costly techniques instead of simple ones. This
paper presents a comparative study on two approaches to color edge detection to
reduce noise in image. The approaches are based on the Sobel operator and the
Laplace operator. Furthermore, an efficient algorithm for implementing the two
operators is presented. The operators have been applied to real images. The results
are presented in this paper. It is shown that the quality of the results increases by
using second derivative operator (Laplace operator). And noise reduced in a good