Preferred Language
Articles
/
8hYDe4cBVTCNdQwClFPP
Speech Emotion Recognition Using Minimum Extracted Features
...Show More Authors

Recognizing speech emotions is an important subject in pattern recognition. This work is about studying the effect of extracting the minimum possible number of features on the speech emotion recognition (SER) system. In this paper, three experiments performed to reach the best way that gives good accuracy. The first one extracting only three features: zero crossing rate (ZCR), mean, and standard deviation (SD) from emotional speech samples, the second one extracting only the first 12 Mel frequency cepstral coefficient (MFCC) features, and the last experiment applying feature fusion between the mentioned features. In all experiments, the features are classified using five types of classification techniques, which are the Random Forest (RF), k-Nearest Neighbor (k-NN), Sequential Minimal Optimization (SMO), Naïve Bayes (NB), and Decision Tree (DT). The performance of the system validated over Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of the experiments showed given good accuracy compared with the previous studies using a fusion of a few numbers of features with the RF classifier.

Scopus Clarivate Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Thu Dec 01 2022
Journal Name
Journal Of Engineering
The Effectiveness of a Simulation Model of Thermal Insulation in Building Materials Using Cellulose Extracted from Agricultural Waste in Baghdad
...Show More Authors

This study found that one of the constructive, necessary, beneficial, most effective, and cost-effective ways to meet the great challenge of rising energy prices is to develop and improve energy quality and efficiency. The process of improving the quality of energy and its means has been carried out in many buildings and around the world. It was found that the thermal insulation process in buildings and educational facilities has become the primary tool for improving energy efficiency, enabling us to improve and develop the internal thermal environment quality processes recommended for users (student - teacher). An excellent and essential empirical study has been conducted to calculate the fundamental values ​​of the

... Show More
View Publication Preview PDF
Crossref (3)
Crossref
Publication Date
Sun Jun 20 2021
Journal Name
Baghdad Science Journal
Arabic Speech Classification Method Based on Padding and Deep Learning Neural Network
...Show More Authors

Deep 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 More
View Publication Preview PDF
Scopus (25)
Crossref (8)
Scopus Clarivate Crossref
Publication Date
Sun Jan 03 2021
Journal Name
Association Of Arab Universities Journal Of Engineering Sciences
Correlation of Minimum Miscibility Pressure for Hydrocarbon Gas Injection In Southern Iraqi Oil Fields
...Show More Authors

One of the most important enhanced oil recoveries methods is miscible displacement. During this method preferably access to the conditions of miscibility to improve the extraction process and the most important factor in these conditions is miscibility pressure. This study focused on establishing a suitable correlation to calculate the minimum miscibility pressure (MMP) required for injecting hydrocarbon gases into southern Iraq oil reservoir.  MMPs were estimated for thirty oil samples from southern Iraqi oil fields by using modified Peng and Robinson equation of state. The obtained PVT reports properties were used for tunning the equation of state parameters by making a match between the equation of state results with experimenta

... Show More
View Publication
Crossref
Publication Date
Sun Feb 25 2024
Journal Name
Baghdad Science Journal
An Adaptive Harmony Search Part-of-Speech tagger for Square Hmong Corpus
...Show More Authors

Data-driven models perform poorly on part-of-speech tagging problems with the square Hmong language, a low-resource corpus. This paper designs a weight evaluation function to reduce the influence of unknown words. It proposes an improved harmony search algorithm utilizing the roulette and local evaluation strategies for handling the square Hmong part-of-speech tagging problem. The experiment shows that the average accuracy of the proposed model is 6%, 8% more than HMM and BiLSTM-CRF models, respectively. Meanwhile, the average F1 of the proposed model is also 6%, 3% more than HMM and BiLSTM-CRF models, respectively.

View Publication Preview PDF
Scopus (4)
Crossref (2)
Scopus Crossref
Publication Date
Tue Oct 01 2019
Journal Name
2019 Ieee 9th International Conference On System Engineering And Technology (icset)
A Digital Signature System Based on Real Time Face Recognition
...Show More Authors

This study proposed a biometric-based digital signature scheme proposed for facial recognition. The scheme is designed and built to verify the person’s identity during a registration process and retrieve their public and private keys stored in the database. The RSA algorithm has been used as asymmetric encryption method to encrypt hashes generated for digital documents. It uses the hash function (SHA-256) to generate digital signatures. In this study, local binary patterns histograms (LBPH) were used for facial recognition. The facial recognition method was evaluated on ORL faces retrieved from the database of Cambridge University. From the analysis, the LBPH algorithm achieved 97.5% accuracy; the real-time testing was done on thirty subj

... Show More
View Publication Preview PDF
Scopus (10)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Sun Jan 02 2022
Journal Name
Journal Of The College Of Languages (jcl)
A Pragmatic Analysis of Illocutionary Act in a Selected Presidential Speech on COVID-19
...Show More Authors

     This paper aims at studying the illocutionary speech acts: direct and indirect to show the most dominant ones in a presidential speech delivered by the USA president. The speech is about the most critical health issue in the world, COVID-19 outbreak.  A descriptive qualitative study was conducted by observing the first speech delivered by president Trump concerning coronavirus outbreak and surveying the illocutionary acts: directive, declarative, commissive, expressive, and representative. Searle's (1985) classification of illocutionary speech acts is adopted in the analysis.

     What are the main types of the illocutionary speech acts performed by Trump in his speech?; Why does

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Fri Aug 30 2019
Journal Name
Journal Of The College Of Education For Women
Men and Women’s Education and Illiteracy in Adrar Speech Community
...Show More Authors

In Algeria, education is compulsory for males and females. This foundational decision was taken right after the independence of the country in 1962. Soon after, in 1963, the central government decided the Arabisation of the whole educational levels starting from primary school till university. At the same period, illiteracy-eradication programmes were launched by the Ministry of Education to get rid of this post-colonial scourge. In the administrative department (or Wilaya) of Adrar, former Tuat, young males and females attend Quranic schools (Zawaya) well before any formal education, that is as early as 4-5 years of age. The adult people who are not enrolled in formal classes could sit for non-formal ones. However, actual measurements a

... Show More
View Publication Preview PDF
Publication Date
Wed Jun 01 2011
Journal Name
Journal Of The College Of Languages (jcl)
Areas in phonetics and phonology Differences Between Speech and Writing
...Show More Authors

In any language there is some amount of difference between written language (planned) and spoken language (spontaneous). Since planned speech could be considered a form of written language, it could be inferred that there are also differences between planned speech and spontaneous speech. Some of these differences are very clear in terms of syntax, lexis, phonology and discourse.  These differences are highlighted in order to make a clear distinction between spontaneous and planned speech.

             This paper is an attempt to show the differences between the two forms of a language (written & spoken English) as far as number of linguistic features are tackle

... Show More
View Publication Preview PDF
Publication Date
Wed Nov 06 2024
Journal Name
2024 17th International Conference On Development In Esystem Engineering (dese)
Speech Enhancement: A Review of Various Approaches, Trends, and challenges
...Show More Authors

View Publication
Scopus (3)
Crossref (3)
Scopus Crossref
Publication Date
Sun Jan 01 2017
Journal Name
Ieee Access
Low-Distortion MMSE Speech Enhancement Estimator Based on Laplacian Prior
...Show More Authors

View Publication
Scopus (44)
Crossref (40)
Scopus Clarivate Crossref