ABED Ahcene

Automatic keyword Detection and Crime Prediction from Phone Call Analysis (SEERIUM) , Zellagui Yacine

Automatic keyword Detection and Crime Prediction from Phone Call Analysis (SEERIUM)

In this paper, we provide a new version of two-sensor source separation recursive structure in sub-band form for acoustic noise reduction in hands-free telephony application, which is controlled by a new independent variable step-size normalized decorrelation method. This algorithm is used to reduce acoustic noise while improving voice quality, particularly in very acoustic noisy environments. This approach is known as the Independent Adaptive-step-size Subband Recursive Decorrelation (IA-SRD) algorithm. We conducted several simulations in a variety of acoustic noisy situations to evaluate the efficacy of the proposed version using numerous subjective and objective criteria, including time evolution of enhanced speech signals, mean square error (MSE), and segmental signal-to-noise ratio (Seg-SNR). Based on all obtained comparative results, the proposed algorithm demonstrates efficient performances when compared to basic decorrelation and sub-band decorrelation algorithms regarding of noise reduction level, convergence rate and voice quality enhancement.

Citation

Abed Ahcene , , (2025-12-12), New independent adaptive-step-size sub-band recursive decorrelation approach for noise reduction and speech enhancement, International Journal of Speech Technology, Vol:29, Issue:1, pages:XXX-XXX, Springer Nature

This study focuses on the formulation of a robust nonlinear control strategy for the Doubly-Fed Induction Machine (DFIM), with the objective of improving its performance in variable-speed drive applications. This approach combines vector control with intelligent techniques, specifically Type-1 Fuzzy Logic, utilizing 12 linguistic variables, to address the shortcomings of traditional control methods. Conventional vector control frequently experiences challenges, including oscillations, sluggish response, and diminished efficiency across different load and speed scenarios. The introduction of fuzzy logic enhances the adaptability and robustness of the control system, thereby significantly improving its dynamic response and steady-state performance. We conducted an extensive simulation to evaluate the effectiveness of the proposed fuzzy-vector control strategy. The results demonstrate that the integration of fuzzy logic reduces oscillations and improves load-driving capability across a range of speeds. Additionally, it enhances response time, resolves derivation issues, and minimizes flux ripples and fluctuations in electromagnetic torque. Overall, the findings suggest that fuzzy logic surpasses traditional vector control, offering a more reliable and efficient solution for modern DFIM applications.

Citation

RIYADH Rouabhi , ABDELGHAFOUR Herizi , Abed Ahcene , , (2025-12-12), A Robust Fuzzy-PI Controller for Doubly Fed Induction Machines Using 12 Linguistic Variables, Journal of Engineering and Technology for Industrial Applications, Vol:11, Issue:56, pages:220-226, ITEGAM-JETIA Journal

This research enhances the dynamic performance and robustness of Permanent Magnet Synchronous Motors (PMSMs) by developing an adaptive fuzzy-PI hybrid control strategy. While PMSMs offer superior power density and durability over DC motors, their control is challenged by parameter variations and external disturbances. This study compares traditional Proportional-Integral (PI) control, standard fuzzy logic, and a proposed adaptive fuzzy controller. Numerical simulations in MATLAB/Simulink demonstrate that the adaptive fuzzy controller significantly improves transient response by minimizing speed overshoot and effectively rejecting disturbances. Upon application of a 6 N.m load torque, the controller rapidly restores the motor speed to its reference value with minimal deviation. Furthermore, it substantially reduces current and torque peaks during transients, thereby decreasing stress on the motor and drive system. The results confirm that the adaptive fuzzy-PI control optimizes dynamic responsiveness, ensures stability, and enhances overall control efficiency for PMSMs in demanding industrial environments.

Citation

ABDELGHAFOUR Herizi , Abed Ahcene , ,(2025-12-10), Adaptive Fuzzy-PI Hybrid Control of Permanent Magnet Synchronous Motors,2nd International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE),University of Msila

This study presents the design, simulation, and characterization of a high-efficiency, compact power divider based on Substrate Integrated Waveguide (SIW) architecture for C-band (4-8 GHz) operations. SIW technology offers a promising solution for microwave and millimetre-wave circuits due to its advantages of low loss, high power handling capability, and compatibility with standard planar fabrication processes. The design methodology will involve electromagnetic simulations using HFSS to optimize key parameters, such as insertion loss, return loss, and isolation. The prototype is implemented on an 0.8 mm thick FR4 substrate(Epoxy laminate material) with (ϵr =4.4). This work aims to contribute to the advancement of integrated microwave circuits by demonstrating a practical and efficient SIW-based power divider design for C-band applications, including modern radar systems, satellite links, and wireless networking infrastructure.

Citation

Abed Ahcene , ,(2025-12-10), Design of a C-Band compact SIW Power Divider,2nd International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE),University of Msila

DC microgrids are being increasingly adopted for their effectiveness in integrating renewable energy sources and energy storage technologies. However, their dependence on communication and control systems makes them susceptible to cyber-attacks. This research introduces a detailed architecture for detecting cyber-attacks in DC microgrids utilizing Long Short-Term Memory (LSTM) networks, augmented by an Unknown Input Observer (UIO) system. The study explores the past applications of LSTM in DC microgrids, outlines the components and signals of interconnected DC microgrids, and introduces a mathematical model for input–output interactions. The proposed system is evaluated on four interrelated DC microgrids, demonstrating high accuracy in identifying attacks. The results are analyzed, leading to conclusions regarding the approach’s effectiveness.

Citation

Abed Ahcene , , (2025-10-17), Cyber Attack Detection on DC Microgrids with the Use of an Unknown Input Observer (UIO) and Long Short-Term Memory (LSTM), Arabian Journal for Science and Engineering, Vol:51, Issue:, pages:XXX-XXX, Springer Nature

The project focuses on industrial maintenance, from the perspective of the extent to which preventive maintenance is applied within PLASTUB-Ghardaïa. This question addresses the aforementioned concerns: controlling industrial risks, ensuring the safety of property and people, ensuring production availability, and optimizing the maintenance policy. More specifically, the project addresses the following questions: How can industrial risks be avoided through better planning of preventive maintenance tasks to ensure industrial safety in production systems? Does PLASTUB apply these preventive maintenance schedules? This work is organized into two main parts, which can be summarized as follows: Part 1 is devoted to reviewing the maintenance function and attempts to introduce the fundamental concepts of this field. It provides basic definitions of concepts specific to the field of preventive maintenance. The second part presents a practical study of preventive maintenance and its organization within the PLASTUB-Ghardaïa company.

Citation

ABDELGHAFOUR Herizi , Abed Ahcene , ,(2025-05-15), Implementation of Preventive Maintenance and its Organization Within the PLATUS-Ghardaïa Company,ICAENS 2025,Turkey

Recently, Substrate Integrated Waveguide (SIW) structures have gained significant interest. This structure is a very promising candidate for many circuits, including millimeterwave applications. It is a simple solution that combines planar and volumetric technologies into a single structure to benefit from their respective advantages. In this paper, we propose an SIW structure with two slots in the Ku band at 16 GHz. The main objective of this document is to study the effect of the width and length parameters of the slots on the reflection coefficient S11.The optimization process is performed using Ansoft HFSS software, where the design parameters of the waveguides Siw are adjusted to achieve the desired frequency response characteristics.

Citation

Abed Ahcene , ,(2025-05-08), The Slot Parameters Effect in a SIW Waveguide for Ku-band Applications,International Conference on Electronics, Energy and Measurement, IC2EM’2025,Algiers

This paper presents research on implementing predictive control for three-phase inverters with output LC filters for uninterruptible power supply (UPS) applications. The goal is to achieve high-quality voltage regulation and fast dynamic response under various load conditions, including nonlinear loads. This model predicts the future behaviour of controlled variables, such as the inverter's output voltage and current. Constraints, such as voltage and current limits, are considered in control design to ensure safe operation. The optimization problem in predictive control is solved at each control time interval, aiming to minimize the cost function while satisfying the system constraints. The cost function can be customized based on specific goals, such as reducing total harmonic distortion (THD) in the output voltage or optimizing performance. The resulting control actions will provide optimal drive for the inverter to regulate the output voltage. With MATLAB/Simulink tools, we assess the efficacy of the suggested control strategy by presenting simulation results across various linear and nonlinear loads. The results demonstrate that the feedforward control scheme produces low THD and satisfactory dynamic response.

Citation

Abed Ahcene , ,(2025-05-08), Three-Phase Inverter Control with LC Filter Output for Uninterruptible Power Supply,International Conference on Electronics, Energy and Measurement,Algiers

Substrate-integrated waveguide (SIW) technology has become a vital component in modern telecommunications due to its unique advantages in performance and integration. It meets the increasing demands of the telecommunications sector by focusing on the essential role of SIW filters. These filters take advantage of the inherent properties of SIW structures to provide high selectivity, low insertion loss, and compact size. As a result, they are essential for various applications, including wireless communication systems, satellite communication, and radar technology. In this study, three band-pass substrate integrated waveguide (SIW) filters were designed, analyzed, and simulated with a thickness of 0.63 mm. These filters are intended to operate in the following frequency bands: S-band (2-4 GHz), C-band (4-8 GHz), and X-band (8-12 GHz). The simulations were conducted using the HFSS simulator with Rogers RT/Droid 6010/6010LM materials. The simulation results demonstrate a strong response and indicate a bandwidth around three frequencies: 2.72 GHz, 6.3 GHz, and 10.31 GHz, corresponding to the S, C, and X bands, respectively. The insertion loss is measured at [-1 dB].

Citation

Abed Ahcene , ,(2025-05-06), Compact SIW Band-pass Filters in [2-12 GHz] for Telecommunication Systems,NC-REAEE’25,University of Msila

Detecting replay attacks in DC microgrids using watermarking involves the integration of secure communication protocols and innovative data authentication techniques between the DGUs. Watermarking, a robust method commonly used in digital media, is adapted to embed unique signatures into data packets exchanged within the microgrid network and between the DGUs. These signatures serve as digital fingerprints, allowing for the verification of data integrity and origin. The attacker intercepts data between the network units through the communication lines between them, records them, and then transmits them back into the network, affecting the network's performance and stability and affecting the Consensus between the DGUs. This research highlights the detection of the attack on the DC microgrids by injecting the watermark into the lines of communication between the interconnected networks and identifying the DGU that was attacked by the simulation results.

Citation

Abed Ahcene , ,(2025-05-06), Distributed Watermarking for Detect Replay Attacks for 4 DGUs in DC Microgrids with Variants Loads,NC-REAEE’25,University of Msila

The paper explores optimizing photovoltaic panel orientation and inclination to enhance their performance in photovoltaic systems. Photovoltaic solar energy is a primary energy source for large-scale clean electricity production, but meteorological, climatic, and electrical constraints influence its efficiency. The research is divided into three sections: defining photovoltaic generators, modelling and simulating a photovoltaic generator using Matlab Simulink and analyzing generator simulation results based on different climatic parameters. The study aims to understand better the orientation and inclination of photovoltaic panels to ensure better performance in photovoltaic systems. The study uses SIMULINK, a platform for multi-domain simulation and modelling of dynamic systems, to define a model applicable to photovoltaic cells. The study reveals that temperature, illumination, series resistance, shunt resistance, and panel inclination all affect the performance of solar power generation systems.

Citation

Abed Ahcene , ,(2025-05-06), Photovoltaic generator characterization and simulation,NC-REAEE’25,University of Msila

Addressing the challenge of sparse acoustic channel is important in communication systems such as tele- and video-conferencing systems. Sparse impulse response plays an efficient role in acoustic identification systems, particularly in long acoustic rooms. This article presents an enhanced version of the Improved Proportionate Normalized Least-Mean-Squares (IP-NLMS) algorithm. It adapts only the active coefficients, thereby reducing the computational complexity of IP-NLMS algorithm. The selected active coefficients of the IP-NLMS algorithm (SAC-IP-NLMS) are proposed exactly in sparse impulse response (SIR) in order to reduce the computational complexity with faster convergence rate. Several simulations conducted across various sparse environments - based on the time evolution of error signals, the mean square error, the echo return loss enhancement and the computational complexity - validate the effectiveness of the proposed algorithm.

Citation

Abed Ahcene , , (2024-09-29), New Low-Complexity Selected Active Coefficients Adaptive Sparse Algorithm for Teleconferencing Systems and Identification, Jordan Journal of Electrical Engineering, Vol:11, Issue:1, pages:XXX-XXX, Scientific Research and Innovation Support Fund (SRISF)

In communication systems as public switched telephone networks and tele-and-vision-conferencing system, addressing the challenge of sparse acoustic echo is of paramount importance. The sparse impulse response identification is very essential in acoustic echo cancellation systems (AEC) exactly in sparse acoustic environments. This paper introduces an enhanced improved proportionate normalized-least-mean-square (IP-NLMS) algorithm, utilizing efficient variable step-size parameters and adapting only the active coefficients based on selection bloc for reducing the computational complexity. The proposed Variable Selection Coefficients IP-NLMS algorithm (VSC-IP-NLMS) focuses on adapting the selected active coefficients of the sparse impulse response (SIR), in order to both accuracy and convergence speed. Extensive simulations conducted under various sparse environments confirm the efficacy of the proposed algorithm. As important characteristic of this proposed VSC-IP-NLMS, it achieves these remarkable results with significantly reduced computational complexity compared to sparse and variable adaptive filtering algorithms, offering a promising avenue for improving the quality of communication systems.

Citation

Abed Ahcene , , (2024-06-26), New Variable Selected Coefficients Adaptive Sparse Algorithm for Acoustic System Identification, Traitement du Signal, Vol:41, Issue:3, pages:1089-1099, International Information and Engineering Technology Association (IIETA)

This research focuses on the development of speech enhancement techniques for two-channel audio systems. Specifically, we explore the utilization of an efficient sparseness recursive algorithm to tackle this challenge. The algorithm is designed to identify and attenuate noise components present in the audio signals, with the aim of improving the overall audio quality. In this investigation, we propose innovative approaches and enhancements to the sparseness recursive normalized least mean square (NLMS) algorithm, denoted Backward µ-law Proportionate NLMS (BMPNLMS), making it more suitable and effective for two-channel speech enhancement. By capitalizing on the sparsity properties of the audio signals, techniques proposed in this paper aim to enhance the desired audio while suppressing unwanted noise. Performance of the presented algorithm was examined by rigorous experiments based on several criteria. The obtained results thoroughly confirm the effectiveness of the proposed approach in real-world situations.

Citation

Abed Ahcene , , (2024-06-01), Improved Proportionate Symmetric Backward Adaptive Speech Enhancement Approach, Jordan Journal of Electrical Engineering, Vol:10, Issue:2, pages:197-211, Scientific Research and Innovation Support Fund (SRISF)

Modern 5G telecommunications systems tend to use higher frequencies. The design of such devices is becoming increasingly miniaturized for more powerful applications and technologies. In this context, Substrate Integrated Waveguides (SIW) replace conventional waveguides. Their design is mainly based on mathematical models. However, the resulting model presents a frequency shift with respect to the working frequency. In this paper we present an optimization method for ensuring the good performance of waveguides, based on SIW technology. These waveguides are easily integrated into 5G telecommunication systems. We'll then look at the different results obtained after changing the variables asiw and h). The direct waveguide had the lowest frequency shift (|Δf|=0.11GHz) at asiw =3.6mm, whereas the indirect waveguide had the best frequency shift (|Δf|=0.01GHz) at asiw =3.25mm.

Citation

Abed Ahcene , ,(2024-04-21), SIW structure optimization for 5G waveguide design,2024 8th International Conference on Image and Signal Processing and their Applications (ISPA),University Mohamed Khider of Biskra

This work is concerned with the design of an antenna array using SIW technology, where the basic element is a rectangular patch antenna. The main goal is to improve the radiation pattern. This technology allows this type of antenna to be produced at a lower cost and easily integrated into communications systems. The antenna was designed in the HFSS simulator on a FR-4 Epoxy substrate with a dielectric constant of εr=4.4 and a thickness of h=1.6mm. Three structures have been proposed: the array antenna (AR2), the array antenna (AR4), and the SIW array antenna (SAR4). This paper proposes to insert metal vias between the four elements of the AR4 antenna to direct the antenna radiation towards the main lobe. The antenna resonates at two different frequencies: 6.1GHz with a matching coefficient S11=17.77dB and 6.85GHz with a matching coefficient S11=16.63dB.

Citation

Abed Ahcene , ,(2024-04-21), SIW-based Network Antenna Design and Analysis,The 8th International Conference on Image and Signal Processing and their Applications (ISPA 2024),University Mohamed Khider of Biskra

This article introduces a novel technique to develop a circular patch antenna specifically tailored for 5G wireless technology operating in the 28 GHz frequency range. By thoughtfully incorporating a rectangular slot into the design on a Rogers substrate, not only does the antenna's performance get enhanced, but its bandwidth also gets expanded. This expansion in bandwidth allows the antenna to effectively cover a broader frequency range, which holds immense significance for practical applications. The compact design occupies only 8.3×8.5 mm 2 of space. Through simulations and measurements, it is demonstrated that the antenna achieves a 10 dB higher gain, ensuring a significant improvement in signal power.It delivers a bandwidth of 2.23 GHz, extending across the spectrum from 27.77 GHz to 30 GHz. The resonance analysis reveals a good return loss of-34.3 dB, indicating excellent signal matching. Furthermore, the antenna achieves a voltage standing wave ratio (VSWR) of 1.11, facilitating the effective transfer of radio frequency energy. The results indicate satisfactory performance in terms of matching, losses, and efficiency, positioning this design as a promising candidate for efficient communication in 5G networks.

Citation

Abed Ahcene , ,(2024-02-13), Design of low Profile, High Bandwidth Circular Patch Antenna at 28 GHz for Fifth Generation Wireless Technology,International Conference on Electronics, Energy and Measurement,University of Medea

In telecommunication systems, the antenna is an important element for transmitting information between transmitter system and receiver system. To improve the performance of antennas in terms of coverage area, they are usually grouped into arrays. Generally, if the spacing between arrays elements is less than half a wavelength, a mutual coupling usually occurs, which reduces the adaptability of the system. It is therefore very difficult to install these elements in mobile units of limited size. In this paper, we propose new design of multi-band MIMO antenna based on Substrate Integrated Waveguide (SIW) technology. The model system is tested by simulation in HFSS environment with the conducting copper is produced on substrate of FR4-Epoxy, a dielectric of 4.4 at frequency 2-5 GHz. This paper is devoted to the presentation and analysis of the proposed antenna using SIW technology, and study theirs characteristics exactly in the frequency band [2 − 5GHz]. The simulations are performed using the HFSS simulation software.

Citation

Abed Ahcene , ,(2024-02-05), New Multi-band MIMO Antennas Based on SIW Technology : Design and Performance Analysis,Second International Conference on Energy Transition and Security (ICETS),University of Adrar

This study focus on solving the acoustic Echo Cancelation (AEC) using adaptive filtering algorithm. The paper introduces as approach to incorporate a double Talk Detection (DTD) mechanism based on Normalized Cross Correlation (NCC) into the Fast Normalized Least Mean Square (FNLMS) algorithm. This integrated algorithm exhibits enhanced convergence speed. The results from simulations validate the effectiveness of this approach in mitigating acoustic echo, particularly in scenarios involving real impulse responses, such as a car cabin impulse response.

Citation

Abed Ahcene , HASSANI Islam, BENDOUMIA Rédha, ZOULIKHA Meriem, KOUDDED Elhachemi, ,(2023-12-12), A Robust Adaptive Filtering Algorithm with Double Talk Detection in-car Communication System,The Second International Conference on Energy Transition and Security,Adrar, Algeria

This paper describes a substrate integrated waveguide (SIW) filter built on an Fr4-Epoxy substrate with a dielectric constant 4.4 and a height of h=1.6mm. SIW-based devices have piqued the interest of researchers in recent years due to their low loss, small size, and low cost. The goal is to simulate and realize a SIW filter for C-band applications. The designed filter is analyzed using the reflection coefficient S11 and electric field distributions. We used the HFSS simulator. According to the findings, there is a high degree of agreement between the simulated and realized filters. The results also show that the filter has a very good response. It also shows a bandwidth of 6.3GHz around the C-band frequencies. This filter's pass-band ranges from 5.39 to 6.83GHz, with an insertion loss of 4.2dB and a return loss of 45.49dB.

Citation

Abed Ahcene , , (2023-06-01), LOW-COST C-BAND SIW BANDPASS FILTER USING FR4-EPOXY SUBSTRATE, Jordanian Journal of Computers and Information Technology, Vol:9, Issue:2, pages:166-174, Princess Sumaya University for Technology (PSUT)

This paper proposes a frequency-configurable (Sierpenski Triangle) fractal antenna. The antenna design is modeled and simulated using HFSS software, and the Sierpenski fractal antenna's reconfigurability is achieved by adding a PIN diode. We investigated four states for the first Reconfigurable order Sierpenski Fractal antenna and five states for the second Reconfigurable order Sierpenski Fractal antenna based on the diode's ON/OFF configuration states. Based on the coefficient comparison, the results show that the proposed Fractal Reconfigurable Antenna and the two proposed structures can be reconfigured in frequency. Furthermore, the antenna S1C3 with a frequency of 𝒇 = 𝟏𝟏.𝟓𝟕𝟗𝟑𝑮𝑯𝒛 adapts best to the first structure, while the antenna S2C5 with a frequency of 𝒇 = 𝟒.𝟗𝟎𝟖𝟐𝑮𝑯𝒛 adapts best to the second structure.

Citation

Abed Ahcene , Aissa Amrouche, Ahmed Bouchekhlal, Abdelmalek Birane, Abderrahim Si Saber, ,(2023-05-15), Reconfigurable Sierpinski Triangle Fractal Antenna Research and Development,International Conference on Advances in Electrical and Computer Engineering (ICAECE'2023),University Larbi Tebessi of Tebessa

Object Detection (OD) techniques have emerged as the key to dealing with the most complex computer vision problems in recent years. Vehicle License Plate Detection (VLPD) is the most important stage of any vehicle license plate recognition system (VLPR) because changes in its size, orientation, color, and background, contrast, and resolution have a direct impact on the system's robustness and accuracy. The purpose of this paper is to present an object detector for detecting vehicle license plates in real-world scenes. We developed a new dataset of vehicle license plate numbers and used it to train our custom model. In YOLO-v3 layers, we decreased the number of classes to one in order to improve the detector. When we evaluated the system, we achieved precision, recall, and overall accuracy metrics of 0.95, 0.96, and 92.83 percent, respectively.

Citation

Abed Ahcene , AMROUCHE Aissa, Nabil Hezil, Youssouf Bentrcia, ,(2022-12-21), Real-Time Detection of Vehicle License Plates Numbers,2022 2nd International Conference on New Technologies of Information and Communication (NTIC),Mila, Algeria

Text identification in natural scenes has emerged as a major research area in computer vision., with several applications including video retrieval and quick translation systems. Text identification is difficult in natural scene images due to changes in text size, color, orientation, background, contrast, and resolution. Text detection in complex backgrounds is more important to us. To address this issue, this work provides a detection and verification approach based on You Only Look Once Yolo (YOLO) algorithm. To get more accurate end findings, we use the YOLO-v4-Tiny approach to develop our custom text detection model. To evaluate the system, we constructed a ground verification system. Our method obtained 94.85% precision for experimental data.

Citation

Abed Ahcene , AMROUCHE Aissa, Youssouf Bentrcia, Nabil Hezil, Khadidja Nesrine Boubakeur, Khadidja Ghribi, ,(2022-11-22), Detection and Localization of Arabic Text in Natural Scene Images,International Conference on Computer Communications and Intelligent Systems (I3CIS),Jijel, Algeria

Vehicle detection and tracking is a popular research topic in Intelligent Transportation Systems. The goal of this paper is to detect, identify, and track vehicles in surveillance camera footage in order for them to be extracted efficiently and accurately. You Only Look Once version 4 (YOLOv4) algorithm is used in this paper to propose a real-time vehicle detection and tracking system. The suggested system has been evaluated using a variety of measures, including accuracy, precision, and recognition recall. For the experimental data, the system attained an accuracy of 96.30 percent and an overall accuracy of 94.17 percent. The results reveal that the suggested system successfully tracks vehicles in the scene.

Citation

Abed Ahcene , AMROUCHE Aissa, Youssouf Bentrcia, Nabil Hezil, ,(2022-05-08), Vehicle Detection and Tracking in Real-time using YOLOv4-tiny,International Conference on Image and Signal Processing and their Applications (ISPA),Mostaganem, Algeria

This article discusses a Deep Neural Network-based Text-to-Speech synthesis for the Arabic language. Subjective and objective tests were used to evaluate the system. We used the Mean Opinion Score (MOS) for subjective evaluation, and the Diagnostic Rhyme Test (DRT) to test the intelligibility of some consonants and vowels. We use the Perceptual Evaluation of Speech Quality (PESQ) for objective evaluation. The results have a mean of 3.92/5, 3.88/5 for the MOS and DRT tests, respectively, and 3.17/5 for the PESQ test; the majority of words and sentences were recognized, and the system's overall evaluation quality was satisfactory. Furthermore, the results show a significant improvement in the quality of synthesized speech for DNN-based TTS when compared to its HMM-based counterpart.

Citation

Abed Ahcene , AMROUCHE Aissa, Youssouf Bentrcia, Khadidja Nesrine Boubakeur, ,(2022-03-29), DNN-Based Arabic Speech Synthesis,International Conference on Electrical and Electronics Engineering (ICEEE),Istanbul (Turkey)

This paper aims to design and validate a phonetically balanced speech corpus for Arabic language. Designing and developing a rich and phonetically balanced corpus in optimal context is one of the key issues in building high quality of text-to-speech synthesis systems. The rich characteristic is in the sense that it must contain all the possible phonemes on the right and left context, whereas the balanced characteristic is in the sense that it respects the phonetic distribution in the language. We propose a new methodology for designing and implementing such corpus for speech synthesis purposes. The paper explains the whole creation process of this corpus, beginning with the design stage, corpus creation, recording phases, and finally the segmentation of the speech corpus. The speech corpus contains 202 sentences with 6174 phonemes. In order to validate the speech corpus, an Arabic speech synthesis system using Hidden Markov Models has been developed.

Citation

Abed Ahcene , AMROUCHE Aissa, Kamel Ferrat, Khadidja Nesrine Boubakeur, Youssouf Bentrcia, Leila Falek, , (2021-09-01), Balanced Arabic corpus design for speech synthesis, International Journal of Speech Technology, Vol:24, Issue:3, pages:1-13, Springer Nature

The voice quality evaluation of communication systems is necessary for technical and commercial reasons for the expansion of digital networks, mobile or VoIP and speech synthesis systems. Voice quality can be evaluated using two types of methods: subjective MOS (Mean Opinion Score) and objective PESQ (Perceptual Evaluation Speech Quality). In this work, we propose a study of voice quality evaluation methods; in which a subjective and objective evaluation platform of voice quality is provided. We applied different tests used in the assessment of the speech signal quality to speech synthesis signal for the Arabic Language (GArabic : Generic Arabic). The listeners recognized the majority of changes of consonants and vowels in words and sentences with respective percentages of 98.26%, 92.97%. The comparison between MOS and PESQ tests gave a good correlation coefficient of 0.922.

Citation

Abed Ahcene , AMROUCHE Aissa, Khadidja Nesrine Boubakeur, Youssouf Bentrcia, Kamel Ferrat, Leila Falek, ,(2021-04-09), Voice Quality Evaluation Platform for the Arabic Language,International Conference on Electrical and Electronics Engineering (ICEEE),Istanbul (Turkey)

The work presented in this paper is about Text-to-Speech (TTS) synthesis and, more particularly, about statistical speech synthesis using the Hidden Markov Models (HMM). The main objective of this work is to study the functioning of the HMM-based speech synthesis system (HTS) and the implementation of this method to create a system that produces understandable speech output for a given Arabic text. We have done a brief description of the statistical parametric speech synthesis based on HMM, the steps followed to implement this method for Arabic language. Finally, for the evaluations of the system are based on subjective mean opinion score and objective tests. Regarding the intelligibility, naturalness aspects (listening) and the quality (Perceptual Evaluation of Speech Quality (PESQ)).

Citation

Abed Ahcene , ,(2019-04-16), Arabic Speech Synthesis System Based on HMM,International Conference on Electrical and Electronics Engineering (ICEEE),Istanbul (Turkey)

In this paper we propose an automatic Arabic phonemes boundary detection system. This system is mainly used to perform an automatic speech corpus labeling. Because the manual labeling is a hard task and consumes time. We have used the HTK (Hidden Markov Tools Kit) model to solve this problem. The Hidden Markov Models implementation is used to detect phonemes boundaries with the textual information given by the transcription file. The final system improves a Correct Classification Rate of 89.5%, obtained by 5-HMM of 8 Gaussian components. Keywords: HTK, HMM, Arabic

Citation

Abed Ahcene , Aissa Amrouche, Khadidja Nesrine Boubakeur, ,(2017-05-17), Investigation of HTK for Arabic Phonemes Boundary Detection,International Conference on Engineering Research & Applications (ICERA-17),Istanbul (Turkey)

Because of its complex morphology, the Arabic language has a very different and difficult structure than other languages. Several stemming approaches that are applied to Arabic language, but a complete stemmer for this language is not available. The existing stem-based stemmers for stemming Arabic text have a poor performance in terms of accuracy and error rates. The aim of this study is to build an effective stemmer that answer the problems of Information Retrieval (IR), and presents new way to build electronic Arabic lexicon by using the most frequency roots as the input of lexicons.

Citation

Abed Ahcene , AMROUCHE Aissa, Boubakeur Khadidja Nesrine, ,(2017-05-17), New Method for Stemming of Arabic Language Text,International Conference on Engineering Research & Applications (ICERA-17),Istanbul (Turkey)

In this paper, we propose an automatic segmentation system of speech into phonemes for the Arabic language. This segmentation is based on two different techniques : Hidden Markov Models (HMM) and Artificial Neural Networks (ANN). Both systems were used to classify the speech signals, extracted from ALGASD corpus (ALGerian Arabic Speech Database), into five classes : fricatives, plosives, nasals, liquids and vowels. These methods achieve important performances with advantage of ANN.

Citation

Abed Ahcene , ,(2016-10-26), Automatic segmentation of Arabic speech signals by HMM and ANN,2016 International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM),Morocco

In this paper, we propose an automatic classification for Arabic phonemic substitution using a Hidden MarkovModel/Gaussian Mixture Model (HMM/GMM) systems. The main objective is to help Algerian children in the correction ofarticulation problems. Five cases are analyzed in the experiments, 20 Arabic words are recorded by a 20 Algerian children,with age range between 4 and 6 years old. Signals are recorded and stored as wave format with 16kHz as sampling rate, 12Mel Frequency Cepstral Coefficients (MFCC), with their first and second derivates, respectively ∆ and ∆∆ are extracted fromeach signal and used to the training and recognition phases. The proposed system achieved its best accuracy recognition85.73%, with 5-stats HMM when the output function is modelled by a GMM with 8Gaussian components.

Citation

Abed Ahcene , , (2016-07-01), HMM/GMM Classification for ArticulationDisorder Correction among Algerian Children, The International Arab Journal of Information Technology, Vol:13, Issue:4, pages:449_455, Zarqa University