Elhassane Ibn-Elhaj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Elhassane Ibn-Elhaj has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Amina Radgui
National Institute of Posts and Telecommunications
5 shared publications - Amimi Rajae
National Institute of Posts and Telecommunications
4 shared publications - El Mehdi Ismaili Alaoui
Moulay Ismail University
4 shared publications - Driss Aboutajdine
Mohammed V University
3 shared publications - Joseph Di Martino
LORIA, B.P. 239, 54506 Vandoeuvre-lès-Nancy, France
3 shared publications - Abdelaali Chaoub
Department of Telecommunication, National Institute of Posts and Telecommunications, Rabat, Morocco
2 shared publications
Latest Publications
- 12 February 2026
- Published by Springer Nature
- p. 257-271
A Conceptual Framework for Adaptive Student Assessment Using AI-Driven Recommendations and Facial Expression Recognition
- 12 February 2026
- Published by Springer Nature
- p. 257-271
A Conceptual Framework for Adaptive Student Assessment Using AI-Driven Recommendations and Facial Expression Recognition
- Open Access
- 1 November 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 36 (2) , 1199-1208
An improved student’s facial emotions recognition method using transfer learning
Instructors endeavour to encourage active participation and interaction among learners. However, in settings with a large number of students, such as universities or online platforms, obtaining real-time feedback and evaluating teaching methodology presents a significant challenge. In this paper, we introduce a student engagement recognition system based on a hybrid method using handcrafted features and transfer learning. The research is conducted on two databases for emotion detection based on facial cues (FER13) benchmarked dataset and our database. We use the local binary patterns (LBP) method combined with pre-trained MobileNet model for feature extraction and classification. The proposed system adeptly discerns students’ facial expressions and categorizes their engagement states as either ‘engaged’ or ‘disengaged’. We determine the most effective model by evaluating and comparing several deep learning models, including Inception-V3, VGG16, EfficientNet, ResNet, and DenseNet. Experimental results underscore the efficacy of our approach, revealing a remarkable accuracy, surpassing benchmarks set by state-of-the-art models.
- 1 November 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 36 (2) , 1199-1208
Open AccessAn improved student’s facial emotions recognition method using transfer learning
Instructors endeavour to encourage active participation and interaction among learners. However, in settings with a large number of students, such as universities or online platforms, obtaining real-time feedback and evaluating teaching methodology presents a significant challenge. In this paper, we introduce a student engagement recognition system based on a hybrid method using handcrafted features and transfer learning. The research is conducted on two databases for emotion detection based on facial cues (FER13) benchmarked dataset and our database. We use the local binary patterns (LBP) method combined with pre-trained MobileNet model for feature extraction and classification. The proposed system adeptly discerns students’ facial expressions and categorizes their engagement states as either ‘engaged’ or ‘disengaged’. We determine the most effective model by evaluating and comparing several deep learning models, including Inception-V3, VGG16, EfficientNet, ResNet, and DenseNet. Experimental results underscore the efficacy of our approach, revealing a remarkable accuracy, surpassing benchmarks set by state-of-the-art models.
- Open Access
- 31 July 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (15) , 6682
Assessment of Self-Supervised Denoising Methods for Esophageal Speech Enhancement
Esophageal speech (ES) is a pathological voice that is often difficult to understand. Moreover, acquiring recordings of a patient’s voice before a laryngectomy proves challenging, thereby complicating enhancing this kind of voice. That is why most supervised methods used to enhance ES are based on voice conversion, which uses healthy speaker targets, things that may not preserve the speaker’s identity. Otherwise, unsupervised methods for ES are mostly based on traditional filters, which cannot alone beat this kind of noise, making the denoising process difficult. Also, these methods are known for producing musical artifacts. To address these issues, a self-supervised method based on the Only-Noisy-Training (ONT) model was applied, consisting of denoising a signal without needing a clean target. Four experiments were conducted using Deep Complex UNET (DCUNET) and Deep Complex UNET with Complex Two-Stage Transformer Module (DCUNET-cTSTM) for assessment. Both of these models are based on the ONT approach. Also, for comparison purposes and to calculate the evaluation metrics, the pre-trained VoiceFixer model was used to restore the clean wave files of esophageal speech. Even with the fact that ONT-based methods work better with noisy wave files, the results have proven that ES can be denoised without the need for clean targets, and hence, the speaker’s identity is retained.
- 31 July 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (15) , 6682
Open AccessAssessment of Self-Supervised Denoising Methods for Esophageal Speech Enhancement
Esophageal speech (ES) is a pathological voice that is often difficult to understand. Moreover, acquiring recordings of a patient’s voice before a laryngectomy proves challenging, thereby complicating enhancing this kind of voice. That is why most supervised methods used to enhance ES are based on voice conversion, which uses healthy speaker targets, things that may not preserve the speaker’s identity. Otherwise, unsupervised methods for ES are mostly based on traditional filters, which cannot alone beat this kind of noise, making the denoising process difficult. Also, these methods are known for producing musical artifacts. To address these issues, a self-supervised method based on the Only-Noisy-Training (ONT) model was applied, consisting of denoising a signal without needing a clean target. Four experiments were conducted using Deep Complex UNET (DCUNET) and Deep Complex UNET with Complex Two-Stage Transformer Module (DCUNET-cTSTM) for assessment. Both of these models are based on the ONT approach. Also, for comparison purposes and to calculate the evaluation metrics, the pre-trained VoiceFixer model was used to restore the clean wave files of esophageal speech. Even with the fact that ONT-based methods work better with noisy wave files, the results have proven that ES can be denoised without the need for clean targets, and hence, the speaker’s identity is retained.
- 29 March 2023
- Published by Springer Nature
- p. 47-58
Towards Face-to-Face Smart Classroom that Adheres to Covid’19 Restrictions
- 29 March 2023
- Published by Springer Nature
- p. 47-58
Towards Face-to-Face Smart Classroom that Adheres to Covid’19 Restrictions
- 1 March 2023
- Published by Springer Nature
- p. 68-76
Predicted Phase Using Deep Neural Networks to Enhance Esophageal Speech
- 1 March 2023
- Published by Springer Nature
- p. 68-76
Predicted Phase Using Deep Neural Networks to Enhance Esophageal Speech
- Open Access
A survey of smart classroom: Concept, technologies and facial emotions recognition application
Technology has transformed traditional educational systems around the globe; integrating digital learning tools into classrooms offers students better opportunities to learn efficiently and allows the teacher to transfer knowledge more easily. In recent years, there have been many improvements in smart classrooms. For instance, the integration of facial emotion recognition systems (FER) has transformed the classroom into an emotionally aware area using the power of machine intelligence and IoT. This paper provides a consolidated survey of the state-of-the-art in the concept of smart classrooms and presents how the application of FER systems significantly takes this concept to the next level
Open AccessA survey of smart classroom: Concept, technologies and facial emotions recognition application
Technology has transformed traditional educational systems around the globe; integrating digital learning tools into classrooms offers students better opportunities to learn efficiently and allows the teacher to transfer knowledge more easily. In recent years, there have been many improvements in smart classrooms. For instance, the integration of facial emotion recognition systems (FER) has transformed the classroom into an emotionally aware area using the power of machine intelligence and IoT. This paper provides a consolidated survey of the state-of-the-art in the concept of smart classrooms and presents how the application of FER systems significantly takes this concept to the next level
- 1 September 2022
- Published by Springer Nature
- p. 326-338
A Survey of Smart Classroom: Concept, Technologies and Facial Emotions Recognition Application
- 1 September 2022
- Published by Springer Nature
- p. 326-338
A Survey of Smart Classroom: Concept, Technologies and Facial Emotions Recognition Application
- 11 December 2018
- Published by Elsevier in Digital Signal Processing
- Vol. 91, 77-90
A multiple description scalable coding scheme for adaptive video streaming over next generation cellular networks
- 11 December 2018
- Published by Elsevier in Digital Signal Processing
- Vol. 91, 77-90
A multiple description scalable coding scheme for adaptive video streaming over next generation cellular networks
- 21 July 2016
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 10 (7) , 1327-1333
A new method for fingerprint matching using phase-only auto- and cross-bispectrum
- 21 July 2016
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 10 (7) , 1327-1333
A new method for fingerprint matching using phase-only auto- and cross-bispectrum
- Open Access
- 6 May 2016
- Published by Springer Nature in SpringerPlus
- Vol. 5 (1) , 564
A corroborative study on improving pitch determination by time–frequency cepstrum decomposition using wavelets
A new wavelet-based method is presented in this work for estimating and tracking the pitch period. The main idea of the proposed new approach consists in extracting the cepstrum excitation signal and applying on it a wavelet transform whose resulting approximation coefficients are smoothed, for a better pitch determination. Although the principle of the algorithms proposed has already been considered previously, the novelty of our methods relies in the use of powerful wavelet transforms well adapted to pitch determination. The wavelet transforms considered in this article are the discrete wavelet transform and the dual tree complex wavelet transform. This article, by all the provided experimental results, corroborates the idea of decomposing the cepstrum excitation by using wavelet transforms for improving pitch detection. Another interesting point of this article relies in using a simple but efficient voicing decision (which actually improves a similar voicing criterion we proposed in a preceding published study) which on one hand respects the real-time process with low latency and on the other hand allows obtaining low classifications errors. The accuracy of the proposed pitch tracking algorithms has been evaluated using the international Bagshaw and the Keele databases which include male and female speakers. Our various experimental results demonstrate that the proposed methods provide important performance improvements when compared with previously published pitch determination algorithms.
- 6 May 2016
- Published by Springer Nature in SpringerPlus
- Vol. 5 (1) , 564
Open AccessA corroborative study on improving pitch determination by time–frequency cepstrum decomposition using wavelets
A new wavelet-based method is presented in this work for estimating and tracking the pitch period. The main idea of the proposed new approach consists in extracting the cepstrum excitation signal and applying on it a wavelet transform whose resulting approximation coefficients are smoothed, for a better pitch determination. Although the principle of the algorithms proposed has already been considered previously, the novelty of our methods relies in the use of powerful wavelet transforms well adapted to pitch determination. The wavelet transforms considered in this article are the discrete wavelet transform and the dual tree complex wavelet transform. This article, by all the provided experimental results, corroborates the idea of decomposing the cepstrum excitation by using wavelet transforms for improving pitch detection. Another interesting point of this article relies in using a simple but efficient voicing decision (which actually improves a similar voicing criterion we proposed in a preceding published study) which on one hand respects the real-time process with low latency and on the other hand allows obtaining low classifications errors. The accuracy of the proposed pitch tracking algorithms has been evaluated using the international Bagshaw and the Keele databases which include male and female speakers. Our various experimental results demonstrate that the proposed methods provide important performance improvements when compared with previously published pitch determination algorithms.