ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition

Ali Abouzeid, Bilal Elbouardi, Mohamed Maged, Shady Shehata


Abstract
Speech emotion recognition is vital for human-computer interaction, particularly for low-resource languages like Arabic, which face challenges due to limited data and research. We introduce ArabEmoNet, a lightweight architecture designed to overcome these limitations and deliver state-of-the-art performance. Unlike previous systems relying on discrete MFCC features and 1D convolutions, which miss nuanced spectro-temporal patterns, ArabEmoNet uses Mel spectrograms processed through 2D convolutions, preserving critical emotional cues often lost in traditional methods. While recent models favor large-scale architectures with millions of parameters, ArabEmoNet achieves superior results with just 1 million parameters—90 times smaller than HuBERT base and 74 times smaller than Whisper. This efficiency makes it ideal for resource-constrained environments. ArabEmoNet advances Arabic speech emotion recognition, offering exceptional performance and accessibility for real-world applications.
Anthology ID:
2025.arabicnlp-main.17
Volume:
Proceedings of The Third Arabic Natural Language Processing Conference
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Kareem Darwish, Ahmed Ali, Ibrahim Abu Farha, Samia Touileb, Imed Zitouni, Ahmed Abdelali, Sharefah Al-Ghamdi, Sakhar Alkhereyf, Wajdi Zaghouani, Salam Khalifa, Badr AlKhamissi, Rawan Almatham, Injy Hamed, Zaid Alyafeai, Areeb Alowisheq, Go Inoue, Khalil Mrini, Waad Alshammari
Venue:
ArabicNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
211–218
Language:
URL:
https://aclanthology.org/2025.arabicnlp-main.17/
DOI:
Bibkey:
Cite (ACL):
Ali Abouzeid, Bilal Elbouardi, Mohamed Maged, and Shady Shehata. 2025. ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 211–218, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition (Abouzeid et al., ArabicNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.arabicnlp-main.17.pdf