EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Diacritical Arabic Speech Recognition: Transformer-Based Models with Transfer Learning and Hybrid Data Augmentation

Haifa Alaqel, Khalil El Hindi

Information · 20.02.2025 · 16 (3) · 161

DOI: 10.3390/info16030161 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 20.02.2025. Verfasst von Haifa Alaqel und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diacritical Arabic (DA) refers to Arabic text with diacritical marks that guide pronunciation and clarify meanings, making their recognition crucial for accurate linguistic interpretation. These diacritical marks (short vowels) significantly influence meaning and pronunciation, and their accurate recognition is vital for the effectiveness of automatic speech recognition (ASR) systems, particularly in applications requiring high semantic precision, such as voice-enabled translation services. Despite its importance, leveraging advanced machine learning techniques to enhance ASR for diacritical Arabic has remained underexplored. A key challenge in developing DA ASR is the limited availability of training data. This study introduces a transformer-based approach leveraging transfer learning and data augmentation to address these challenges. Using a cross-lingual speech representation (XLSR) model pretrained on 53 languages, we fine-tune it on DA and integrate connectionist temporal classification (CTC) with transformers for improved performance. Data augmentation techniques, including volume adjustment, pitch shift, speed alteration, and hybrid strategies, further mitigate data limitations, significantly reducing word error rates (WER). Our methods achieve a WER of 12.17%, outperforming traditional ASR systems and setting a new benchmark for DA ASR. These findings demonstrate the potential of advanced machine learning to address longstanding challenges in DA ASR and enhance its accuracy.

Zitieren

APA

Alaqel, H., & Hindi, K. E. (2025). Improving Diacritical Arabic Speech Recognition: Transformer-Based Models with Transfer Learning and Hybrid Data Augmentation. Information, 16(3), 161. https://doi.org/10.3390/info16030161

Vancouver

Alaqel H, Hindi KE. Improving Diacritical Arabic Speech Recognition: Transformer-Based Models with Transfer Learning and Hybrid Data Augmentation. Information. 2025;16(3):161. doi:10.3390/info16030161

BibTeX
@article{Alaqel2025,
  author = {Alaqel, Haifa and Hindi, Khalil El},
  title = {Improving Diacritical Arabic Speech Recognition: Transformer-Based Models with Transfer Learning and Hybrid Data Augmentation},
  journal = {Information},
  year = {2025},
  volume = {16},
  number = {3},
  pages = {161},
  doi = {10.3390/info16030161}
}
Kostenlos starten →