EUVIMEDEUVIMED entdecken
Crossref

LIPCOORDNET: A DUAL-STREAM DEEP LEARNING ARCHITECTURE FOR VISUAL SPEECH RECOGNITION USING FACIAL LANDMARKS

Wissem Karous, Hanen Lajnef, Tehani Dammak

Malaysian Journal of Computer Science · 11.06.2026 · 38 (4) · 354-369

DOI: 10.22452/mjcs.vol38no4.4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Malaysian Journal of Computer Science, online erschienen am 11.06.2026. Verfasst von Wissem Karous und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated lip reading systems have emerged as critical assistive technologies for hearing-impaired individuals and communication in noisy environments. This research presents an advanced deep learning framework for sentence-level lip reading that integrates 3D Convolutional Neural Networks (3D CNN) with bidirectional Long Short-Term Memory (Bi-LSTM) networks, enhanced by facial landmark coordinates as supplementary input features. Our proposed LipCoordNet architecture achieves state-of-the-art performance on the GRID corpus benchmark, obtaining a Word Error Rate (WER) of 1.7% and Character Error Rate (CER) of 0.6%, representing significant improvements over existing state-of-the-art methodologies evaluated on the same dataset. The system demonstrates robust performance through the integration of spatial-temporal visual features and geometric lip movement patterns, validated through comprehensive experiments including statistical significance testing across five independent runs, and deployed as an interactive demonstration platform.

Zitieren

APA

Karous, W., Lajnef, H., & Dammak, T. (2026). LIPCOORDNET: A DUAL-STREAM DEEP LEARNING ARCHITECTURE FOR VISUAL SPEECH RECOGNITION USING FACIAL LANDMARKS. Malaysian Journal of Computer Science, 38(4), 354-369. https://doi.org/10.22452/mjcs.vol38no4.4

Vancouver

Karous W, Lajnef H, Dammak T. LIPCOORDNET: A DUAL-STREAM DEEP LEARNING ARCHITECTURE FOR VISUAL SPEECH RECOGNITION USING FACIAL LANDMARKS. Malaysian Journal of Computer Science. 2026;38(4):354-369. doi:10.22452/mjcs.vol38no4.4

BibTeX
@article{Karous2026,
  author = {Karous, Wissem and Lajnef, Hanen and Dammak, Tehani},
  title = {LIPCOORDNET: A DUAL-STREAM DEEP LEARNING ARCHITECTURE FOR VISUAL SPEECH RECOGNITION USING FACIAL LANDMARKS},
  journal = {Malaysian Journal of Computer Science},
  year = {2026},
  volume = {38},
  number = {4},
  pages = {354--369},
  doi = {10.22452/mjcs.vol38no4.4}
}
Kostenlos starten →