EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Parallel Bilingual Datasets: A Multimodal Deep Learning Framework for Proficiency and Style Classification

Padmavathi Kesavan, Miranda Lakshmi Travis, Martin Aruldoss, Martin Wynn

Multimodal Technologies and Interaction · 30.04.2026 · 10 (5) · 47

DOI: 10.3390/mti10050047 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Multimodal Technologies and Interaction, online erschienen am 30.04.2026. Verfasst von Padmavathi Kesavan und 3 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a multimodal deep learning framework for automatic proficiency and style classification of parallel Bilingual Tamil–Hindi learner data. The proposed system employs a dual-headed neural architecture to simultaneously predict proficiency levels (Basic, Advanced) and stylistic categories (Formal, Literary) using shared feature representations. A curated dataset of bilingual text samples is utilized, along with synthetic speech generated through text-to-speech (TTS) to enable controlled multimodal experimentation. Five deep learning architectures are evaluated under text-only, audio-only, and learnable fusion settings. Experimental findings indicate that text-based models consistently achieve strong performance in both proficiency and style classification tasks. In contrast, the audio-only model demonstrates limited effectiveness, highlighting the constraints of synthetic acoustic features in capturing meaningful linguistic information. The fusion models provide only marginal improvements over text-based approaches, suggesting that textual representations play a dominant role in proficiency and stylistic classification within controlled datasets. These results emphasize the importance of linguistic features over acoustic signals for automated language assessment in low-resource settings. The proposed framework provides a scalable and reproducible approach and offers a foundation for future work incorporating real speech data and more diverse linguistic inputs.

Zitieren

APA

Kesavan, P., Travis, M. L., Aruldoss, M., & Wynn, M. (2026). Parallel Bilingual Datasets: A Multimodal Deep Learning Framework for Proficiency and Style Classification. Multimodal Technologies and Interaction, 10(5), 47. https://doi.org/10.3390/mti10050047

Vancouver

Kesavan P, Travis ML, Aruldoss M, Wynn M. Parallel Bilingual Datasets: A Multimodal Deep Learning Framework for Proficiency and Style Classification. Multimodal Technologies and Interaction. 2026;10(5):47. doi:10.3390/mti10050047

BibTeX
@article{Kesavan2026,
  author = {Kesavan, Padmavathi and Travis, Miranda Lakshmi and Aruldoss, Martin and Wynn, Martin},
  title = {Parallel Bilingual Datasets: A Multimodal Deep Learning Framework for Proficiency and Style Classification},
  journal = {Multimodal Technologies and Interaction},
  year = {2026},
  volume = {10},
  number = {5},
  pages = {47},
  doi = {10.3390/mti10050047}
}
Kostenlos starten →