@inproceedings{nebhi-szaszak-2023-automatic,
    title = "Automatic Assessment Of Spoken {E}nglish Proficiency Based on Multimodal and Multitask Transformers",
    author = {Nebhi, Kamel  and
      Szasz{\'a}k, Gy{\"o}rgy},
    editor = "Mitkov, Ruslan  and
      Angelova, Galia",
    booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
    month = sep,
    year = "2023",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/landing_page/2023.ranlp-1.83/",
    pages = "769--776",
    abstract = "This paper describes technology developed to automatically grade students on their English spontaneous spoken language proficiency with common european framework of reference for languages (CEFR) level. Our automated assessment system contains two tasks: elicited imitation and spontaneous speech assessment. Spontaneous speech assessment is a challenging task that requires evaluating various aspects of speech quality, content, and coherence. In this paper, we propose a multimodal and multitask transformer model that leverages both audio and text features to perform three tasks: scoring, coherence modeling, and prompt relevancy scoring. Our model uses a fusion of multiple features and multiple modality attention to capture the interactions between audio and text modalities and learn from different sources of information."
}