Accessibility and Inclusivity in Broadcast Learning Environments: A Computational Perspective
DOI:
https://doi.org/10.22399/ijcesen.5362Keywords:
broadcast learning, accessibility, automatic speech recognition, inclusive education, adaptive streaming, NLPAbstract
Broadcast learning environments—encompassing television-based education, live-streamed instruction, podcasted lectures, and synchronous video classrooms—have expanded access to formal and informal education globally. Yet these environments carry inherent structural barriers for learners with disabilities, non-native language speakers, and those operating under constrained technological or bandwidth conditions. This paper examines accessibility and inclusivity challenges in broadcast learning through a computational lens, surveying the state of automatic speech recognition (ASR), natural language processing (NLP)-driven captioning, AI-based sign language synthesis, adaptive bitrate streaming, and multimodal accessibility frameworks. We analyze existing technological solutions, identify persistent gaps in computational approaches, propose an integrative framework for universally accessible broadcast education, and outline directions for future research. The findings suggest that while computational tools have significantly narrowed accessibility gaps, systemic challenges remain—particularly at the intersection of linguistic diversity, cognitive load management, and infrastructure inequality.
References
[1] Baevski, A., Zhou, Y., Mohamed, A., & Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, 33, 12449–12460.
[2] CAST. (2018). Universal Design for Learning guidelines version 2.2. Retrieved from http://udlguidelines.cast.org
[3] Hersh, M., & Johnson, M. A. (2017). Assistive technology for visually impaired and blind people. Springer Science & Business Media.
[4] Koenecke, A., Nam, A., Lake, E., Nudell, J., Quartey, M., Mengesha, Z., ... & Goel, S. (2020). Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences, 117(14), 7684–7689.
[5] Mao, H., Netravali, R., & Alizadeh, M. (2017). Real experience: Adaptive bitrate video streaming with reinforcement learning. In Proceedings of the 16th ACM Workshop on Hot Topics in Networks (pp. 53–59).
[6] Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022). Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356.
[7] Rose, D. H., & Meyer, A. (2002). Teaching every student in the digital age: Universal design for learning. Association for Supervision and Curriculum Development.
[8] Sainath, T. N., Prabhavalkar, R., Kumar, S., Rao, K., Gruenstein, A., Lee, B., ... & Strohman, T. (2020). An efficient streaming non-recurrent on-device end-to-end model with improvements to achieve over 97.6% of beam search quality. In Proceedings of Interspeech 2020 (pp. 2679–2683).
[9] Štajner, S. (2021). Automatic text simplification with neural networks: A systematic literature review. arXiv preprint arXiv:2107.02986.
[10] Stoll, S., Camgoz, N. C., Hadfield, S., & Bowden, R. (2020). Text2Sign: Towards sign language production using neural machine translation and generative adversarial networks. International Journal of Computer Vision, 128(4), 891–908.
[11] Tatman, R. (2017). Gender and dialect bias in YouTube's automatic captions. In Proceedings of the First ACL Workshop on Ethics in Natural Language Processing (pp. 53–59).
[12] UNESCO. (2020). COVID-19 and higher education: Today and tomorrow. UNESCO-IESALC Impact Analysis and Policy Recommendations.
[13] Wald, M. (2012). Learning and teaching with technology through automatic speech recognition and captioning. In Ubiquitous Learning: An International Journal, 4(3), 37–46.
[14] W3C. (2018). Web Content Accessibility Guidelines (WCAG) 2.1. World Wide Web Consortium. https://www.w3.org/TR/WCAG21/
[15] Zhang, J., Zhao, Y., Saleh, M., & Liu, P. J. (2020). PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization. In Proceedings of the 37th International Conference on Machine Learning (pp. 11328–11339).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
