IncluiMedia Studio: Autoria Web com Preservação de Privacidade para Experiências de Vídeo Acessíveis e Adaptáveis

• Julio C. S. Lima UFLA
• Daniel Henrique Silva UFLA
• Esther Silva de Magalhães UFLA
• Gabriel Aguiar A. Silva UFLA
• Luiz H. A. Correia UFLA
• André de Lima Salgado UFLA
• Mayron C. O. Moreira UFLA

DOI: https://doi.org/10.5753/webmedia_estendido.2026.34896

Resumo

The production of accessible videos may require separate tools for captioning, transcription, visual descriptions, and semantic navigation. This paper presents IncluiMedia Studio v0.4, a browser-based authoring tool that integrates temporal track editing, local acoustic assistance, consistency checking, and adaptive preview without transmitting media to remote inference services. The implementation uses Web APIs for local media access and processing, authoring data storage, and experimental integration of automatic speech recognition using Whisper through Transformers.js. Suggestions generated by the assistance mechanisms remain separate from the finalized tracks until explicitly accepted by the author. In three technical sessions conducted by a single author using videos ranging from 127.1 to 157.8 s and previously prepared tracks, acoustic analysis was completed in 1.12 to 1.31 s, the average heuristic completeness score increased from 53.7 to 77.0 points, and nine validation issues were resolved. Whisper inference was not completed in any of the sessions due to failures in the WASM/WebGPU execution environments; therefore, no experimental evidence regarding its accuracy or processing speed was obtained. The results demonstrate the execution of the track enrichment and inspection workflow but do not assess accessibility effectiveness or usability with target users. The release of a reproducible artifact through a digital preservation repository is part of the tool’s distribution strategy.

Palavras-chave: Accessible video, multimedia authoring, WebVTT, human review, automatic speech recognition, privacy

Referências

Jessica Oliveira Brito, Rodrigo Laiola Guimarães, and Celso A. S. Santos. 2017. Investigating the Collaborative Process of Subtitles Creation and Sharing for Videos on the Web. In Proceedings of the 23rd Brazilian Symposium on Multimedia and the Web. Association for Computing Machinery, 69–72. DOI: 10.1145/3126858.3131592

Alex de Souza Vieira, Álan Lívio V. Guedes, Daniel de Sousa Moraes, Lucas Ribeiro Madeira, Sérgio Colcher, and Carlos de S. Soares Neto. 2020. ListeningTV: Accessible Video using Interactive Audio Descriptions. In Anais Estendidos do XXVI Simpósio Brasileiro de Sistemas Multimídia e Web (WebMedia). Sociedade Brasileira de Computação, 71–74. DOI: 10.5753/webmedia_estendido.2020.13065

Leonardo A. Domingues, Virgínia P. Campos, Tiago M. U. Araújo, and Guido L. de S. Filho. 2016. Accessibility in Digital Cinema: A Proposal for Generation and Distribution of Audio Description. In Proceedings of the 22nd Brazilian Symposium on Multimedia and the Web. Association for Computing Machinery, 119–126. DOI: 10.1145/2976796.2976867

Itamar Rocha Filho, Felipe Honorato, J. Wallace Lucena, J. Pedro Teixeira, and Tiago Maritan. 2021. An Approach for Automatic Description of Characters for Blind People. In Proceedings of the Brazilian Symposium on Multimedia and the Web. Association for Computing Machinery, 53–56. DOI: 10.1145/3470482.3479617

Hugging Face. 2026. Transformers.js Documentation. [link] Accessed: 2026-08-13.

Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-ScaleWeak Supervision. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202). PMLR, 28492–28518. [link]

World Wide Web Consortium. 2015. Media Accessibility User Requirements. W3C Working Group Note. [link] Accessed: 2026-08-13.

World WideWeb Consortium. 2024.Web Content Accessibility Guidelines (WCAG) 2.2. W3C Recommendation. [link] Accessed: 2026-08-13.

World WideWeb Consortium. 2026. WebVTT: TheWeb Video Text Tracks Format. W3C Technical Report. [link] Accessed: 2026-08-13.