Web Educational Services for All: The APEINTA Project
Ana Iglesias, Lourdes Moreno, Belén Ruiz, José Luis Pajares, Javier Jiménez, Juan Francisco López, Pablo Revuelta, Julián Hernández · 2011 · Proceedings of the International Cross-Disciplinary Conference on Web Accessibility (W4A) · doi:10.1145/1969289.1969313
Summary
This paper presents APEINTA, a Spanish educational project from Carlos III University of Madrid and the Spanish Centre of Captioning and Audio Description (CESyA), aimed at providing inclusive education through three cloud-based web services. Started in 2008, the project was migrating from on-site classroom tools to Software-as-a-Service (SaaS) cloud computing architecture, enabling access from any device (tablet, PDA, laptop, mobile phone) via WiFi or 3G from any location. The three services are: (1) a captioning service using automatic speech recognition to transcribe teacher speech in real time, delivered to students' personal devices — supporting both live captioning (where teacher and deaf student may be in different locations, with the teacher connecting via microphone or mobile phone) and recorded captioning (where a student uploads an unsubtitled video/audio file for automatic transcription); (2) a text-to-speech service enabling students with speech disabilities to type questions or comments on their devices which are then spoken aloud by synthetic voice, allowing full classroom participation; and (3) a web-based educational system providing accessible digital pedagogical resources with time and location independence, designed with user-centered principles accounting for functional diversity of students.
Key findings
The APEINTA services were deployed in multiple real-world settings: a web-based educational system for a Computer Science degree at Carlos III University (2009), captioning at two conferences (AMADIS'09 and ACCAPS'09), talks at two secondary schools (2010), and in two university degree programs (Computer Science and Library and Information Science, 2009). The project received the 2009 FIAPAS award for research and innovation in education from the Spanish Confederation of Parents and Friends of Deaf People, indicating strong reception from the deaf community. The cloud migration was significant — the original classroom-bound services gained new use cases once they became web-based, such as remote participation and on-demand captioning of pre-recorded content. At the time of publication, the captioning service was fully operational as a web service, while the TTS service was still being migrated to the cloud architecture.
Relevance
APEINTA anticipated the cloud-based accessibility services model that became mainstream during and after the COVID-19 pandemic, when remote learning made real-time captioning and communication tools essential rather than optional. The bidirectional approach — captioning for deaf students to receive information, and TTS for speech-impaired students to contribute — addresses both input and output communication barriers in education, a more complete model than systems that only address one direction. The project's migration from on-site to cloud services illustrates a broader trend in accessibility: moving from specialized equipment installed in specific classrooms to ubiquitous services available on any device. The real-world deployments across primary, secondary, and university settings demonstrate practical viability, though the paper lacks quantitative evaluation data on ASR accuracy, user satisfaction, or learning outcomes. The project represents a collaborative model between academia (Carlos III), a national accessibility center (CESyA), and industry (Orange R&D Spain) that could serve as a template for other countries' inclusive education initiatives.
Tags: education accessibility · captioning · text-to-speech · deaf and hard of hearing · speech disability · cloud computing · inclusive education · automatic speech recognition