Lexical Analysis of Automatic Transcriptions Using Speech-to-Text Services: A Statistically Evaluated Case Study

Abstract

This paper introduces Speech2Learning, an innovative architecture designed to leverage Speech-To-Text (STT) technology to enhance the accessibility of Learning Objects (LOs). Stemming from a recognized gap in prior Systematic Mapping, the primary objective of this architecture is to simplify the development of flexible educational solutions. In a collaborative endeavor with Brazilian EdTech DIO, we instantiated Speech2Learning as a Proof of Concept (PoC) to subtitle video lessons on their e-learning platform. This PoC was essential to obtain valuable insights for a more comprehensive Case Study. Therefore, we performed a lexical similarity analysis on the automatic transcriptions generated by leading STT providers in Portuguese, English and Spanish. Finally, we carried out a rigorous Statistical Analysis to evaluate the quantitative data from the Case Study. Our findings highlight the potential of Speech2Learning to promote the accessibility of LOs, as well as the relevance of continued research to increase the accuracy of STT services.