Language learning with interactive virtual agent scenarios and speech recognition: Lessons learned

The SPELL (Spoken Electronic Language Learning) system is a self-access computer-assisted language learning (CALL) package that integrates speaker-independent continuous speech recognition technology with virtual worlds and embodied virtual agents to create an environment in which learners can converse in the target language within meaningful contextualized scenarios. In this paper we provide an overview of the functionality, architecture, and implementation of the SPELL system. We also describe four phases of usability evaluation conductedwith the system and summarize the main results of these user assessments. Finally, we discuss the most significant lessons learned in the development and evaluation of the system. The paper focuses on the technological aspects of the system and its evaluation for usability and robustness, rather than its pedagogical methodology. Copyright # 2008 John Wiley & Sons, Ltd.