Voice Chatbot for Language Learning
Explore outputs from this project supported by the AI Teaching and Learning Exploratory Fund in 2024-25
Project members
Marion Sadoux, Cornelia Wiedenhofer, Jieun Kiaer, Emine Cakir (OUDCE and Humanities Division).
Project summary
Developing an AI-powered voice chatbot integrated into Canvas to help L2 learners practice spoken interaction in various languages, reducing anxiety and fostering inclusivity.
View final project report (PDF)
AI in Teaching and Learning at Oxford Knowledge Exchange Forum, 9 July 2025
Findings from projects supported by the AI Teaching and Learning Exploratory Fund in 2024–25 were presented at the AI in Teaching and Learning at Oxford Knowledge Exchange Forum at Saïd Business School on Wednesday, 9 July 2025.
Project team members each presented a lightning talk to all event participants, and hosted a series of small group discussions.
Follow the links below to view the lightning talk recording and presentation slides for this project.
View presentation slides (PDF)
Project case study
The AI voice chatbot for language learning developed as part of this exploratory fund was embedded into Canvas learning pathways for the Language Centre French General Stage 4 course from weeks 4 to week 7 of Trinity Term. It was made available to a cohort of 15 learners attending either an in-person class or an online one.
Scenarios were designed to enable learners to engage in spontaneous dialogue with the Chatbot on the topic of each pathway to prepare for class interaction. This gave learners a precious opportunity to apply their learning on the pathway to a spontaneous dialogue and to have more time to focus on pragmatic oral production in a digital safe space. The students who made more use of the voice chatbot (2) found the activity useful and demonstrated a stronger awareness of their learning needs. Non-AI variants of the scenarios were provided for learners who might object to using AI but these did not provide any opportunities for learners to interact orally.
For the class tutor, this provided valuable insight on individual learner’s language in action, on the importance of control and mediation in interaction and on different compensation strategies that were used or could be further developed by learners to reinforce communication in a foreign language and boost learner confidence and motivation.
Language tutors of other languages were invited to a hands-on workshop to see the tool in action and test it, feedback was very positive, and all participants expressed the wish to be able to use it with their learners in the future.
The timing of the implementation of the voice chatbot coincided with the busy end of Trinity examinations and deadlines period and this had an impact on engagement. The AI Voice Chatbot required further fine tuning, and the samples of participation were too few to evaluate qualitatively, yet they provide promising insight for further research and development.
The use of AI voice chatbots provides enormous benefits to language learners but requires embedding as part of the learning strategies from the beginning of a course. Resistance to using AI is important to recognise and accept. However, students also need stronger coherent guidelines from the wider institution on whether and how to use AI for learning as well as an understanding of the comparative environmental impact of using different digital tools. Learners and teachers alike expressed a strong wish to continue to use this tool.
