Generative Artificial Intelligence Chatbot Integration for Virtual Reality Language Learning

This paper describes the potential of integrating generative artifi-cial intelligence (GenAI) based chatbots into virtual reality (VR) for language learning. Existing VR and AI-based systems primarily focus on practicing vocabulary or written skills, often neglecting speaking practice. To address this gap, a VR-enabled conversation trainer, chatbot AI for VR (CHAI) <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>, is introduced. The system integrates speech-to-text, a large language model, text-to-speech, and an avatar to enable natural conversations with CHAI. It is evaluated for its language error detection capabilities in English and German. The results show high accuracy in detecting language errors and demonstrate substantial reproducibility in error detection.

Authors

Institutions

Publication Details

Published
2025-03-08
DOI
https://doi.org/10.1109/vrw66409.2025.00035
Citations
1
Primary Topic
AI in Service Interactions
Type
article
Field-Weighted Citation Impact
2.48
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Generative Artificial Intelligence Chatbot Integration for Virtual Reality Language Learning

Andreas Künz, Joy Gisler, Long Cheng, Kaiqin Lao
1 citations
AI in Service Interactions
2.48
article

Generative Artificial Intelligence Chatbot Integration for Virtual Reality Language Learning

Andreas Künz, Joy Gisler, Long Cheng, Kaiqin Lao
article en
1 citations

Abstract

This paper describes the potential of integrating generative artifi-cial intelligence (GenAI) based chatbots into virtual reality (VR) for language learning. Existing VR and AI-based systems primarily focus on practicing vocabulary or written skills, often neglecting speaking practice. To address this gap, a VR-enabled conversation trainer, chatbot AI for VR (CHAI) <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>, is introduced. The system integrates speech-to-text, a large language model, text-to-speech, and an avatar to enable natural conversations with CHAI. It is evaluated for its language error detection capabilities in English and German. The results show high accuracy in detecting language errors and demonstrate substantial reproducibility in error detection.

ETH Zurich (CH)
Openalex Percentile: Top 11%
AI in Service Interactions
2.48
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.