Voice-Based Chatbots for English Speaking Practice in Multilingual Low-Resource Indian Schools: A Multi-Stakeholder Study

2026-01-27

AI Summary

This study addresses how limited opportunities for English speaking practice constrain economic mobility among low-income students in India. Deploying a voice-based chatbot across four under-resourced schools in Delhi, the research employed a six-day field deployment combined with observations and interviews involving multiple stakeholders—students, teachers, and school principals—to investigate the feasibility and design requirements of such technology in multilingual, low-resource educational settings. The project proposes three core design principles: intelligible speech output tailored for non-native learners, a one-button simplified interaction interface, and actionable analytics tools to support teacher decision-making. Findings indicate that the system significantly boosted students’ speaking confidence and demonstrated high willingness to engage, while also revealing a tension between students’ preference for open-ended conversation and administrators’ emphasis on curriculum alignment—a critical consideration for the sustainable, multi-stakeholder adoption of educational AI.

Technology Category

• Humans and AI: AI for Accessibility
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Intelligent Robots: Human-Robot Interaction

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Spoken English proficiency is a powerful driver of economic mobility for low-income Indian youth, yet opportunities for spoken practice remain scarce in schools. We investigate the deployment of a voice-based chatbot for English conversation practice across four low-resource schools in Delhi. Through a six-day field study combining observations and interviews, we captured the perspectives of students, teachers, and principals. Findings confirm high demand across all groups, with notable gains in student speaking confidence. Our multi-stakeholder analysis surfaced a tension in long-term adoption vision: students favored open-ended conversational practice, while administrators emphasized curriculum-aligned assessment. We offer design recommendations for voice-enabled chatbots in low-resource multilingual contexts, highlighting the need for more intelligible speech output for non-native learners, one-tap interactions with simplified interfaces, and actionable analytics for educators. Beyond language learning, our findings inform the co-design of future AI-based educational technologies that are socially sustainable within the complex ecosystem of low-resource schools.

Problem

• spoken English proficiency
• low-resource schools
• voice-based chatbot
• English speaking practice
• multilingual education

Innovation

• voice-based chatbot
• low-resource schools
• multilingual education
• spoken English practice
• AI for social sustainability