Hey Dona! Can you help me with student course registration?
Project Overview
The document explores the transformative role of generative AI in education, focusing on the application 'Hey Dona', an intelligent personal agent that facilitates automated, voice-operated course registration. This innovative tool addresses the growing demand for voice assistance in educational environments by accommodating multiple accents and integrating features such as task planning optimization and language translation. By enhancing user experience through both speech and text interactions, 'Hey Dona' operates seamlessly across various devices, ultimately aiming to improve human-AI interaction in educational contexts. The findings indicate that such applications not only streamline administrative processes but also foster a more inclusive and accessible learning environment, demonstrating the potential of generative AI to significantly enhance educational outcomes and engagement.
Key Applications
Hey Dona
Context: Voice-assisted course registration for students at Montclair State University.
Implementation: Developed using Python, utilizing speech recognition, text-to-speech, and natural language processing to facilitate voice commands and interactions.
Outcomes: Enhanced user satisfaction in course registration, with positive feedback on accent recognition and task optimization.
Challenges: Encountered latency issues, especially in outdoor settings, and lacks automated tuition payment functionality.
Implementation Barriers
Technical Barrier
Latency issues during processing, particularly in noisy outdoor environments.
Proposed Solutions: Future work aims to fix latency problems and incorporate automated tuition payments.
Usability Barrier
Voice assistants may misinterpret queries or fail to recognize various accents adequately.
Proposed Solutions: Optimizing voice recognition and incorporating extensive training with diverse data.
Project Team
Vishesh Kalvakurthi
Researcher
Aparna S. Varde
Researcher
John Jenq
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Vishesh Kalvakurthi, Aparna S. Varde, John Jenq
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai