EARL Research - Reshaping Departmental Information Systems

Reshaping Departmental Information Systems

Design and Deployment of an OpenAI Powered Voice Assistant

Abstract

This study describes the development and assessment of a voice-activated assistant system that is intended to address both general knowledge queries and departmental information retrieval. The system integrates Python-based libraries for speech recognition, natural language processing, and text-to-speech conversion, utilizing the Raspberry Pi 4 as the primary hardware. The system utilizes a hybrid mechanism that integrates OpenAI GPT-3.5-Turbo API with a custom departmental database to process voice commands and provide precise responses. YouTube search and playback, Wikipedia integration, voice-activated web browsing, and current affairs updates via the News API are among the additional features. It is illustrated that the system is effective in a variety of acoustic environments, which underscores its potential to improve user interaction in institutional and academic environments.

Technology Used

Raspberry Pi

The dataset is available on Kaggle. The code will be made public upon publication of the paper.

Python

Python libraries were used.

Raspberry Pi Display

The display was used to view the I/O status.

Speakers and Microphone

These were utilized for input and output.

Motivation

The motivation behind this work stems from the increasing need for efficient and interactive voice-activated systems that can streamline both general information retrieval and institution-specific tasks. With the growing complexity of information systems within academic and institutional environments, there is a pressing demand for a solution that can seamlessly integrate multiple information sources while being intuitive and accessible to users. By leveraging the versatility of Raspberry Pi 4 and Python-based libraries for speech recognition, natural language processing, and text-to-speech, this study aims to develop a low-cost, user-friendly assistant capable of handling both general queries and specific departmental information retrieval. The integration of OpenAI's GPT-3.5-Turbo API alongside a custom departmental database ensures that the system delivers precise responses, making it highly adaptable for various use cases. Furthermore, additional functionalities such as YouTube search, Wikipedia integration, voice-activated web browsing, and real-time news updates enhance the system's overall usability, offering users a comprehensive voice-activated tool. The system's effectiveness in diverse acoustic environments highlights its potential to improve accessibility and user interaction, making it a valuable asset for academic institutions looking to modernize their information dissemination and internal operations.

Team

Hierarchy

The team was led by Hamza and Juhan. Jasim and A.B.Shahed contributed significantly to all aspects of the research project. The research work was supervised by A.N.Chowdhury and proofread by A.Begum.