Luganda Speech Intent Classification For IoT Applications.
Abstract
The rise of Internet of Things (IoT) technology has sparked interest in voice-controlled smart homes. This research project focuses on developing a Luganda speech intent classification system for IoT applications, aiming to integrate local languages into smart home environments. The project utilizes a combination of hardware components, including a Raspberry Pi, Wio Terminal, and ESP32 nodes as microcontrollers. The Raspberry Pi acts as the central hub for processing and interpreting Luganda voice commands, while the Wio Terminal serves as a display device, providing a user-friendly interface for interacting with the smart home system. The ESP32 nodes are utilized for controlling and coordinating the IoT devices within the smart home setup. The IoT devices within the smart home system are implemented using the MQTT (Message Queuing Telemetry Transport) protocol. The main objective of the project is to enable voice control using Luganda, a widely spoken local language in Uganda. To achieve this, a natural language processing (NLP) model is developed and deployed on the Raspberry Pi. The model incorporates Mel Frequency Cepstral Coefficients (MFCCs) as acoustic features and utilizes a Convolutional Neural Network (Conv2D) architecture for speech intent classification. A dataset of Luganda voice commands was collected. By incorporating Luganda as the spoken language for voice commands, this project addresses the localization challenges and linguistic diversity in IoT applications. The proposed Luganda speech intent classification system allows users to interact seamlessly and naturally with their smart home devices, eliminating the requirement for English language proficiency. The research findings will contribute to the advancement of IoT applications by promoting inclusive and accessible voice control interfaces for smart home environments, particularly in regions where local languages are predominant.