Speakece: raspberry pi based wearable augmentation device for speech disordered individuals using cnn based models and real-time audio speech recognition/
Sean Iverson G. Geronimo, Rica Mae B. Pedemonte, Angelica A. Perez, Edward Miguel M. Saringan, and Paul Patrick W. Villarin.--
- Manila: Technological University of the Philippines, 2025.
- xiii, 132pages: 29cm.
Bachelor's thesis
College Of Engineering.--
Includes bibliographic references and index.
Speech disorders significantly impact an individual’s ability to communicate effectively, often leading to social and emotional challenges. Assistive technologies can bridge this gap, but many existing solutions are expensive, bulky, or lack real-time capabilities. SpeakECE, a wearable augmentation device designed to help individuals with speech impairments communicate more effectively. Built on a Raspberry Pi platform, the system leverages Convolutional Neural Network (CNN), particularly the Whisper OpenAI model for real-time audio speech recognition and processing. By translating impaired speech and converting it into clear, intelligible output, SpeakECE provides a cost-effective, portable, and user-friendly solution. This research study explores the development, implementation, and validation of the device, contributing to accessible and affordable assistive technology innovations.