Inspiration: To bridge the communication gap between hearing and non-hearing people using technology.
What it does: Converts real-time speech from a webpage into sign language alphabets for easy understanding.
How we built it: Used speech recognition and machine learning to convert voice into text and map it to sign language images.
Challenges I ran into: Handling speech accuracy, noise, and real-time conversion.
Accomplishments that I'm proud of: Built a working prototype that improves accessibility.
What I learned: Speech recognition, ML basics, and accessible web development.
What's next: Convert full sentences into animated sign language and add multi-language support.
Built With
- machine-learning
- natural-language-processing
- opencv
- python
- speech-recognition
- tensorflow-/-pytorch
- text-to-sign-dataset