A digital signal processing website made using HTML and CSS where users can speak and our website understand what the user speak and recogize the identity of the speaker in this project we make 3 model for the speakers and 4 models for the spoken sentenses using GMM.
We are class of 2024 Systems and Biomedical Engineering, at Cairo university.
- Python
- HTML
- CSS
- recognition of the speaker and what he says.
- plot score of the three speakers models.
- plot the RMS energy for the output and 3 speakers model
- plot Mel scale.
- plot mfcc for the output.