Skip to content

Latest commit

 

History

History
44 lines (30 loc) · 2.26 KB

README.md

File metadata and controls

44 lines (30 loc) · 2.26 KB

Lip-Reading Final Year Project :

This deep learning project focuses on Lip Reading, a technique for understanding speech by visually interpreting the movements of the lips. Our implementation utilizes deep learning and can be beneficial for individuals who are hard of hearing or for extracting information from videos without sound.

Project Presentation :

PFA.mp4

Lip2AudSpec: Speech Reconstruction from Silent Lip Movements Video 📹

Lip2AudSpec

Objective 🎯

Lip Reading is language-dependent, and in this project, we have chosen Hangul as the language for Lip Reading implementation.

Model-Graph:

Model

Loss Results After Using CTC Layer 📉 :

  • For 20 Epochs:
    20 Epochs

  • For 40 Epochs:
    40 Epochs

  • For 50 Epochs:
    50Epochs -For 50 Epochs & Batch-Normalization:
    image -For 80 Epochs & Batch-Normalization:
    image -For 90 Epochs & Batch-Normalization:

    image

DATASET :

check this link : image

Author :

Wissem Karous Reach me at:
wissemkar203@gmail.com