Team Members:

  1. Ziad Thabe
  2. Amr Tarek
  3. Karim Azmi
  4. Youssef Samy

Supervisors:

  1. Dr. Mai El-Shehaly
  2. Dr. Ghada Khoreba

Project Description:

Lip-reading is to understand what someone is saying by watching the movements of their mouth. Lipreading plays a vital role in human communication and speech understanding however, it is a difficult task to be done by humans. Thus, the main goal of this project is to develop a deep learning approach for the real-time detection of spoken words. The training of a deep-layered CNN and RNN is being used to convert lips movement to written words.

Achievements:

  • Published a paper entitled “Lipreading Using a Comparative Machine Learning Approach” in the 1st International Workshop on Deep and Representation Learning” IWDRL Conference. https://ieeexplore.ieee.org/document/8358210/
  • First Place Winner of the “Three Minutes Thesis” Competition that took place during AUC Tech Summit 2018.
  • Winning the 2nd place award at “The Emirates NBD S.A.E Future Intelligence Program 2017”.

Project’s Video: 

Proposal Document:

LipDrive Proposal

Proposal Presentation:

LipDrive Proposal Presentation

SRS Document:

software-requirement-specification

SRS Presentation:

SRS Presentation

SDD Document:

software-design-document-Lip-Drive

SDD Presentation:

Thesis Document:

Thesis

Thesis Technical Presentation:

Lip-Drive Technical Final

Thesis Presentation:

Demo: