Published Paper Details:

Lip Reading Recognition System is a technology that uses Artificial Intelligence to recognize words or speech by visual interpretation of face, mouth and lip movement without involvement of audio. Imagine you are talking to someone, and they can't hear what you're saying. They might try to understand your words by watching how your lips move. That's called lip reading. This task is difficult as people use different dictions and various ways to articulate a speech. The system works by using a camera to capture a video of a person's face while they are speaking. It's like a recording a video of their lips moving. The video is then analyzed by an AI algorithm that can identify lip movements, extract features, train the classifier by giving user's lip movement frames sequences as input and will identify said word and finally translate them into words. It's not always perfect, but it's often quite accurate. This can help deaf and mute individuals in understanding spoken language through visual cues of the speaker's lips and addressing communication barriers in their daily lives. It can also be used to improve privacy and security in applications for detecting suspicious behavior. The survey focuses on deep learning related approaches such as convolutional neural networks (CNN) [6], recurrent neural networks (RNN) [15] and their variants which have been proven to be more fruitful for both feature extraction and classification. This paper provides comparisons of different audio-visual databases, various algorithmic techniques by highlighting their accuracies, feature extraction methodologies and classification networks.