An Efficient Knock Code Decoding Approach to assist the People with Communication Impairments

Communicating with communication impaired people is a challenging task for doctors and caretakers and hence computer based automated assistant systems are important to identify their needs in real-time. An efficient automated assistant system should be simple, fast and easy to use. To achieve these objectives, we have proposed a novel communication assistant approach based on the Knock code. In the proposed approach, communication impaired people are able to encode their messages into knock sounds. Then the sound patterns are decoded as the English words by processing the corresponding waveform images using a sequence of image processing algorithms. Finally, the decoded text is displayed to the patient and a voice message is also produced. Based on the evaluation studies, proposed approach is able to recognize the English words with accuracy of 94.11 percentage in real-time.