Classification of distorted text and speech using projection pursuit features

Information to be exchanged between two parties needs compression for achieving its efficient transmission. Encoded information gets distorted during its transmission over a channel due to noise. For monitoring and analysis of such noisy traffic of an adversary over communication networks, it is required to find the type of information, whether it is text or speech, then to restore it for further interpretation. Identification of text and speech helps to take preventive measure to avoid plain communication of sensitive information. In this paper, we consider a minimum distance criterion based pattern classification technique to classify distorted (noisy) encoded text and speech using multidimensional feature vectors and their projection pursuits obtained through Sammon´s and Chang´s algorithms. Feature extraction technique computes longest runs of one´s in blocks of bit-stream of noisy text and speech data. The classification results show that the highly noisy text and speech could be classified with almost 100% success using Chang´s projection pursuit technique.