Speech Recognition Using Zero-Crossing Features

Voice recognition system is very useful in several areas of computer science and mathematics. In this paper, text-dependent speaker identification method is used. This system contains training phase, testing phase and recognition phase. In the training phase, the feature word spoken is extracted. During the testing phase, feature matching takes place. The feature that extracted is stored in the database. During the recognition phase, the features are extracted by the same techniques and are compared with the template in the database. In this thesis, the feature of the extraction takes place by Zero-crossing features.