![]() | Only 14 pages are availabe for public view |
Abstract Speaker identification is an interesting speech processing topic that has a large number of applications. The main objective of speaker identification is to mimic the human auditory system that identifies the person from his spoken phrase. The elementary task is to find a unique voice signature that discriminates one person from another. This voice signature is found by a feature extraction process, which is the initial stage of any recognition system. So, we can say that the feature extraction is the process of converting the speech signal into a vector called the feature vector that represents the voice characteristics of the speaker with a low data rate. |