55395

465

484

20

A speech signal consists of several levels of information, which can be divided into two main categories. First, the speech signal conveys words or a message being spoken, and second, the signal also conveys information about the identity of the speaker. While the area of speech recognition is concerned with extracting the underlying linguistic message in an utterance, the area of speaker recognition is concerned with extracting the identity of the person speaking. In this research, the Wavelet Transform (Daubechies4) is used for addressing the problem of speaker recognition as a means to help match phonemes from a speaker signal. This work uses a template of pre-recorded, wavelet-transformed phonemes as its basis for comparison. This application illustrates how wavelets can be used for better accuracy in speaker recognition.

Speaker Recognition Using , Daubechies Wavelet Transform

2011

الاستاذ للعلوم الانسانيه و الاجتماعيه

الاستاذ للعلوم الانسانيه و الاجتماعيه