ABSTRACT
Speech is one of the most natural and efficient modes for
human communication. Speech contains many different levels of
information that are communicated to its listener. It not only
conveys a message of spoken words, but also at other levels conveys
information about the language being spoken, the emotion, gender,
and the identity of the speaker. Over the years, the ability to
communicate with machines using speech has gradually improved.
Speech recognition systems deal with the identification of spoken
language at different levels from phoneme, words, to continuous
sentences. An automatic speaker recognition system extracts the
feature of an individual speaker, then characterizes and classifies the
information in the speech signal to decide the speaker identity.