ABSTRACT
This chapter focuses on automatic speaker recognition technology. The technology closely related to speech recognition is speaker recognition, or the automatic recognition of a speaker through measurements of specifically individual characteristics arising in the speaker's voice signal. The actual realization of speaker recognition systems makes use of voice as the key tool for verifying to identify of a speaker for application to an extensive array of customer-demand services. Speaker recognition can be principally divided into speaker verification and speaker identification. Speaker verification is the process of accepting or rejecting the identity claim of a speaker by comparing a set of measurements of the speaker's utterances with a reference set of measurements of the utterance of the person whose identity is being claimed. The receiver operating characteristic curve adopted from psychophysics is used for evaluating speaker verification systems. One of the most difficult problems in speaker recognition is the intra-speaker variation of feature parameters.
