Defining the voice recognition task
Voice recognition is the process of determining the identity of speakers and/or what the speakers say in their voices.
A full definition is given by Russ Adams as "the technology by which sounds, words or phrases spoken by humans are converted into electrical signals, and these signals are transformed into coding patterns to which meaning has been assigned" [Adams1990].
Voice recognition is related to, and overlaps with, two very similar applications: speaker recognition and speech recognition. Speaker recognition is the automated determination of who is speaking, and speech recognition is to determine what is being said. In addition, there is a difference between the act of authentication (commonly referred to as speaker verification) and identification. Another way to differentiate between voice recognition systems is by determining if they can handle only discrete words, connected words, or continuous speech.
In this chapter, our voice recognition task...