Speaker Recognition: A Review

Human can identify a speaker by hearing their voice over digital device or through phone in addition to in-person. Automatic Speaker Recognition (ASR), a voice biometric authentication technology, has been developed to take advantage of this innate human competency. It is capable of examining the voice signals and traits gleaned from speaker sounds, from which speakers can be identified. As a crucial component of speech biometrics, ASR has lately emerged as a successful study topic. While providing an overview of ASR and the key concepts navigating speaker recognition technology, this literature review highlights the research perspectives in the area of speaker recognition. This paper also illustrates the concepts of ASR with its types, challenges, and its applications.