Abstract
An identity verification and identification system based on a person's distinctive vocal characteristics is known as speaker recognition. This paper sheds light on the evolution of speaker recognition systems from the earliest days of computers to the most recent innovations. Voice represents the behavior biometric that communicates details about a person's features, ranging from the speaker's age, gender, and ethnicity. The field of speaker recognition focuses on identifying individuals by their voices. Even though speaker recognition has been the subject of research for the past eight decades. Applications such as the Internet of Things (IoT), smart homes, and smart gadgets have made their use fashionable in the modern era. The speaker recognition field is briefly discussed in this work with an outline of its modeling methodology and various feature extraction strategies across multiple languages. The aim of this speaker recognition literature is to advance academic knowledge of speaker recognition.
