This tutorial provides an overview of automatic speaker recognition systems, which can identify or verify a person's identity based on their spoken phrase. The paper discusses the basic components and design trade-offs of such systems, including speech processing and feature extraction. It introduces a new automatic speaker-recognition system that achieves 98.9% correct identification. Various systems' performances are compared, and the paper highlights the importance of speaker recognition in access control, authentication, and security applications. The tutorial also covers the motivation for speaker recognition, the problem formulation, generic speaker verification, and the development of a simple but effective speaker-recognition algorithm. Additionally, it reviews previous work in the field, including advancements in speaker verification and identification systems, and discusses the YOHO Speaker-Verification Corpus, a high-quality speech database used for evaluation. The tutorial delves into speech processing, including signal acquisition, production, and linear prediction, and presents feature selection methods such as reflection coefficients, log area ratios, and mel-warped cepstrum. It also discusses mean and covariance estimation, divergence measures, and the Bhattacharyya distance, emphasizing the importance of selecting features that minimize the probability of error.This tutorial provides an overview of automatic speaker recognition systems, which can identify or verify a person's identity based on their spoken phrase. The paper discusses the basic components and design trade-offs of such systems, including speech processing and feature extraction. It introduces a new automatic speaker-recognition system that achieves 98.9% correct identification. Various systems' performances are compared, and the paper highlights the importance of speaker recognition in access control, authentication, and security applications. The tutorial also covers the motivation for speaker recognition, the problem formulation, generic speaker verification, and the development of a simple but effective speaker-recognition algorithm. Additionally, it reviews previous work in the field, including advancements in speaker verification and identification systems, and discusses the YOHO Speaker-Verification Corpus, a high-quality speech database used for evaluation. The tutorial delves into speech processing, including signal acquisition, production, and linear prediction, and presents feature selection methods such as reflection coefficients, log area ratios, and mel-warped cepstrum. It also discusses mean and covariance estimation, divergence measures, and the Bhattacharyya distance, emphasizing the importance of selecting features that minimize the probability of error.