Text Independent Speaker Identification: A Review
Praveen Kumar P.S., Thimmaraja Yadava G, H. S. Jayanna · 2017
This paper presents an overview of Automatic Speaker Identificationtechnology (ASI) with an emphasis on textindependent identification. Speakeridentification is the process of automatically identifying person on thebasis of the information obtained from the speech data. ASI is generallyaccomplished in four steps. The first step is the acquisition of raw speechdata from real world environment. In the second step, the feature extractionis performed. The third step involves modeling the feature vectors andstoring in a database. In the last step, the decision-making/testing isdone. In this paper, the main techniques followed in each of the above stepsare reviewed.