期刊名称：International Journal of Computer and Information Technology
印刷版ISSN：2279-0764
出版年度：2014
卷号：3
期号：5
页码：952
出版社：International Journal of Computer and Information Technology
摘要：Speech is the basic means of communication of people. In addition to having certain content, it also contains important acoustic information, which allows us to identify the speaker. The identification of persons has long been interesting for researchers. There is a whole set of methods aimed at this purpose, commonly called biometrics. However, if we want to identify a person by his/her voice, we have to analyze his/her speech and decide about the identity by means of specific properties of the voice. This article provides an overview of the possibilities of processing voice recordings and describes a speaker identification system using two different approaches. The first approach is based on vector quantization and the LBG algorithm, while the second approach uses self-organizing maps (SOM).
