文章基本信息

标题：Voice Matching Using Genetic Algorithm
本地全文：下载
作者：Abhishek Bal ; Nilima Paul ; Suvasree Chakraborty 等
期刊名称：International Journal of Advanced Computer Research
印刷版ISSN：2249-7277
电子版ISSN：2277-7970
出版年度：2014
卷号：4
期号：14
页码：305-312
出版社：Association of Computer Communication Education for National Triumph (ACCENT)
摘要：In this paper, the use of Genetic Algorithm (GA) for voice recognition is described. The practical application of Genetic Algorithm (GA) to the solution of engineering problem is a rapidly emerging approach in the field of control engineering and signal processing. Genetic algorithms are useful for searching a space in multi-directional way from large spaces and poorly defined space. Voice is a signal of infinite information. Digital processing of voice signal is very important for automatic voice recognition technology. Nowadays, voice processing is very much important in security mechanism due to mimicry characteristic. So studying the voice feature extraction in voice processing is very necessary in military, hospital, telephone system, investigation bureau and etc. In order to extract valuable information from the voice signal, make decisions on the process, and obtain results, the data needs to be manipulated and analyzed. In this paper, if the instant voice is not matched with same person’s reference voices in the database, then Genetic Algorithm (GA) is applied between two randomly chosen reference voices. Again the instant voice is compared with the result of Genetic Algorithm (GA) which is used, including its three main steps: selection, crossover and mutation. We illustrate our approach with different sample of voices from human in our institution.
关键词：Genetic Algorithm; Voice Recognition; Euclidean Distance; Threshold Value; Fitness Function.