Speaker Identification Using Evolutionary Algorithm

Jane J. Stephan

《Research Journal of Applied Sciences, Engineering and Technology》 13卷9期 (2016/12) Pp. 717-721

https://doi.org/10.19026/rjaset.13.3345

摘要

The aim of this study was identifying the speaker using evolutionary algorithm such as Genetic Algorithm (GA). This study provides an efficient approach for speaker identification using Discrete Wavelet Transform (DWT) and the Energy in feature extraction stage and Genetic Algorithm used in classification stage to recognize the sound of speaker. Speaker recognition is the process of automatically recognizing who is speaking on the basis of individual information included in speech waves. The files that have been chosen here named WAV and recording sounds with different speakers. In practical side was used Delphi language (version 7) to tests the course. The results showed that the recognition good was 87%.

關鍵字

Energy ； genetic algorithm ； speaker identification ； wavelet transform