Comparative analysis of two different system's framework for text dependent speaker verification

摘要: Speaker verification is among the widely used biometrics which generally offers more secure authentication for user access compared to regular passwords. process of automatically authenticating identity speaker in order protect resources by controlling its access. Usually claimed presenting a unique personal possession, here this case sample user's voice. In paper we present two different framework text dependent verification, one using Hard threshold based system and other Cohort Based System. The baseline employs MFCC DTW their purposes. A database 30 Speakers collected over practical noisy environment was testing validating modules. Experimental results shows that achieves good performance hard on constrained task. Finally combined normalized score individual techniques outperforms stand alone increases 85.61% conditions respectively. approaches are described detailed experimental analysis presented discussed.