SISTEM VERIFIKASI PENUTUR BERBASIS EKSTRAKSI CIRI
FAST FOURIER TRANSFORM
Total View This Week0
Total View This Week0
Institusion
INSTITUT TEKNOLOGI DIRGANTARA ADISUTJIPTO
Author
RIZKIA ZAINI, ELDESYA
Subject
T Technology (General)
Datestamp
2024-03-27 05:16:09
Abstract :
In this day and age, science and technology has begun to move into the modern era, and has developed rapidly and has a very large influence on human life today, one of which is the voice recognition system and verification system. Voice recognition system is part of the branch of signal processing or voice cues from a speaker. While the verification system aims to reject or accept the input voice signal that is given is the identity of a speaker or not.The second paragraph contains the methods used to achieve the objectives of the thesis along with the steps taken. In this study, an analysis of the voice verification system will be carried out using the Fast Fourier Transform method and the Euclidean Distance classification using the Matlab 2017b software. The goal is to perform speech recognition of words spoken by someone with the accuracy of the training data and test data as evidenced in the form of the minimum Euclidean Distance results from all experiments. The results of the study indicate that a voice verification system that can state whether a person's voice matches the claimed identity is by processing training data and test data. This system uses the Fast Fourier Transform method with Euclidean Distance classification and produces an average accuracy of 100% which is carried out 6 times testing the test data on 9 training data with the best recognition accuracy of 100%
In this day and age, science and technology has begun to move into the modern era, and has developed rapidly and has a very large influence on human life today, one of which is the voice recognition system and verification system. Voice recognition system is part of the branch of signal processing or voice cues from a speaker. While the verification system aims to reject or accept the input voice signal that is given is the identity of a speaker or not.The second paragraph contains the methods used to achieve the objectives of the thesis along with the steps taken. In this study, an analysis of the voice verification system will be carried out using the Fast Fourier Transform method and the Euclidean Distance classification using the Matlab 2017b software. The goal is to perform speech recognition of words spoken by someone with the accuracy of the training data and test data as evidenced in the form of the minimum Euclidean Distance results from all experiments. The results of the study indicate that a voice verification system that can state whether a person's voice matches the claimed identity is by processing training data and test data. This system uses the Fast Fourier Transform method with Euclidean Distance classification and produces an average accuracy of 100% which is carried out 6 times testing the test data on 9 training data with the best recognition accuracy of 100%
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
