ANALISIS SISTEM PENGENALAN SUARA
MENGGUNAKAN METODE FAST FOURIER TRANSFORM
(FFT) DENGAN MATLAB
Total View This Week0
Total View This Week0
Institusion
INSTITUT TEKNOLOGI DIRGANTARA ADISUTJIPTO
Author
DESYA WAHYUDIANTHY, IKA
Subject
T Technology (General)
Datestamp
2024-07-11 02:50:54
Abstract :
The very rapid development of technology is currently affecting the sophistication of technology that is needed to facilitate human work. Based on these problems, one of the technological sophistication that can be used is the voice recognition technology (Speaker Recognition) which is a technology that uses speech recognition (Speaker Recognition) from a piece of a spoken phrase (word). This technology is part of biometric technology. In this research, voice recognition analysis will be performed using the Fast Fourier Transform (FFT) method using MATLAB 2016a. With the aim to identify a speaker with the accuracy of the reference data and test data which is evidenced in the form of sound output in the form of text names from the speaker sound samples. From this research it can be show that designing a speech recognition system that can identify sounds starts with the process of reference data and test data. Voice recognition made using Fast Fourier Transform (FFT) produces an average recognition accuracy rate of 50% which is carried out as many as 50 times the testing of 5 speakers who say the same word, with the best recognition accuracy rate of 100%.
The very rapid development of technology is currently affecting the sophistication of technology that is needed to facilitate human work. Based on these problems, one of the technological sophistication that can be used is the voice recognition technology (Speaker Recognition) which is a technology that uses speech recognition (Speaker Recognition) from a piece of a spoken phrase (word). This technology is part of biometric technology. In this research, voice recognition analysis will be performed using the Fast Fourier Transform (FFT) method using MATLAB 2016a. With the aim to identify a speaker with the accuracy of the reference data and test data which is evidenced in the form of sound output in the form of text names from the speaker sound samples. From this research it can be show that designing a speech recognition system that can identify sounds starts with the process of reference data and test data. Voice recognition made using Fast Fourier Transform (FFT) produces an average recognition accuracy rate of 50% which is carried out as many as 50 times the testing of 5 speakers who say the same word, with the best recognition accuracy rate of 100%.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
