Pemisahan Suara Manusia Berdasarkan Jenis Kelamin Menggunakan Fast Fourier Transform (Fft)
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Telkom Purwokerto
Author
Lela, Sari Kristina
Subject
T Technology (General)
Datestamp
2021-06-09 02:06:39
Abstract :
Voice is one of the biometric features possessed by humans, just as there are fingerprints, DNA, retina of the eye, etc. there are no two humans who have the same voice. One of human's ability to identify a person is by seeing and hearing. Through the ability to see and hear someone can easily distinguish sexes, based on physical and voice categories. Voices that were previously easily recognizable by humans, can now also be recognized by computers, which aim to separate voices by gender, because there has been no research to separate voices by gender to help deaf people get information. The final result of this research is to know the average error of data objects that have been inputted with the algorithm used in this study is Fast Fourier Transform because the Fast Fourier Transform method itself can distinguish between the frequency domain and the time domain because every human has a different voice fingerprint. The results of the process of implementing the Fast Fourier Transform algorithm show whether or not the average sound error is influenced by the high and low amplitude of the sound being tested and from these results it is found that the average error amplitude of the female voice is lower than the amplitude of the average male voice error. Of the two sources of human voices used, the lowest average error was produced in the 7th cluster on Female 3 votes with an average error result of 132.840, while the results of trials conducted with 3 sound sources resulted in the lowest average error in the 3rd cluster on Female 3 votes with an average error result of 212,976, and on the four sound sources used the lowest error average in the 3rd cluster on Mela's voice with an average error result of 217.462. Keyword : Algorithm, Amplitude, Fast Fourier Transform, Implementation, Voice.
Voice is one of the biometric features possessed by humans, just as there are fingerprints, DNA, retina of the eye, etc. there are no two humans who have the same voice. One of human's ability to identify a person is by seeing and hearing. Through the ability to see and hear someone can easily distinguish sexes, based on physical and voice categories. Voices that were previously easily recognizable by humans, can now also be recognized by computers, which aim to separate voices by gender, because there has been no research to separate voices by gender to help deaf people get information. The final result of this research is to know the average error of data objects that have been inputted with the algorithm used in this study is Fast Fourier Transform because the Fast Fourier Transform method itself can distinguish between the frequency domain and the time domain because every human has a different voice fingerprint. The results of the process of implementing the Fast Fourier Transform algorithm show whether or not the average sound error is influenced by the high and low amplitude of the sound being tested and from these results it is found that the average error amplitude of the female voice is lower than the amplitude of the average male voice error. Of the two sources of human voices used, the lowest average error was produced in the 7th cluster on Female 3 votes with an average error result of 132.840, while the results of trials conducted with 3 sound sources resulted in the lowest average error in the 3rd cluster on Female 3 votes with an average error result of 212,976, and on the four sound sources used the lowest error average in the 3rd cluster on Mela's voice with an average error result of 217.462. Keyword : Algorithm, Amplitude, Fast Fourier Transform, Implementation, Voice.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
