VOICE GENDER RECOGNITION USING MFCCAND CNN

MINCELUNGAN, JOSHUA ARBIE YEDIDYA (2024) VOICE GENDER RECOGNITION USING MFCCAND CNN. Skripsi thesis, UNIVERSITAS KATOLIK SOEGIJAPRANATA.

[img]
Preview
 Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_COVER_1.pdf
Download (231kB) | Preview
[img] Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_BAB I_1.pdf
Restricted to Registered users only
Download (237kB)
[img] Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_BAB II_1.pdf
Restricted to Registered users only
Download (178kB)
[img] Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_BAB III_1.pdf
Restricted to Registered users only
Download (337kB)
[img] Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_BAB IV_1.pdf
Restricted to Registered users only
Download (1MB)
[img] Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_BAB V_1.pdf
Restricted to Registered users only
Download (167kB)
[img]
Preview
 Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_DAPUS_1.pdf
Download (233kB) | Preview
[img] Text
20.K1.0019-YOSHUA ARBIE YEDIDYA MINCELUNGAN_LAMPIRAN_1.pdf
Restricted to Registered users only
Download (332kB)

Abstract

Audio gender recognition is an interesting play of technology with the biological society. It has lots of advantages in security, healthcare, and social sciences. In recent papers, audio recognition using Convolutional Neural Network (CNN) perform a great performance. Then comes a question is CNN also able to do a voice gender recognition from Mel Frequency Cepstral Coefficients (MFCC) feature extraction. This research will implementing CNN model and MFCC feature extraction on voice gender recognition and do tuning on the parameter to find the best quality. The dataset used in this research was obtained from Kaggle, it contains validated audio files of male's and female's voices. After extracting the MFCC feature, it will be inputted into CNN to learn its pattern. Finally, the model will be tuned and find the best quality.

Item Type: Thesis (Skripsi)
Subjects: 000 Computer Science, Information and General Works
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: Mr Yosua Norman Rumondor
Date Deposited: 23 Apr 2024 02:57
Last Modified: 23 Apr 2024 02:57
URI: http://repository.unika.ac.id/id/eprint/35215

Actions (login required)

View Item View Item
Unika Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.