Aqilah Qathrunnada Mumtaz, . (2026) RANCANG BANGUN APLIKASI VERIFIKASI PENGGUNA BERBASIS VOICE BIOMETRIC MENGGUNAKAN ECAPA-TDNN PADA PENYIMPANAN DOKUMEN PRIBADI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
|
Text
ABSTRAK.pdf Download (575kB) |
|
|
Text
AWAL.pdf Download (4MB) |
|
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (11MB) |
|
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (25MB) |
|
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (40MB) |
|
|
Text
BAB 5.pdf Download (1MB) |
|
|
Text
DAFTAR PUSTAKA.pdf Download (2MB) |
|
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (208kB) |
|
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (41MB) |
|
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (429kB) |
Abstract
This research designs and builds DokuSafe as an Android-based personal document storage application with voice biometric and document encryption. The system is built using client-server architecture, where Android Application is used as document management, while FastAPI backend is used to process the voice authentication. ECAPA-TDNN model is used to verify the speaker based on the speaker embedding, while Nes2Net-X is used for Anti-spoofing layer to detect a faked audio before the verification process ran. The stored documents is secured by using AES-256, while the user data, document metadatas, and activity history saved locally in Room Database. Development method that is used in this research is Rapid Application Development (RAD) and the testing envolving unit testing, integration testing, system testing, performance testing, also model evaluation. The result of system testing shows that all the 35 testing scenarios is successfully executed with a 100% success rate. ECAPA-TDNN evaluation in 0,45 threshold delivered FAR 0,0154 and FRR 0,0000. Meanwhile, Nes2Net-X in 4,5 threshold delivered FAR 0,2353 and FRR 0,2778. Based on the result, DokuSafe is built successfully as a personal document storage application that implements layered protection with voice biometric, anti-spoofing detection, and document encryption.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511155] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Muhammad Panji Muslim] [Penguji 1: Ridwan Raafi’udin] [Penguji 2: Anis Fitri Nur Masruriyah] |
| Uncontrolled Keywords: | Android, ECAPA-TDNN, Nes2Net-X, AES-256, Voice biometric |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | AQILAH QATHRUNNADA MUMTAZ |
| Date Deposited: | 08 Sep 2026 07:47 |
| Last Modified: | 08 Sep 2026 07:47 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51922 |
Actions (login required)
![]() |
View Item |
