IMPLEMENTASI MODEL DETEKSI WAKE WORD UNTUK INTELLIGENT VOICE ASSISTANT MENGGUNAKAN METODE CONVOLUTIONAL RECCURENT NEURAL NETWORK

MULYANA, IKA ELVINA and Ubaya, Huda (2021) IMPLEMENTASI MODEL DETEKSI WAKE WORD UNTUK INTELLIGENT VOICE ASSISTANT MENGGUNAKAN METODE CONVOLUTIONAL RECCURENT NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011381722110.pdf] Text
RAMA_56201_09011381722110.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_TURNITIN.pdf] Text
RAMA_56201_09011381722110_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_0216068101_01_front_ref.pdf]
Preview
Text
RAMA_56201_09011381722110_0216068101_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_56201_09011381722110_0216068101_02.pdf] Text
RAMA_56201_09011381722110_0216068101_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (517kB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_0216068101_03.pdf] Text
RAMA_56201_09011381722110_0216068101_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (159kB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_0216068101_04.pdf] Text
RAMA_56201_09011381722110_0216068101_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (752kB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_0216068101_05.pdf] Text
RAMA_56201_09011381722110_0216068101_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (120kB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_0216068101_06_ref.pdf] Text
RAMA_56201_09011381722110_0216068101_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (221kB) | Request a copy
[thumbnail of RAMA_56201_09011381722110_0216068101_07_lamp.pdf] Text
RAMA_56201_09011381722110_0216068101_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (149kB) | Request a copy

Abstract

Artificial Intelligence (AI) is a system that regulates human-machine interaction, especially through voice. Intelligent Voice Assistant (IVA) technology is a technology that uses voice to perform commands. There is an important aspect in IVA, namely Wake Word (WW) detection. WW is speech recognition found by word number identification (keyword). Wake Word used is the word "active". The Convolutional Recurrent Neural Network (CRNN) method is a combination of two neural networks involving CNN followed by RNN, by connecting the two CRNN networks to produce good and quite optimal results, especially for audio signals. CRNN has the advantage that in the convolutional layer there is an efficient feature extraction followed by a repeating layer that can extract information from the sequence of features generated by the convolutional layer. With the CRNN model, the results obtained for detecting the "active" sound in this study were an accuracy of 99.37%. Keyword: Artificial Intelligent, Wake Word, Intelligent Voice Assistant, Convolutional Recurrent Neural Network

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Artificial Intelligent, Wake Word, Intelligent voice Assistant, Convolutional Recurrent Neural Network.
Subjects: T Technology > T Technology (General) > T1-995 Technology (General)
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Ms Ika Elvina Mulyana
Date Deposited: 16 Dec 2021 04:28
Last Modified: 16 Dec 2021 04:28
URI: http://repository.unsri.ac.id/id/eprint/59290

Actions (login required)

View Item View Item