Skripsi

PERANCANGAN SISTEM KOMUNIKASI DUA ARAH PADA HUMANOID ROBOT BERBASIS ALGORITMA DEEP LEARNING

---

Penilaian

---

Humanoid robots are robots that resemble humans and can perform various activities like humans. Generally, humanoid robots can respond to every question from the interlocutor as a form of interaction in the form of two-way communication between humans and robots. Two-way communication on humanoid robots can occur because of the speech-to-text and text-to-speech systems embedded in the robot. However, research on two-way communication systems on humanoid robots using speech to text and text to speech is still limited and uses English. Therefore, in this study a two-way communication system was developed between humans and robots in real-time. The data used in this study came from 10 respondents (5 men and 5 women) and the sentences used met the standard Indonesian rules. The speech-to-textt system to convert voice into text uses a deep bidirectional long short-term memory (LSTM) algorithm and uses feature extraction Mel frequency cepstral coefficient (MFCC). The text to speech system uses the python pyttsx3 module which can convert text into speech as a robot response. The test results show that the speech to text model tested in a quiet room condition with a noise level of 57.5 - 60 dB has a good level of accuracy with an average word error rate (WER) of 25.10294% compared to the model. which is tested in conditions that have engine noise and crowds with a noise level of 62.4 – 86 dB which has a WER of 34.3635 %. This study shows that a two-way communication system can be implemented between humans and robots, where the robot can respond well to every sound that is inputted into the humanoid robot.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207002404	T74874	T748742022	Central Library (Referens)	Available

Detail Information

Series Title

-

Call Number

T748742022

Publisher

Indralaya : Prodi Teknik Elektro, Fakultas Teknik Universitas Sriwijaya., 2022

Collation

xvii, 66 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

621.382 07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Teknik Komunikasi
Teknik elektro
Sistem komunikasi dua arah

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment