HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION
FACULTY OF INTERNATIONAL EDUCATION

GRADUATION PROJECT
DEVELOPING AN INTELLIGENT REAL-TIME AI VOICE
ASSISTANT SYSTEM USING ESP32 BOARD

PHAN NHU KHOI
Student ID: 20119189
LE DUY DAT
Student ID: 20119124
Major: COMPUTER ENGINEERING TECHNOLOGY
Advisor: Assoc. Prof. Dr Vo Minh Huan.

Ho Chi Minh City, December 2024

THE SOCIALIST REPUBLIC OF VIETNAM
Independence – Freedom– Happiness

Ho Chi Minh City, December 24th, 2024

GRADUATION PROJECT ASSIGNMENT
Student name: Le Duy Dat

Student ID: 20119124

Student name: Phan Nhu Khoi

Student ID: 20119189

Advisor: Assoc. Prof. Dr Vo Minh Huan

Phone number:

Date of assignment:

Date of submission:

1. Project title: DEVELOPING AN INTELLIGENT REAL-TIME AI VOICE

ASSISTANT SYSTEM USING ESP32 BOARD.
2. Initial materials provided by the advisor:

3. Content of the project:
The project focuses on developing an intelligent, real-time voice assistant system powered by
AI, using the ESP32 microcontroller. It integrates advanced APIs like Google Cloud, ChatGPT,
and Chatbot to enable natural language processing and contextual interactions. The system
aims to provide efficient voice-based command ution, real-time responses, and seamless
integration with IoT devices. Key features include speech recognition, adaptive learning
capabilities, and low-power consumption, ensuring scalability and cost-effectiveness for smart
home or industrial applications
4. Final product:
CHAIR OF THE PROGRAM

ADVISOR

(Sign with full name)

(Sign with full name)

THE SOCIALIST REPUBLIC OF VIETNAM
Independence – Freedom– Happiness

Ho Chi Minh City, December 24th, 2024

ADVISOR’S EVALUATION SHEET
Student name: LE DUY DAT

Student ID: 20119124

Student name: PHAN NHU KHOI

Student ID: 20119189

Major: COMPUTER ENGINEERING TECHNOLOGY
Project title: DEVELOPING AN INTELLIGENT REAL-TIME AI VOICE

ASSISTANT SYSTEM USING ESP32 BOARD.
Advisor: Assoc. Prof. Dr Vo Minh Huan.
EVALUATION
1. Content of the project: The project focuses on developing an intelligent, real-time AI voice
assistant system using the ESP32 microcontroller. It integrates advanced APIs like Google
Cloud, ChatGPT, and Chatbot to enable natural language processing and contextual
interactions.
2. Strengths: This project integrates advanced technologies like the ESP32, Google Cloud API,
and ChatGPT API for real-time, cost-effective performance. Its energy-efficient design,
scalability, and user-friendly int
...

...
formation Technology, Spring 2024.
[7] Phan Ly Huynh, “Nhan dang giong noi Web App su dung SpeechRecognition Web
API,” [Online]. Available: https://viblo.asia/p/nhan-dang-giong-noi-web-app-su-dungspeechrecognition-web-api-naQZRvvXZvx [Accessed Dec. 17, 2024]
[8] Hoy, M. B. (2018). Alexa, Siri, Cortana, and more: an introduction to voice assistants.
Medical reference services quarterly, 37(1), 81-88.
[9] Sk.Asma Sulthana, Sk.Masood, T.Ananth Kumar, V.Jaya Chandra, V. Adithya,
“VOICE GPT COMPANION”, International Journal of Research in Engineering, IT and
Social Sciences, ISSN 2250-0588, Impact Factor: 6.565, Volume 14 Issue 06, June 2024, Page
604-608
[10] Open AI, “GPT-4o mini: advancing cost-efficient intelligence”, [Online]. Available:
https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/ , [Accessed
Dec. 17, 2024].
[11] ESP32-WROOM-32, Copyright © 2024 Espressif Systems (Shanghai) Co., Ltd. All
rights reserved.
[12] Cassandra Dizon, “What is the Token Limit for ChatGPT 3.5 and ChatGPT 4?”,
[Online]. Available: https://tactiq.io/learn/token-limit-chatgpt-3-5-and-chatgpt-4, [Accessed
Dec. 17, 2024].
[13] Thomas A.FinkTM , “Creating an Adjacency Matrix Using the Dijkstra Algorithm for
Graph
Convolutional
Networks
GCNs”,
[Online].
Available:
https://thomasafink.medium.com/creating-an-adjacency-matrix-using-the-dijkstraalgorithm-for-graph-convolutional-networks-gcns-cc84c37e297 , [Accessed Dec. 17, 2024].
[14] Dinh Trong Huy, “Tom tat vai mo hinh Text-To-Speech (p1) - Tacotron va Tacotron2”,
[Online]. Available: https://viblo.asia/p/tom-tat-vai-mo-hinh-text-to-speech-p1-tacotron-vatacotron2-E375zApqlGW , [Accessed Dec. 17, 2024].
69

[15] Vo Thu Trang, “Cac Phuong phap tong hop going noi (Speech Synthesis) pho bien hien
nay”, [Online]. Available: https://vbee.vn/blog/chuyen-van-ban-thanh-giong-noi/phuongphap-tong-hop/ , [Accessed Dec. 17, 2024].
[16] Benoit Mariat, Yohann Balawender, “Web Speech API - Creating a web interface with
0 clicks”, [Online]. Available: https://techtalk.intersec.com/2023/03/web-speech-apicreating-a-web-interface-with-0-clicks/ , [Accessed Dec. 17, 2024].
[17] Enes Zvornicanin, “How Does ChatGPT Work?”, [Online]. Available:
https://www.baeldung.com/cs/chatgpt-model , [Accessed Dec. 17, 2024].
[18] Taivo Pungas, “A wild speed-up from OpenAI Dev Day”, [Online]. Available:
https://www.taivo.ai/__a-wild-speed-up-from-openai-dev-day/ , [Accessed Dec. 17, 2024].

70

S

K

L

0

0

2

1

5

4