CV

Education

VNU University of Engineering and Technology (UET) | Aug 2019 - Jun 2023
Bachelor in Computer Science

• Thesis: Vietnamese Automatic Speech Recognition in Low-resource conditions using Deep Learning
• Thesis advisor: Dr. Tran Quoc Long
• Cumulative GPA: 3.71/4.0 (Top 10)

Industry and Research Experience

AI Resident Intern | Aug 2021 - Present
FPT Software AI Center - website: fpt-aicenter.com/

• Works on #AI4Science

Research Student | Sep 2022 - May 2023
Institute of Artificial Intelligence (IAI), UET

• Research Topic: Person Tracking in Multiple Cameras
• Supervisor: Dr. Tran Quoc Long

Speech Processing Intern | Oct 2021 - Nov 2022
Speech and Language Processing Department, VinBigData - website: vinbigdata.com

• Worked on:
  • Streaming Automatic Speech Recognition (ASR) system
  • Decoding Algorithm
  • Speech Augmentation

Publications

Vietnamese Automatic Speech Recognition Boosted by Conformer Transducer in VLSP 2022 ASR Challenge
Thanh Tran Van Trong, Nam Nguyen Van, Khanh Le Duy
International Workshop on Vietnamese Language and Speech Processing (VLSP), 2022.

Projects

Automatic Speech Recognition Toolkit

• Written in TensorFlow 2.0
• Support multiple architectures and utilities for ASR.
• Technologies: Python, TensorFlow, Docker
• Source code: Github

Smart Room Simulator

• Speech Recognition System
• Monitor objects in the room by voice command
• Technologies: Python, TensorFlow, Tensorflow.js, JavaScript, HTML/CSS
• Source code: Github

Multi-label Image Recognition

• The combination of CNN and GCN
• Multiple variants of CNN and GCN supported
• Technologies: Python, PyTorch, Lightning Hydra
• Source code: Github

Image Captioning

• Caption generator for images using CNN and RNN
• Technologies: Python, TensorFlow
• Source code: Github

Honors and Awards

Third prize in Scientific Research Contest for Undergraduate - FIT-UET | 2023
VNU University of Engineering and Technology

2nd place in Automatic Speech Recognition - Task 1 | 2022
9th International Workshop on Vietnamese Language and Speech Processing

3rd place in Automatic Speech Recognition - Task 2 | 2022
9th International Workshop on Vietnamese Language and Speech Processing

The Excellence Scholarship - Full-ride | 2020, 2021, 2023
VNU University of Engineering and Technology
Top 10% of students in each department are awarded.

Technical Skills

• Programming Languages: Python, C/C++, Bash, Java, SQL, JavaScript, HTML/CSS
• Libraries: PyTorch, TensorFlow, Scikit-learn, OpenCV
• Developer Tools: Git, Docker, Jupyter

Certificates

• [FIT-UET] Third Prize in the Scientific Research Conference for Undergraduates
• [VLSP] Second Place in the shared task of ASR - Task 1
• [VLSP] Third Place in the shared task of ASR - Task 2

Other Activities

Data Science Mentor | 2023
Math and Science Summer Program (MaSSP) - website: masspvn.org/

• Teach high school and freshman students math and deep learning.

Technical Presentation | 2022
9th International Workshop on Vietnamese Language and Speech Processing

• Present our solution to the Vietnamese ASR task at VIASM.
• Poster: bit.ly/3CiLfBf

Head of Content | 2021
Human Resources in Technology Club (HRTech), UET - website: fb.com/hrtechclub

• Responsible for content creation and management of various HRTech’s events.