Nguyen Thi Thu Trang

Senior Lecturer and Researcher, Department Of Computer Science

Ph.D. in Computer Science, Université Paris-Sud 11 (now Université Paris-Saclay), France, 2015

M.S. in Computer Science, Hanoi University of Science and Technology, Vietnam, 2007

B.S. in Software Engineering, Hanoi University of Science and Technology, Vietnam, 2005

 

Email: trangntt@soict.hust.edu.vn

Web: https://soict.hust.edu.vn/en/ph-d-nguyen-thi-thu-trang.html

Research Areas

  • Speech Technology
  • Natural Language Processing
  • Large Language Model

Research Interests

  • Speech Synthesis
  • Speaker Recognition
  • Singing Voice Synthesis
  • Automatic Speech Recognition
  • Mispronunciation Detection and Diagnosis
  • Speech Emotion Recognition
  • Virtual Agents/Chatbots

Profile

NGUYEN Thi Thu Trang is a senior lecturer and researcher in Computer Science at the School of Information and Communication Technology (SoICT), Hanoi University of Science and Technology (HUST). She earned her Ph.D. in Computer Science in 2015 from the University of Paris-Sud 11 (now Paris-Saclay) and LIMSI-CNRS (now LISN-CNRS), France. Dr. Trang’s research focuses on speech technology and natural language processing, covering a wide range of topics including speech synthesis, speaker recognition, singing voice synthesis, automatic speech recognition, mispronunciation detection and diagnosis, speech emotion recognition, and virtual agents/chatbots. She has published over 40 top-tier international papers, co-authored several books, and has more than 20 years of experience in software engineering and artificial intelligence. She is the founder of Vbee, a conversational AI startup (https://vbee.ai), which delivers real-world applications such as smart call center solutions for hundreds of enterprises (e.g., Sacombank, MoMo, VietCredit) and AI voice platforms serving millions of users and SMEs (https://vbee.vn).

Dr. Trang was honored with the National Golden Globe Award in ICT in 2009. Together with Vbee, she has also received multiple major awards, including the Highest Prize at the Vietnamese Talent Awards 2018, VinTech Fund 2019, Best Female Founder Award at Startup Wheel 2020, Winner of Grab Venture Ignite 2020, Special Award at the Tuoi Tre Start-up Award 2023, and First Prize at QVIC 2024.

Publications

  • Huu Tuong Tu, Vu Huan, Nguyen Tien Cuong, Ngo Dien Hy and Nguyen Thi Thu Trang (2025, November). O_O-VC: Synthetic Data-Driven One-to-One Alignment for Any-to-Any Voice Conversion. Proceedings of the 30th Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). Suzhou, China.
  • Huu Tuong Tu; Luong Thanh Long; Vu Huan; Nguyen Thi Phuong Thao; Nguyen Van Thang; Nguyen Tien Cuong, Nguyen Thi Thu Trang (2025, April). Voice Conversion for Low-Resource Languages via Knowledge Transfer and Domain-Adversarial Training. In Proceeding of 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025), 1-5. Hyderabad, India.
  • Hoang Long Vu, Phuong Tuan Dat, Pham Thao Nhi, Nguyen Song Hao, Nguyen Thi Thu Trang (2025, April). VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition. In Proceeding of 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025). Hyderabad, India.
  • Hoang Long Vu, Pham Viet Thanh, Phuong Tuan Dat, Pham Thao Nhi, Nguyen Thi Thu Trang (2024, September). VSASV: a Vietnamese Dataset for Spoofing-Aware Speaker Verification. Proceedings of the 25th Conference of the International Speech Communication Association (Interspeech 2024), 4288-4292. Kos, Greece.
  • Tran Dang Tuyen, Le Trong Khanh, Nguyen Duy Khanh, Vu Duc Minh, Ngo Thi Thu Huyen, Woomyoung Park, Nguyen Thi Thu Trang (2025, September). VN-SLU: A Vietnamese Spoken Language Understanding Dataset. Proceedings of the 25th Conference of the International Speech Communication Association (Interspeech 2024), 1335-1339. Kos, Greece.
  • Pham Viet Thanh, Ngo Thi Thu Huyen, Pham Ngoc Quan, Nguyen Thi Thu Trang (2024, March). A Robust Pitch-Fusion Model for Speech Emotion Recognition in Tonal Languages. Procededings of the 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), 12386-12390. Seoul, Republic of Korea.
  • Nguyen Thi Thu Trang, Dang Trung Duc Anh, Vu Quoc Viet and Park Woomyoung (2022, September). Building Vietnamese Conversational Smart Home Dataset and Natural Language Understanding Model. Proceedings of the 23th Conference of the International Speech Communication Association (Interspeech 2022), 5180-5184. Incheon, Korea.
  • Nguyen Hoang Tien Bach, Nguyen Manh Dung, Nguyen Thi Thu Trang (2022, July). Machine Reading Comprehension Model for Low-Resource Languages and Experimenting on Vietnamese. Proceedings of the 35th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA/AIE 2022), 270-281. Kitakyushu, Japan.
  • Nguyen Thi Thu Trang, Dang Trung Duc Anh, Vu Quoc Viet and Park Woomyoung (2022, April). Advanced Joint Model for Vietnamese Intent Detection and Slot Tagging. Proceedings of the 8th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2022), 125-135. Springer, Cham.
  • Vi Thanh Dat, Pham Viet Thanh, Nguyen Thi Thu Trang (2021, November). Deep Speaker Verification Model for Low-Resource Languages and Vietnamese Dataset. Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation (PACLIC 2021), 442–451. Shanghai, China. November 2021.
  • Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro (2021, September). Prosodic Boundary Prediction Model for Vietnamese Text-To-Speech. Proceedings of the 22th Conference of the International Speech Communication Association (Interspeech 2021), 3885-3889. Brno, Czech Republic.
  • Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro (2021, September). Prosodic Boundary Prediction Model for Vietnamese Text-To-Speech. Proceedings of the 22th Conference of the International Speech Communication Association (Interspeech 2021), 3885-3889. Brno, Czech Republic.
  • Dang Trung Duc Anh, Nguyen Thi Thu Trang. TDP – A Hybrid Diacritic Restoration with Transformer Decoder. In Proceedings of The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC 2020). Hanoi, Vietnam. 2020.
  • Nguyen Thi Thu Trang, Rilliard Albert, Tran Do Dat, and d’Alessandro Christophe. Prosodic phrasing modeling for Vietnamese TTS using syntactic information. In Proceedings of the 15th Conference of the International Speech Communication Association (Interspeech 2014), pages 2332–2336. Singapore. September 2014.
  • Nguyen Thi Thu Trang, Tran Do Dat, Rilliard Albert, Christophe D’Alessandro and Thi Ngoc Yen Pham. Intonation issues in HMM-based speech synthesis for Vietnamese. The 4th International Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU 2014). St. Petersburg, Russia. May 2014.
  • Nguyen Thi Thu Trang, Christophe D’Alessandro, Albert Rilliard, Tran Do Dat. HMM-based TTS for Hanoi Vietnamese: issues in design and evaluation. In Proceedings of the 14th Conference of the International Speech Communication Association (Interspeech 2013). Lyon, France. August 2013.
  • Nguyen Thi Thu Trang, Ninh-Thuan Truong, and Viet-Ha Nguyen. Verifying invariants of Java objects at runtime. International Journal IJSEKE, Vol. 21, No. 4, pp. 605-619, June 2011.
  • Anh-Hoang Truong, Nguyen Thi Thu Trang, Thanh-Binh Trinh, Dang Van Hung, Viet-Ha Nguyen, Pham Dinh Hung. Checking Interface Interaction Protocols Using Aspect-oriented Programming. IEEE International conference Software Engineering and Formal Methods (SEFM) 2008, No. SEFM.2008.32, pp 382-386, November 2008, Cape Town, South Africa.

Awards & Honours

  • National Golden Globe Award in ICT, 2009
  • Highest Prize at the Vietnamese Talent Awards 2018
  • VinTech Fund 2019
  • Best Female Founder Award at Startup Wheel 2020
  • Winner of Grab Venture Ignite 2020
  • First Prize at QVIC 2024.

Teaching

  • IT3100/IT3100E: Object-Oriented Programming
  • IT4549/IT4549E: ITSS Software Development
  • IT4490: Software Design and Construction
  • IT5424: Speech Generation

Current Projects

  • Speaker Recognition System for Smart Device Applications – Principal Investigator of a research project funded by the Ministry of Education and Training (MOET).