I currently study in KAIST EE as a Master student.
From March 2023, I work at Multimodal AI Lab under the supervision of Prof. Joon Son Chung.
I am now working on TTS, audio generation, and interest in modern generative models. If you are seeking any form of academic cooperation, please feel free to email me at tandat.kaist@kaist.ac.kr.
In 2022, I graduated from Department of Computer Science and Engineering, Ho Chi Minh University of Technology - Vietnam National University with a bachelorβs degree of Computer Science advised by Dr. Duc Dung Nguyen.
π₯ News
- 2023.11: Β ππ One paper is accepted by ICASSP 2024
π Publications
π Speech Synthesis
FreGrad: Lightweight and fast frequency-aware diffusion vocoder
Tan Dat Nguyen* , Ji-Hoon Kim*, Youngjoon Jang, Jaehun Kim, Joon Son Chung+ Demo page, Official Code ( Oral Presentation )
- We employ discrete wavelet transform that helps FreGrad to operate on a simple and concise feature space.
- We design a frequency-aware dilated convolution and introduce a bag of tricks that boosts the generation quality of the proposed model.
Calib-StyleSpeech: A Zero-shot Approach In Voice Cloning Of High Adaptive Text To Speech System With Imbalanced Dataset ( Oral Presentation )
Nguyen Tan Dat, Lam Quang Tuong, Nguyen Duc Dung
- We propose to use CLUB to minimize the mutual information between content embedding and style embedding.
- Our work well-perform on zero-shot scenerio even when using skew ASR dataset
A Linguistic-based Transfer Learning Approach for Low-resource Bahnar Text-to-Speech ( Oral Presentation )
Tan Dat Nguyen, Quang Tuong Lam, Duc Hao Do, Huu Thuc Cai, Hoang Suong Nguyen, Thanh Hung Vo, Duc Dung Nguyen.
- We apply phonetic-based transfer learning approach to create Bahnar-Kriem (very low resource language) TTS model.
π» Other Research Papers
π§βπ¨ Low-resource TTS
FICC 2022
Instance-Based Transfer Learning Approach for Vietnamese Speech Synthesis with Very Low Resource, Tuong Q. Lam, Dung D. Nguyen, Dat T. Nguyen, Han K. Lam, Thuc H. Cai, Suong N. Hoang, Hao D. Do.RIVF 2021
[CNN-based Vietnamese Speech synthesis with limited dataset]. Lam Quang Tuong, Nguyen Tan Dat, Lam Kha Han, Do Duc Hao.RIVF 2021
[Instanced-based Transfer Learning for Vietnamese Speech Synthesis]. Lam Quang Tuong, Nguyen Tan Dat, Do Duc Hao.
π Honors and Awards
- 2023.03 KAIST Scholarship (Full tuition and fees)
- 2022.10 Certificate of Merit for students with high achievements in academic competitions and scientific research
- 2022.12 First prize in the poster competition of the technical festival 2021-2022
- 2018.08 Vallet scholarships
- 2018.01 Third prize, Vietnam Mathematical Olympiad (VMO 2018)
- 2017.04 Silver medal, Mathematical oplimpiad 30/04
- 2016.04 Bronze medal, Mathematical oplimpiad 30/04
- 2016.01 Third prize, Hanoi open mathematical oplimpiad
π Educations
- 2023.03 - Present, Master, Korea Advanced Institute of Science and Technology. Daejeon, KAIST. (Current GPA: 3.75)
- 2018.10 - 2022.10, Undergraduate, Ho Chi Minh University of Technology - Vietnam National University. Ho Chi Minh city, Vietnam. (Thesis grade: 9.8/10)
- 2015.08 - 2018.08, Nguyen Chi Thanh high school for gifted. Dak Nong, Vietnam
π» Internships
- 2021.06 - 2021.09, OLLI Technology Corp., Vietnam.
If you like the template of this homepage, please go to AcadHomepage . Thank YiRen for providing a clean yet beautiful template.