Hieu-Thi Luong
Email: contact (at) hieuthi.com
CV: pdf (Last updated: 2025-05-11)
I'm a researcher in Computational Speech and Language, with a Ph.D. in Interdisciplinary Sciences from SOKENDAI, Japan (2020). Currently, I serve as a Research Fellow at Nanyang Technological University, Singapore. My research centers on developing novel Speech and Language Processing Systems, including Automatic Speech Recognition, Generative AI, and Machine Learning. Right now, I'm particularly interested in Fake Speech Detection, as well as exploring AI applications in human-computer interaction and natural language processing.
I do programming and drawing as hobbies. More below.
For inquiries about research, technology, education, or something else, you can contact me via the email listed above.
Blog posts [read more]
Articles written in English
⅓ espresso [read more]
Fleeting notes written in Vietnamese
Selected publications
LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation
Hieu-Thi Luong, Haoyang Li, Lin Zhang, Kong Aik Lee, Eng Siong Chng
ICASSP 2025
2025
Room Impulse Responses help attackers to evade Deep Fake Detection
Hieu-Thi Luong, Duc-Tuan Truong, Kong Aik Lee, Eng Siong Chng
SLT 2024
2024
Controlling Multi-Class Human Vocalization Generation via a Simple Segment-based Labeling Scheme
Hieu-Thi Luong, Junichi Yamagishi
Interspeech 2023
2023
2022
LaughNet: synthesizing laughter utterances from waveform silhouettes and a single laughter example
Hieu-Thi Luong, Junichi Yamagishi
arXiv manuscript
Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance
Hieu-Thi Luong, Junichi Yamagishi
Speech Synthesis Workshop 2021 (SSW11)
2021
Latent linguistic embedding for cross-lingual text-to-speech and voice conversion
Hieu-Thi Luong, Junichi Yamagishi
VCC2020 Workshop
Deep learning based voice cloning framework for a unified system of text-to-speech and voice conversion (Ph.D. thesis)
Hieu-Thi Luong
Ph.D. thesis, 2020
NAUTILUS: a Versatile Voice Cloning System
Hieu-Thi Luong, Junichi Yamagishi
IEEE/ACM Transactions on Audio, Speech, and Language Processing
2020
Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech
Hieu-Thi Luong, Junichi Yamagishi
ASRU 2019
A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation
Hieu-Thi Luong, Junichi Yamagishi
arXiv manuscript
Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Interspeech 2019
2019
Scaling and bias codes for modeling speaker-adaptive DNN-based speech synthesis systems
Hieu-Thi Luong, Junichi Yamagishi
SLT 2018
Multimodal Speech Synthesis Architecture for Unsupervised Speaker Adaptation
Hieu-Thi Luong, Junichi Yamagishi
Interspeech 2018
Investigating accuracy of pitch-accent annotations in neural network-based speech synthesis and denoising effects
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Interspeech 2018
2018
Adapting and Controlling DNN-based Speech Synthesis using Input Codes
Hieu-Thi Luong, Shinji Takaki, Gustav Eje Henter, Junichi Yamagishi
ICASSP 2017
2017
A non-expert Kaldi recipe for Vietnamese Speech Recognition System
Hieu-Thi Luong, Hai-Quan Vu
WLSI-OIAF4HLT 2016
2016
Others
Patents
Learning device, learning method, voice synthesis device, voice synthesis method and program
Inventor: Hieu-Thi Luong, Junichi Yamagishi
P7109071 · Issued Jul 29, 2022
Side projects
Vo
Vocabulary
Utility extracts vocabulary from text for learning English. Present in printer-friendly format