Hieu-Thi Luong

Email: contact (at) hieuthi.com

CV: pdf (Last update: January 2020)

I have been a PhD candidate at Sokendai/National Institute of Informatics, Tokyo, Japan since 2017. My study mainly involves Speech Synthesis and Speech Recognition. I'm interested in Speech Processing, Machine Learning and Natural Language Processing in general.

I also do programming and drawing as hobbies. More below.

Blog posts [read more]

Selected publications

Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech

Hieu-Thi Luong, Junichi Yamagishi

ASRU 2019

Samples Poster Preprint

A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation

Hieu-Thi Luong, Junichi Yamagishi

arXiv manuscript

Samples Preprint

Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora

Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa

Interspeech 2019

Samples Preprint


Scaling and bias codes for modeling speaker-adaptive DNN-based speech synthesis systems

Hieu-Thi Luong, Junichi Yamagishi

SLT 2018

Samples Poster Preprint

Multimodal Speech Synthesis Architecture for Unsupervised Speaker Adaptation

Hieu-Thi Luong, Junichi Yamagishi

Interspeech 2018

Samples Poster Preprint

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



Adapting and Controlling DNN-based Speech Synthesis using Input Codes

Hieu-Thi Luong, Shinji Takaki, Gustav Eje Henter, Junichi Yamagishi


Samples Preprint


A non-expert Kaldi recipe for Vietnamese Speech Recognition System

Hieu-Thi Luong, Hai-Quan Vu


Corpus Preprint



I'm drawing and sketching in free time. Find me on Instagram

Side projects


Pixels Touch

Android drawing application optimized for pixel art and touch screen devices


Meteor Puppy

A parody game of Nyan Cat on Android. Developing using Unity game engine




Utility extracts vocabulary from text for learning English. Present in printer-friendly format