Luong Hieu-Thi

Affiliation and department：
Job title： Project Researcher
Homepage URL (1)： http://www.hieuthi.com

Research field (1)： Perceptual information processing

Research keywords (5)： Speech Recognition , Speech Synthesis , Natural Language Processing , Machine Learning , Speech Processing

Papers (13)：

Hieu-Thi Luong, Junichi Yamagishi. LaughNet: synthesizing laughter utterances from waveform silhouettes and a single laughter example. 2021
Hieu-Thi Luong, Junichi Yamagishi. Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance. 11th ISCA Speech Synthesis Workshop (SSW 11). 2021
Hieu-Thi Luong, Junichi Yamagishi. Latent linguistic embedding for cross-lingual text-to-speech and voice conversion. Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020. 2020. 150-154
Hieu-Thi Luong, Junichi Yamagishi. NAUTILUS: A Versatile Voice Cloning System. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2020. 28. 2967-2981
Hieu-Thi Luong, Junichi Yamagishi. Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech. 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). 2019. 200-207

ｍore...

Patents (1)：

Learning device, learning method, voice synthesis device, voice synthesis method and program

Lectures and oral presentations (2)：

Scaling and bias codes for modeling speaker-adaptive DNN-based speech synthesis systems
(SIG-SLP 126th meeting 2019)
Do prosodic manual annotations matter for Japanese speech synthesis systems with WaveNet vocoder?
(IEICE SP Workshop 2018)

Professional career (1)：

※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page