- A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System, APSIPA Trans., 2022
- Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder, Interspeech, 2021
- Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network, IEEE TASLP, 2021
- Quasi-Periodic WaveNet: An Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network, IEEE TASLP, 2021
- Quasi-Periodic parallel WaveGAN vocoder: a non-autoregressive pitch-dependent dilated convolution model for parametric speech generation, Interspeech, 2020
- A cyclical post-filtering approach to mismatch refinement of neural vocoder for text-to-speech systems, Interspeech, 2020
Research Experience
- Research Scientist, FAIR, Meta, NYC, US (Oct. 2023 - present)
- Research Scientist, Codec Avatars Lab, Meta, NYC, US (Jan. 2022 - Sep. 2023)
- System Designer, Realtek, Taiwan (Mar. 2012 - Oct. 2013)
- Research Assistant, National Chiao Tung University, Taiwan (Sep. 2009 - Dec. 2011), Advisors: Sin-Horng Chen, Yih-Ru Wang
Education
- Ph.D. (2021), Graduate School of Informatics, Nagoya University, Advisor: Tomoki Toda
- M.S. (2011), School of Communication Engineering, National Chiao Tung University, Advisors: Sin-Horng Chen, Yih-Ru Wang
- B.S. (2009), School of Communication Engineering, National Chiao Tung University
Background
Currently a research scientist at Meta FAIR. Research interests include speech generation applications based on machine learning methods, such as neural vocoders, voice conversion, speech enhancement, and speech bandwidth expansion.