News

2017-0808: I started my Ph.D. at the University of Southern California in Los Angeles.
2017-0522: Our INTERSPEECH paper is accepted!
2017-0401: I'm currently visiting Nagoya University under the supervision of Professor Tomoki Toda.

About Me

My research interest is deep generative models and their applications to speech. I'm especially interested variational auto-encoders (VAE) and Generative Adversarial Nets (GANs). Before joining USC, I was a research assistant at the Academia Sinica in Taiwan. My advisors there were Dr. Hsin-Ming Wang and Dr. Yu Tsao. Before I became a full-time researcher in 2016, I was a software engineer at ASUS, working on text-to-speech (TTS) systems. If you're interested in my work, please contact me through email: jeremycchsu AT gmail DOT com

Tensorflow/Python

Deep/Machine Learning

Github

Speech/Signal Processing

Publications

Research/Work