Ye Bai (白烨)

[CV] [PhD Thesis]

I am currently a research scientist at Bytedance. We build speech understanding systems.

My research interests include speech recognition, language modeling, and keyword spotting. I am also interested in other applications and mechanisms of deep learning. My mid-term goal is to make machines better understand (or structuralize) multimedia data.

Before Bytedance, I was a speech engineer at Kuaishou Technology. We built large-scale automatic speech recognition systems to make billion-user applications, such as Kuaishou, Kwai, Kuaiying, better understand and display the content of short videos and live streaming.

Before Kuaishou, I obtained my Ph.D from Institute of Automation, Chinese Academy of Sciences (CASIA) in 2021. My advisor was Prof. Jianhua Tao. In 2016, I obtained my bachelor’s degree from China Agricultural University (CAU).