I am a research engineer on the Facebook AI Research (FAIR) team working on speech recognition. I currently work on language modeling and beam-search decoding as well as developing open-source toolkits — Wav2Letter and Flashlight. Before joining FAIR, I graduated from Cornell University with a master’s degree in computer science and prior to that, I received my bachelor’s degree from Peking University in artificial intelligence.

Interests

Machine learning, speech recognition, natural language processing, representation learning, metric learning

Latest Publications