Hao Tang received his B.S. in Computer Science and M.S. in Electrical Engineering from National Taiwan University in 2007 and 2010, respectively. He completed his Ph.D. at Toyota Technological Institute at Chicago in 2017, and is now a Postdoctoral Associate at MIT in the Spoken Language Systems group. His interests include machine learning and its application to speech and language processing. He has worked on discriminative training and end-to-end neural segmental models for speech and American Sign Language recognition, and is now exploring unsupervised approaches for robust speech recognition.




Automatic Speech Recognition

Automatic speech recognition (ASR) has been a grand challenge machine learning problem for decades. Our ongoing research in this area examines the use of deep learning models for distant and noisy recording conditions, multilingual, and low-resource scenarios.