I am a Ph.D. candidate in linguistics at McGill university. My research interests lie in phonetics, laboratory phonology, and computational linguistics. I am interested in bridging speech technologies with human speech perception, with a focus on using automatic speech recognition (ASR) systems and large speech corpora as tools to understand human speech processing.

I am currently working on using deep neural networks to explore acoustic tone space in Mandarin Chinese (in prep), and using various ASR systems to investigate the minimal linguistic knowledges enabling a hypothesis-neutral listener to display perceptual effects of phonology (compensation for phonological assimilation) as humans. Before shifting to computational modelling, I worked on the general pattern and individual variability in perceiving multiple cues (involving breathy voice quality) for the tonal register contrast in Chinese Wu dialects.