研究兴趣为智能语音及语言处理、人机交互及机器学习。主要包括基于统计方法的语音识别及合成、说话人识别、自然语言处理、语义理解及对话管理、人机口语对话系统等。在国际一流期刊和会议上发表论文 80 余篇，在InterSpeech、IEEE Spoken Language Processing 等国际会议上获得多篇国际会议优秀论文奖，获得国际语音通讯联盟（ISCA）2013年颁发的2008-2012 Computer Speech and Language 最优论文奖。受邀担任InterSpeech2009/2014 语音识别及对话系统领域主席、EUSIPCO2011/2014 语音处理领域主席、ChinaSIP 2015语音领域主席等，任多个一流国际会议任组委会成员和多个一流国际会议和期刊的审稿人。
Speech & Language understanding and human computer interaction Large vocabulary continuous speech recognition Discriminative training of acoustic models Robust speech recognition Multilingual speech recognition and Low-resource speech recognition Deep learning based speech signal processing Multimedia Signal Processing GPU and SOC based fast speech recognition
My research interests are primarily concerned with the mechanism of speech processing: experimental phonetics, speech perception and production and articulatory acoustics. I'm particularly interested in the intersection of phonetics, computer science and neuroscience, for example prosody and its applilcations in speech technology, and manifestations in human brains. My previous research includes the perception and production of Cantonese lexical tones by speakers with different linguistic experiences, speech production by children with cochlear implants, quantative phonetic analysis of infant-directed speech etc. Lately I'm exploring subjective and objective evaluation of synthetic speech. I achieved my bachelor's degree from Beijing Normal University in 2011 and Ph.D. from the University of Melbourne in 2017.