Hank Liao

Hank Liao is a researcher in the speech recognition group with interests in acoustic modeling and large vocabulary speech recognition. Hank Liao obtained a BASc in Systems Design Engineering from the University of Waterloo in 1999. In 2002 he completed an MPhil from the University of Cambridge. In 2007 he submitted his dissertation on "Uncertainty Decoding for Noise Robust Speech Recognition" to the Cambridge University Engineering Department, supervised by Dr. Mark Gales, and sponsored by Toshiba Research Europe. He has published research on and deployed automatic captioning of YouTube videos, Google Voice's voicemail transcription, and Voice Search speech recognition systems.

Google Publications

Previous Publications

  •   

    Issues with uncertainty decoding for noise robust automatic speech recognition

    Hank Liao, M.J.F. Gales

    Speech Communication, vol. 50 (2008), pp. 265-277

  •   

    Adaptive Training with Joint Uncertainty Decoding for Robust Recognition of Noise Data

    Hank Liao, M.J.F. Gales

    ICASSP (2007)

  •   

    Uncertainty Decoding for Noise Robust Speech Recognition

    Hank Liao

    Ph.D. Thesis, University of Cambridge (2007)

  •   

    Issues with Uncertainty Decoding for Noise Robust Speech Recognition

    Hank Liao, M.J.F. Gales

    University of Cambridge (2006)

  •   

    Issues with Uncertainty Decoding for Noise Robust Speech Recognition. In Proc. Interspeech

    Hank Liao, M.J.F. Gales

    Interspeech (2006)

  •   

    Joint Uncertainty Decoding for Robust Large Vocabulary Speech Recognition

    Hank Liao, M.J.F. Gales

    University of Cambridge (2006)

  •   

    Joint Uncertainty Decoding for Noise Robust Speech Recognition. In Proc. Interspeech

    Hank Liao, M.J.F. Gales

    Interspeech (2005)

  •   

    Uncertainty Decoding for Noise Robust Speech Recognition

    Hank Liao, M.J.F. Gales

    University of Cambridge (2004)