Search Contact information
University of
Cambridge Home Department of Engineering
University of Cambridge > Engineering Department > Machine Intelligence Lab
Small Photo

Matt Gibson

Matt Gibson is a research associate in the Machine Intelligence Laboratory working on the EMIME (Effective Multilingual Interaction in Mobile Environments) project.

Biography

I graduated in 1994 from the University of Glasgow with Honours in Mathematics and Physics and in 1996 with an MSc in Mathematics and Foundations of Computer Science from Oxford University. In 2003, following seven years of research, development and education in the software industry I pursued an MPhil in Computer Speech, Text and Internet Technology at Cambridge University. I received a PhD in 2008 from Sheffield University, where I researched in the Speech and Hearing Group at the Department of Computer Science.

Publications

Journal articles

  • M. Gibson and T. Hain. Error approximation and minimum phone error acoustic model estimation. IEEE Transactions on Audio, Speech and Language Processing Vol.18, No.2 pp. 1269 - 1279 (August 2010)

  • M. Gibson and W. Byrne. Unsupervised intralingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. IEEE Transactions on Audio, Speech and Language Processing (in press).

    Conference proceedings

  • M. Gibson, T. Hirsimaki, R. Karhila, M. Kurimo and W. Byrne. Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. Proceedings ICASSP, Dallas, USA, March 2010.

  • M. Gibson. Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models. Proceedings Interspeech, Brighton, U.K., September 2009.

  • J Yamagishi, M. Lincoln, S. King, J. Dines, M. Gibson, J. Tian and Y. Guan. Analysis of unsupervised and noise-robust speaker-adaptive HMM-based speech synthesis systems toward a unified ASR and TTS framework. Proceedings Blizzard Challenge, Edinburgh, U.K., 2009.

  • M. Gibson and T. Hain. Temporal masking for unsupervised minimum Bayes risk speaker adaptation. Proceedings Interspeech, Antwerp, Belgium, August 2007.

  • M. Gibson and T. Hain. Hypothesis spaces for minimum Bayes risk training in large vocabulary speech recognition. Proceedings Interspeech, Pittsburgh, USA, September 2006.

    Theses

  • M. Gibson. Minimum Bayes risk acoustic model estimation and adaptation. PhD thesis, November 2008.

  • M. Gibson. Efficient maximum likelihood linear regression. MPhil thesis, July 2004.

    Contact Information

    © 2008 Cambridge University Engineering Dept
    Information provided by milab-maintainer