A (possibly outdated) list of all my publications is available. If you
want a postscript copy of any of these papers contact me by email mjfg@eng.cam.ac.uk.
Some presentations are also available
online.
T. Hain, P.C. Woodland, G. Evermann, M.J.F. Gales, D. Povey, G. Moore, L. Wang and X. Liu (2005).
Automatic Transcription of Conversational Telephone Speech.
IEEE Transactions on Speech and Audio Processing, November 2005.
M.J.F. Gales and M.I. Layton (2006).
Training Augmented Models using SVMs.
IEICE Special Issue on Statistical Models for Speech Recognition, March 2006.
K.C. Sim and M.J.F. Gales (2005).
Adaptation of Precision Matrix Models on LVCSR.
ICASSP05.
D.Y. Kim, H.Y. Chan,G. Evermann, M.J.F. Gales, D. Mrva, K.C. Sim and P.C. Woodland (2005).
Development of the CU-HTK 2004 Broadcast News Transcription Systems.
ICASSP05.
X. Liu, M.J.F. Gales, K.C. Sim and K. Yu (2005).
Investigation of Acoustic Modelling Techniques for LVCSR Systems.
ICASSP05.
G. Evermann, M.J.F. Gales, B. Jia, D. Mrva, P.C. Woodland and K. Yu (2005).
Training LVCSR Systems on Thousands of Hours of Data.
ICASSP05.
M.J.F. Gales (2007).
Discriminative Models for Speech Recognition.
Information Theory and Applications Workshop, UCSD, California, USA.
A related invited paper is also available. An
extended
version of this paper (revised May 2007), which includes a longer discussion of large margin training of HMMs
and some typo corrections, is also available.