Projects/Interests:
Development of NTT CS Labs SOLON speech recognition system
Discriminative Training for Speech Recognition
Speech Recognition using Articulatory Constraints
Some of my publications:
E. McDermott, S. Watanabe and A. Nakamura (2009): "Margin-Space Integration of MPE Loss via Differencing of MMI Functionals for Generalized Error-Weighted Discriminative Training", Proceedings of Interspeech 2009, 224-227 pdf
E. McDermott and A. Nakamura (2008): "Flexible discriminative training based on equal error group scores obtained from an error-indexed forward-backward algorithm", Proceedings of Interspeech 2008, 2398-2401 pdf
E. McDermott and A. Nakamura (2007): "String and Lattice based Discriminative Training for the Corpus of Spontaneous Japanese Lecture Transcription Task" pdf pdf Proceedings of Interspeech 2007.
E. McDermott, T.J. Hazen, J. Le Roux, A. Nakamura and S. Katagiri (2007): "Discriminative training for large vocabulary speech recognition using Minimum Classification Error" pdf IEEE Transactions on Audio, Speech and Language Processing Vol 15, No 1, January 2007 (Obligatory notice: This work is copyrighted by the IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.)
S. King, J. Frankel, K. Livescu, E. McDermott, K. Richmond, and M. Wester (2007): "Speech production knowledge in automatic speech recognition" pdf Journal of the Acoustical Society of America 121(2):723-742, February 2007.
A. Nakamura, S. Watanabe, T. Hori, E. McDermott and S. Katagiri (2006): "Advanced computational models and learning theories for spoken language processing" pdf IEEE Computational Intelligence Magazine, May 2006. (Obligatory notice: This work is copyrighted by the IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.)
E. McDermott and A. Nakamura (2006): "Production-oriented models for speech recognition" pdf IEICE Transactions, Special issue on Statistical Modeling for Speech Processing, Vol. E89D, No. 3, pp. 1006-1014, March 2006 (This work is copyrighted by the IEICE. Permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from IEICE)
E. McDermott and S. Katagiri (2006): "Discriminative Training via Minimization of Risk Estimates based on Parzen Smoothing", Journal of Applied Intelligence, Kluwer Academic Publishers, Vol. 25, No. 1, pp. 37-57, August 2006.
J. Le Roux and E. McDermott (2005): "Optimization methods for discriminative training" pdf Proceedings of Interspeech 2005
E. McDermott and S. Katagiri (2005): "Minimum Classification Error for Large Scale Speech Recognition Tasks using Weighted Finite State Transducers" pdf Proceedings of ICASSP 2005
E. McDermott and S. Katagiri (2004): "A Derivation of Minimum Classification Error from the Theoretical Classification Risk using Parzen Estimation", Computer Speech and Language, Vol. 18, pp. 107-122, 2004.
E. McDermott and T.J. Hazen (2004): "Minimum Classification Error Training of Landmark Models for Real-Time Continuous Speech Recognition" pdf Proc. ICASSP 2004
E. McDermott and S. Katagiri (2003): "A new formalization of Minimum Classification Error using a Parzen estimate of classification chance" pdf Proc. ICASSP 2003
E. McDermott and S. Katagiri (2002): "A Parzen window based derivation of Minimum Classification Error from the theoretical Bayes classification risk" pdf Proc. ICSLP 2002
E. McDermott, A. Biem, S. Tenpaku and S. Katagiri (2000): "Discriminative Training for Large Vocabulary Telephone-based Name
Recognition" postscript In Special Session
on Speech Recognition for Telecommunication Applications, ICASSP 2000
E. McDermott (2000): "Discriminative prototype-based methods for speech recognition." gzipped postscript.
In "Handbook of Neural Networks for Speech Processing", Artech House.
Copyright Artech House, 2000
E. McDermott (1997): "Discriminative Training for Speech Recognition" gzipped postscript (US letter) gzipped postscript (A4) Doctoral thesis, Waseda University, 1997