Erik McDermott

发表

Prototype-based MCE/GPD training for word spotting and connected word recognition

Shigeru Katagiri, Erik McDermott, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Mitch Weintraub, Tara N. Sainath, Arun Narayanan, 2017, INTERSPEECH.

Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training

Shinji Watanabe, Atsushi Nakamura, Erik McDermott, 2009, INTERSPEECH.

A theoretical analysis of speech recognition based on feature trajectory models

Shigeru Katagiri, Atsushi Nakamura, Erik McDermott, 2004, INTERSPEECH.

Discriminative Training for Speech Recognition

Erik McDermott, E. McDermott, 1997 .

String-level MCE for continuous phoneme recognition

Shigeru Katagiri, Erik McDermott, 1997, EUROSPEECH.

A discriminative filter bank model for speech recognition

Alain Biem, Shigeru Katagiri, Erik McDermott, 1995, EUROSPEECH.

Sequence discriminative distributed training of long short-term memory recurrent neural networks

Georg Heigold, Oriol Vinyals, Erik McDermott, 2014, INTERSPEECH.

A Kernel Machine Derived by Minimum Relative Entropy Discrimination For Automatic Speech Recognition

Tetsunori Kobayashi, Shinji Watanabe, Atsushi Nakamura, 2009 .

Sampled Connectionist Temporal Classification

Tom Bagby, Michiel Bacchiani, Erik McDermott, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Prototype-based minimum error training for speech recognition

Shigeru Katagiri, Erik McDermott, E. McDermott, 1994, Applied Intelligence.

A Sequential Pattern Classifier Based on Hidden Markov Kernel Machine and Its Application to Phoneme Classification

Tetsunori Kobayashi, Shinji Watanabe, Atsushi Nakamura, 2010, IEEE Journal of Selected Topics in Signal Processing.

Optimization methods for discriminative training

Jonathan Le Roux, Erik McDermott, 2005, INTERSPEECH.

Discriminative training via minimization of risk estimates based on Parzen smoothing

Shigeru Katagiri, Erik McDermott, E. McDermott, 2006, Applied Intelligence.

Classification error from the theoretical Bayes classification risk

Shigeru Katagiri, Erik McDermott, 2002, INTERSPEECH.

Prototype-based minimum classification error/generalized probabilistic descent training for various speech units

Shigeru Katagiri, Erik McDermott, E. McDermott, 1994, Comput. Speech Lang..

An application of discriminative feature extraction to filter-bank-based speech recognition

Biing-Hwang Juang, Alain Biem, Shigeru Katagiri, 2001, IEEE Trans. Speech Audio Process..

Efficient normalization based upon GPD [generalized probabilistic descent]

Alain Biem, Shigeru Katagiri, Erik McDermott, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Speech recognition using HMMs with an LVQ‐trained codebook

Shigeru Katagiri, Erik McDermott, Hitoshi Iwamida, 1989 .

A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture

Georg Heigold, Erik McDermott, Ehsan Variani, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Blind inversion of multidimensional functions for speech enhancement

Shigeru Katagiri, Erik McDermott, John Hogden, 2003, INTERSPEECH.

A unified view for discriminative objective functions based on negative exponential of difference measure between strings

Shigeru Katagiri, Shinji Watanabe, Atsushi Nakamura, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Asynchronous stochastic optimization for sequence training of deep neural networks

Georg Heigold, Michiel Bacchiani, Erik McDermott, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss

Qian Zhang, Erik McDermott, Hasim Sak, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A derivation of minimum classification error from the theoretical classification risk using Parzen estimation

Shigeru Katagiri, Erik McDermott, 2004, Comput. Speech Lang..

A telephone-based directory assistance system adaptively trained using minimum classification error/generalized probabilistic descent

Shigeru Katagiri, Erik McDermott, Eric A. Woudenberg, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

A hybrid speech recognition system using HMMs with an LVQ-trained codebook

Shigeru Katagiri, Erik McDermott, Hitoshi Iwamida, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Large Vocabulary Continuous Speech Recognition with Long Short-Term Recurrent Networks

Georg Heigold, Oriol Vinyals, Erik McDermott, 2014 .

Deep neural networks for small footprint text-dependent speaker verification

Erik McDermott, Xin Lei, Ehsan Variani, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Production-Oriented Models for Speech Recognition

Atsushi Nakamura, Erik McDermott, E. McDermott, 2006, IEICE Trans. Inf. Syst..

On the robustness of HMM and ANN speech recognition algorithms

Shigeru Katagiri, Kiyohiro Shikano, Erik McDermott, 1990, ICSLP.

A recognition method with parametric trajectory synthesized using direct relations between static and dynamic feature vector time series

Shigeru Katagiri, Atsushi Nakamura, Erik McDermott, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Time and memory efficient viterbi decoding for LVCSR using a precompiled search network

Shigeru Katagiri, Erik McDermott, Daniel Willett, 2001, INTERSPEECH.

An integrated framework for "margin" based sequential discriminative training over lattices based on differenced maximum mutual information (dMMI)

Erik McDermott, 2012, MLSLP.

Minimum classification error training of landmark models for real-time continuous speech recognition

Erik McDermott, Timothy J. Hazen, E. McDermott, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A Deep Generative Acoustic Model for Compositional Automatic Speech Recognition

Erik McDermott, E. McDermott, 2018 .

A new formalization of minimum classification error using a Parzen estimate of classification chance

Shigeru Katagiri, Erik McDermott, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Minimum classification error for large scale speech recognition tasks using weighted finite state transducers

Shigeru Katagiri, Erik McDermott, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Pervasive unsupervised adaptation for lecture speech transcription

Shigeru Katagiri, Thomas Niesler, Erik McDermott, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Smoothed language model incorporation for efficient time-synchronous beam search decoding in LVCSR

Shigeru Katagiri, Erik McDermott, Daniel Willett, 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

Flexible discriminative training based on equal error group scores obtained from an error-indexed forward-backward algorithm

Atsushi Nakamura, Erik McDermott, 2008, INTERSPEECH.

Computer-based second language production training by using spectrographic representation and HMM-based speech recognition scores

Hideki Kawahara, Erik McDermott, John S. Pruitt, 1998, ICSLP.

Training Conditional Random Fields with Multivariate Evaluation Measures

Jun Suzuki, Erik McDermott, Hideki Isozaki, 2006, ACL.

Speech production knowledge in automatic speech recognition.

Simon King, Karen Livescu, Erik McDermott, 2007, The Journal of the Acoustical Society of America.

Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error

Jonathan Le Roux, Shigeru Katagiri, Atsushi Nakamura, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Discriminative MCE-based speaker adaptation of acoustic models for a spoken lecture processing task

Erik McDermott, Timothy J. Hazen, E. McDermott, 2007, INTERSPEECH.

A discriminative model for continuous speech recognition based on Weighted Finite State Transducers

Shinji Watanabe, Atsushi Nakamura, Takaaki Hori, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

LVQ-based shift-tolerant phoneme recognition

Shigeru Katagiri, Erik McDermott, 1991, IEEE Trans. Signal Process..

Inverting mappings from smooth paths through Rn to paths through Rm: A technique applied to recovering articulation from acoustics

Shigeru Katagiri, Louis Goldstein, Philip Rubin, 2007, Speech Commun..

Discriminative training for large vocabulary telephone-based name recognition

Alain Biem, Shigeru Katagiri, Erik McDermott, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

Discriminative training based on an integrated view of MPE and MMI in margin and error space

Shinji Watanabe, Atsushi Nakamura, Erik McDermott, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow

Tom Bagby, Michiel Bacchiani, Erik McDermott, 2017, INTERSPEECH.

Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2

Shigeru Katagiri, Erik McDermott, E. McDermott, 1989, International Conference on Acoustics, Speech, and Signal Processing,.

Prototype-based discriminative training for various speech units

Shigeru Katagiri, Erik McDermott, E. McDermott, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

String and lattice based discriminative training for the corpus of spontaneous Japanese lecture transcription task

Atsushi Nakamura, Erik McDermott, 2007, INTERSPEECH.

Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription

Hank Liao, Erik McDermott, Andrew W. Senior, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Minimum Error Classification with geometric margin control

Shigeru Katagiri, Shinji Watanabe, Atsushi Nakamura, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

A RECOGNITION METHOD USING SYNTHESIS-BASED SCORING THAT INCORPORATES DIRECT RELATIONS BETWEEN STATIC AND DYNAMIC FEATURE VECTOR TIME SERIES

Shigeru Katagiri, Atsushi Nakamura, Erik McDermott, 2001 .