Erik McDermott

According to our database, Erik McDermott authored at least 60 papers between 1989 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Variable Attention Masking for Configurable Transformer Transducer Speech Recognition.

Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang

Proceedings of the IEEE International Conference on Acoustics, 2023

Neural Transducer Training: Reduced Memory Consumption with Sample-Wise Computation.

Stefan Braun, Erik McDermott, Roger Hsiao

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation.

Thien Nguyen, Nathalie Tran, Liuhui Deng, Thiago Fraga da Silva, Matthew Radzihovsky, Roger Hsiao, Henry Mason, Stefan Braun, Erik McDermott, Dogan Can, Pawel Swietojanski, Lyan Verwimp, Sibel Oyman, Tresi Arvizo, Honza Silovsky, Arnab Ghoshal, Mathieu Martel, Bharat Ram Ambati, Mohamed Ali

CoRR, 2022

2020

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

Qian Zhang, Han Lu, Hasim Sak, Anshuman Tripathi, Erik McDermott, Stephen Koo, Shankar Kumar

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

A Density Ratio Approach to Language Model Fusion in End-to-End Automatic Speech Recognition.

Erik McDermott, Hasim Sak, Ehsan Variani

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Sampled Connectionist Temporal Classification.

Ehsan Variani, Tom Bagby, Kamel Lahouel, Erik McDermott, Michiel Bacchiani

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

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

Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani

Proceedings of the Interspeech 2017, 2017

Acoustic Modeling for Google Home.

Bo Li, Tara N. Sainath, Arun Narayanan, Joe Caroselli, Michiel Bacchiani, Ananya Misra, Izhak Shafran, Hasim Sak, Golan Pundak, Kean K. Chin, Khe Chai Sim, Ron J. Weiss, Kevin W. Wilson, Ehsan Variani, Chanwoo Kim, Olivier Siohan, Mitchel Weintraub, Erik McDermott, Richard Rose, Matt Shannon

Proceedings of the Interspeech 2017, 2017

2015

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

Ehsan Variani, Erik McDermott, Georg Heigold

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

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

Hasim Sak, Oriol Vinyals, Georg Heigold, Andrew W. Senior, Erik McDermott, Rajat Monga, Mark Z. Mao

Proceedings of the INTERSPEECH 2014, 2014

Asynchronous stochastic optimization for sequence training of deep neural networks: towards big data.

Erik McDermott, Georg Heigold, Pedro J. Moreno, Andrew W. Senior, Michiel Bacchiani

Proceedings of the INTERSPEECH 2014, 2014

Deep neural networks for small footprint text-dependent speaker verification.

Ehsan Variani, Xin Lei, Erik McDermott, Ignacio López-Moreno, Javier Gonzalez-Dominguez

Proceedings of the IEEE International Conference on Acoustics, 2014

Asynchronous stochastic optimization for sequence training of deep neural networks.

Georg Heigold, Erik McDermott, Vincent Vanhoucke, Andrew W. Senior, Michiel Bacchiani

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

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

Hank Liao, Erik McDermott, Andrew W. Senior

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

2012

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

Erik McDermott

Proceedings of the 2012 Symposium on Machine Learning in Speech and Language Processing, 2012

2010

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

Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura, Erik McDermott, Tetsunori Kobayashi

IEEE J. Sel. Top. Signal Process., 2010

Minimum Error Classification with geometric margin control.

Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe, Miho Ohsaki

Proceedings of the IEEE International Conference on Acoustics, 2010

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

Shinji Watanabe, Takaaki Hori, Erik McDermott, Atsushi Nakamura

Proceedings of the IEEE International Conference on Acoustics, 2010

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

Erik McDermott, Shinji Watanabe, Atsushi Nakamura

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

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

Erik McDermott, Shinji Watanabe, Atsushi Nakamura

Proceedings of the INTERSPEECH 2009, 2009

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

Atsushi Nakamura, Erik McDermott, Shinji Watanabe, Shigeru Katagiri

Proceedings of the IEEE International Conference on Acoustics, 2009

2008

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

Erik McDermott, Atsushi Nakamura

Proceedings of the INTERSPEECH 2008, 2008

2007

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

Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura, Shigeru Katagiri

IEEE Trans. Speech Audio Process., 2007

Inverting mappings from smooth paths through Rⁿ to paths through R^m: A technique applied to recovering articulation from acoustics.

John Hogden, Philip Rubin, Erik McDermott, Shigeru Katagiri, Louis Goldstein

Speech Commun., 2007

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

Erik McDermott, Atsushi Nakamura

Proceedings of the INTERSPEECH 2007, 2007

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

Timothy J. Hazen, Erik McDermott

Proceedings of the INTERSPEECH 2007, 2007

2006

Production-Oriented Models for Speech Recognition.

Erik McDermott, Atsushi Nakamura

IEICE Trans. Inf. Syst., 2006

Advanced computational models and learning theories for spoken language processing.

Atsushi Nakamura, Shinji Watanabe, Takaaki Hori, Erik McDermott, Shigeru Katagiri

IEEE Comput. Intell. Mag., 2006

Discriminative training via minimization of risk estimates based on Parzen smoothing.

Erik McDermott, Shigeru Katagiri

Appl. Intell., 2006

Training Conditional Random Fields with Multivariate Evaluation Measures.

Jun Suzuki, Erik McDermott, Hideki Isozaki

Proceedings of the ACL 2006, 2006

2005

Optimization methods for discriminative training.

Jonathan Le Roux, Erik McDermott

Proceedings of the INTERSPEECH 2005, 2005

Minimum Classification Error for Large Scale Speech Recognition Tasks using Weighted Finite State Transducers.

Erik McDermott, Shigeru Katagiri

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

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

Erik McDermott, Shigeru Katagiri

Comput. Speech Lang., 2004

A theoretical analysis of speech recognition based on feature trajectory models.

Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri

Proceedings of the INTERSPEECH 2004, 2004

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

Erik McDermott, Timothy J. Hazen

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003

Blind inversion of multidimensional functions for speech enhancement.

John Hogden, Patrick Valdez, Shigeru Katagiri, Erik McDermott

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Pervasive unsupervised adaptation for lecture speech transcription.

Daniel Willett, Thomas Niesler, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

Recognition method with parametric trajectory generated from mixture distribution HMMs.

Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

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

Erik McDermott, Shigeru Katagiri

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Minimum classification error via a Parzen window based estimate of the theoretical Bayes classification risk.

Erik McDermott, Shigeru Katagiri

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing, 2002

Classification error from the theoretical Bayes classification risk.

Erik McDermott, Shigeru Katagiri

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

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

Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri

Proceedings of the IEEE International Conference on Acoustics, 2002

2001

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

Alain Biem, Shigeru Katagiri, Erik McDermott, Biing-Hwang Juang

IEEE Trans. Speech Audio Process., 2001

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

Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

2000

Discriminative training for large vocabulary telephone-based name recognition.

Erik McDermott, Alain Biem, Seiichi Tenpaku, Shigeru Katagiri

Proceedings of the IEEE International Conference on Acoustics, 2000

1998

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

Reiko Akahane-Yamada, Erik McDermott, Takahiro Adachi, Hideki Kawahara, John S. Pruitt

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

1997

String-level MCE for continuous phoneme recognition.

Erik McDermott, Shigeru Katagiri

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Efficient normalization based upon GPD [generalized probabilistic descent].

Eric A. Woudenberg, Alain Biem, Erik McDermott, Shigeru Katagiri

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1996

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

Erik McDermott, Eric A. Woudenberg, Shigeru Katagiri

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

1995

A discriminative filter bank model for speech recognition.

Alain Biem, Erik McDermott, Shigeru Katagiri

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

1994

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

Erik McDermott, Shigeru Katagiri

Comput. Speech Lang., 1994

Prototype-based minimum error training for speech recognition.

Erik McDermott, Shigeru Katagiri

Appl. Intell., 1994

1993

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

Erik McDermott, Shigeru Katagiri

Proceedings of the IEEE International Conference on Acoustics, 1993

1992

Prototype-based discriminative training for various speech units.

Erik McDermott, Shigeru Katagiri

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

1991

LVQ-based shift-tolerant phoneme recognition.

Erik McDermott, Shigeru Katagiri

IEEE Trans. Signal Process., 1991

Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm.

Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott

Proceedings of the 1991 International Conference on Acoustics, 1991

1990

On the robustness of HMM and ANN speech recognition algorithms.

Yasuhiro Minami, Toshiyuki Hanazawa, Hitoshi Iwamida, Erik McDermott, Kiyohiro Shikano, Shigeru Katagiri, Masaona Kagawa

Proceedings of the First International Conference on Spoken Language Processing, 1990

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

Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott, Yoh'ichi Tohkura

Proceedings of the 1990 International Conference on Acoustics, 1990

1989

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

Erik McDermott, Shigeru Katagiri

Proceedings of the IEEE International Conference on Acoustics, 1989

A new algorithm for representing acoustic feature dynamics.

Shigeru Katagiri, Erik McDermott, Manami Yokota

Proceedings of the IEEE International Conference on Acoustics, 1989