Erik McDermott

70 papers A* 1A 13C 2Misc 21Journal 20Unranked 13

Year	Rank	Type	Title / Venue / Authors
2025	Misc	`conf`	Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition. ICASSP Takaaki Hori, Martin Kocour, Adnan Haider, Erik McDermott, Xiaodan Zhuang
2025	J	`jnl`	Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition. CoRR Takaaki Hori, Martin Kocour, Adnan Haider, Erik McDermott, Xiaodan Zhuang
2024	J	`jnl`	Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition. CoRR Zijin Gu, Tatiana Likhomanenko, He Bai, Erik McDermott, Ronan Collobert, Navdeep Jaitly
2024	J	`jnl`	Focused Discriminative Training For Streaming CTC-Trained Automatic Speech Recognition Models. CoRR Adnan Haider, Xingyu Na, Erik McDermott, Tim Ng, Zhen Huang, Xiaodan Zhuang
2024	—	`conf`	Optimizing Byte-Level Representation For End-To-End ASR. SLT Roger Hsiao, Liuhui Deng, Erik McDermott, Ruchir Travadi, Xiaodan Zhuang
2024	J	`jnl`	Optimizing Byte-level Representation for End-to-end ASR. CoRR Roger Hsiao, Liuhui Deng, Erik McDermott, Ruchir Travadi, Xiaodan Zhuang
2023	Misc	`conf`	Neural Transducer Training: Reduced Memory Consumption with Sample-Wise Computation. ICASSP Stefan Braun, Erik McDermott, Roger Hsiao
2023	Misc	`conf`	Variable Attention Masking for Configurable Transformer Transducer Speech Recognition. ICASSP 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
2022	J	`jnl`	Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation. CoRR Stefan Braun, Erik McDermott, Roger Hsiao
2022	J	`jnl`	Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation. CoRR 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
2022	J	`jnl`	Variable Attention Masking for Configurable Transformer Transducer Speech Recognition. CoRR 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
2020	J	`jnl`	A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition. CoRR Erik McDermott, Hasim Sak, Ehsan Variani
2020	Misc	`conf`	Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss. ICASSP Qian Zhang, Han Lu, Hasim Sak, Anshuman Tripathi, Erik McDermott, Stephen Koo, Shankar Kumar
2020	J	`jnl`	Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss. CoRR Qian Zhang, Han Lu, Hasim Sak, Anshuman Tripathi, Erik McDermott, Stephen Koo, Shankar Kumar
2019	C	`conf`	A Density Ratio Approach to Language Model Fusion in End-to-End Automatic Speech Recognition. ASRU Erik McDermott, Hasim Sak, Ehsan Variani
2018	Misc	`conf`	Sampled Connectionist Temporal Classification. ICASSP Ehsan Variani, Tom Bagby, Kamel Lahouel, Erik McDermott, Michiel Bacchiani
2017	A	`conf`	Acoustic Modeling for Google Home. INTERSPEECH 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
2017	A	`conf`	End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow. INTERSPEECH Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani
2015	Misc	`conf`	A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture. ICASSP Ehsan Variani, Erik McDermott, Georg Heigold
2014	Misc	`conf`	Asynchronous stochastic optimization for sequence training of deep neural networks. ICASSP Georg Heigold, Erik McDermott, Vincent Vanhoucke, Andrew W. Senior, Michiel Bacchiani
2014	A	`conf`	Asynchronous stochastic optimization for sequence training of deep neural networks: towards big data. INTERSPEECH Erik McDermott, Georg Heigold, Pedro J. Moreno, Andrew W. Senior, Michiel Bacchiani
2014	Misc	`conf`	Deep neural networks for small footprint text-dependent speaker verification. ICASSP Ehsan Variani, Xin Lei, Erik McDermott, Ignacio López-Moreno, Javier Gonzalez-Dominguez
2014	A	`conf`	Sequence discriminative distributed training of long short-term memory recurrent neural networks. INTERSPEECH Hasim Sak, Oriol Vinyals, Georg Heigold, Andrew W. Senior, Erik McDermott, Rajat Monga, Mark Z. Mao
2013	C	`conf`	Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription. ASRU Hank Liao, Erik McDermott, Andrew W. Senior
2012	—	`conf`	An integrated framework for "margin" based sequential discriminative training over lattices based on differenced maximum mutual information (dMMI). MLSLP Erik McDermott
2010	J	`jnl`	A Sequential Pattern Classifier Based on Hidden Markov Kernel Machine and Its Application to Phoneme Classification. IEEE J. Sel. Top. Signal Process. Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura, Erik McDermott, Tetsunori Kobayashi
2010	Misc	`conf`	A discriminative model for continuous speech recognition based on Weighted Finite State Transducers. ICASSP Shinji Watanabe, Takaaki Hori, Erik McDermott, Atsushi Nakamura
2010	Misc	`conf`	Discriminative training based on an integrated view of MPE and MMI in margin and error space. ICASSP Erik McDermott, Shinji Watanabe, Atsushi Nakamura
2010	Misc	`conf`	Minimum Error Classification with geometric margin control. ICASSP Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe, Miho Ohsaki
2009	Misc	`conf`	A unified view for discriminative objective functions based on negative exponential of difference measure between strings. ICASSP Atsushi Nakamura, Erik McDermott, Shinji Watanabe, Shigeru Katagiri
2009	A	`conf`	Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training. INTERSPEECH Erik McDermott, Shinji Watanabe, Atsushi Nakamura
2008	A	`conf`	Flexible discriminative training based on equal error group scores obtained from an error-indexed forward-backward algorithm. INTERSPEECH Erik McDermott, Atsushi Nakamura
2007	A	`conf`	Discriminative MCE-based speaker adaptation of acoustic models for a spoken lecture processing task. INTERSPEECH Timothy J. Hazen, Erik McDermott
2007	J	`jnl`	Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error. IEEE Trans. Speech Audio Process. Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura, Shigeru Katagiri
2007	J	`jnl`	Inverting mappings from smooth paths through R Speech Commun. John Hogden, Philip Rubin, Erik McDermott, Shigeru Katagiri, Louis Goldstein
2007	A	`conf`	String and lattice based discriminative training for the corpus of spontaneous Japanese lecture transcription task. INTERSPEECH Erik McDermott, Atsushi Nakamura
2006	J	`jnl`	Advanced computational models and learning theories for spoken language processing. IEEE Comput. Intell. Mag. Atsushi Nakamura, Shinji Watanabe, Takaaki Hori, Erik McDermott, Shigeru Katagiri
2006	J	`jnl`	Discriminative training via minimization of risk estimates based on Parzen smoothing. Appl. Intell. Erik McDermott, Shigeru Katagiri
2006	J	`jnl`	Production-Oriented Models for Speech Recognition. IEICE Trans. Inf. Syst. Erik McDermott, Atsushi Nakamura
2006	A*	`conf`	Training Conditional Random Fields with Multivariate Evaluation Measures. ACL Jun Suzuki, Erik McDermott, Hideki Isozaki
2005	—	`conf`	Minimum Classification Error for Large Scale Speech Recognition Tasks using Weighted Finite State Transducers. ICASSP (1) Erik McDermott, Shigeru Katagiri
2005	A	`conf`	Optimization methods for discriminative training. INTERSPEECH Jonathan Le Roux, Erik McDermott
2004	J	`jnl`	A derivation of minimum classification error from the theoretical classification risk using Parzen estimation. Comput. Speech Lang. Erik McDermott, Shigeru Katagiri
2004	A	`conf`	A theoretical analysis of speech recognition based on feature trajectory models. INTERSPEECH Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri
2004	—	`conf`	Minimum classification error training of landmark models for real-time continuous speech recognition. ICASSP (1) Erik McDermott, Timothy J. Hazen
2003	—	`conf`	A new formalization of minimum classification error using a Parzen estimate of classification chance. ICASSP (2) Erik McDermott, Shigeru Katagiri
2003	A	`conf`	Blind inversion of multidimensional functions for speech enhancement. INTERSPEECH John Hogden, Patrick Valdez, Shigeru Katagiri, Erik McDermott
2003	—	`conf`	Pervasive unsupervised adaptation for lecture speech transcription. ICASSP (1) Daniel Willett, Thomas Niesler, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri
2003	—	`conf`	Recognition method with parametric trajectory generated from mixture distribution HMMs. ICASSP (1) Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri
2002	Misc	`conf`	A recognition method with parametric trajectory synthesized using direct relations between static and dynamic feature vector time series. ICASSP Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri
2002	A	`conf`	Classification error from the theoretical Bayes classification risk. INTERSPEECH Erik McDermott, Shigeru Katagiri
2002	—	`conf`	Minimum classification error via a Parzen window based estimate of the theoretical Bayes classification risk. NNSP Erik McDermott, Shigeru Katagiri
2001	J	`jnl`	An application of discriminative feature extraction to filter-bank-based speech recognition. IEEE Trans. Speech Audio Process. Alain Biem, Shigeru Katagiri, Erik McDermott, Biing-Hwang Juang
2001	A	`conf`	Time and memory efficient viterbi decoding for LVCSR using a precompiled search network. INTERSPEECH Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri
2000	Misc	`conf`	Discriminative training for large vocabulary telephone-based name recognition. ICASSP Erik McDermott, Alain Biem, Seiichi Tenpaku, Shigeru Katagiri
1998	—	`conf`	Computer-based second language production training by using spectrographic representation and HMM-based speech recognition scores. ICSLP Reiko Akahane-Yamada, Erik McDermott, Takahiro Adachi, Hideki Kawahara, John S. Pruitt
1997	Misc	`conf`	Efficient normalization based upon GPD [generalized probabilistic descent]. ICASSP Eric A. Woudenberg, Alain Biem, Erik McDermott, Shigeru Katagiri
1997	—	`conf`	String-level MCE for continuous phoneme recognition. EUROSPEECH Erik McDermott, Shigeru Katagiri
1996	Misc	`conf`	A telephone-based directory assistance system adaptively trained using minimum classification error/generalized probabilistic descent. ICASSP Erik McDermott, Eric A. Woudenberg, Shigeru Katagiri
1995	—	`conf`	A discriminative filter bank model for speech recognition. EUROSPEECH Alain Biem, Erik McDermott, Shigeru Katagiri
1994	J	`jnl`	Prototype-based minimum classification error/generalized probabilistic descent training for various speech units. Comput. Speech Lang. Erik McDermott, Shigeru Katagiri
1994	J	`jnl`	Prototype-based minimum error training for speech recognition. Appl. Intell. Erik McDermott, Shigeru Katagiri
1993	—	`conf`	Prototype-based MCE/GPD training for word spotting and connected word recognition. ICASSP (2) Erik McDermott, Shigeru Katagiri
1992	Misc	`conf`	Prototype-based discriminative training for various speech units. ICASSP Erik McDermott, Shigeru Katagiri
1991	J	`jnl`	LVQ-based shift-tolerant phoneme recognition. IEEE Trans. Signal Process. Erik McDermott, Shigeru Katagiri
1991	Misc	`conf`	Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm. ICASSP Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott
1990	Misc	`conf`	A hybrid speech recognition system using HMMs with an LVQ-trained codebook. ICASSP Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott, Yoh'ichi Tohkura
1990	—	`conf`	On the robustness of HMM and ANN speech recognition algorithms. ICSLP Yasuhiro Minami, Toshiyuki Hanazawa, Hitoshi Iwamida, Erik McDermott, Kiyohiro Shikano, Shigeru Katagiri, Masaona Kagawa
1989	Misc	`conf`	A new algorithm for representing acoustic feature dynamics. ICASSP Shigeru Katagiri, Erik McDermott, Manami Yokota
1989	Misc	`conf`	Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2. ICASSP Erik McDermott, Shigeru Katagiri