Erik McDermott

3.5k citations

67 papers · 2.2k · 2 hit papers · h-index 20

Impact in

Signal Processing top 0.2%
- Speech and Audio Processing
- Music and Audio Processing
Artificial Intelligence top 0.5%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Neural Networks and Applications
- Speech and dialogue systems

Papers in

Artificial Intelligence 58
- Speech Recognition and Synthesis 49
- Neural Networks and Applications 14
- Natural Language Processing Techniques 10
- Topic Modeling 7
- Speech and dialogue systems 6
Signal Processing 40
- Speech and Audio Processing 34
- Music and Audio Processing 21

Co-authors: Shigeru Katagiri (38 shared papers)Ehsan Variani (5 shared papers)Xin Lei (1 shared paper)Javier Gónzalez-Domínguez (1 shared paper)Ignacio López Moreno (1 shared paper)Andrew Senior (4 shared papers)Haşim Sak (3 shared papers)Atsushi Nakamura (14 shared papers)
Journals: The Journal of the Acoustical Society of America (2 papers)Computer Speech & Language (2 papers)Applied Intelligence (1 paper)IEEE Transactions on Speech and Audio Processing (1 paper)Speech Communication (1 paper)
Partner nations: Japan United States Italy

In The Last Decade

Erik McDermott

64 papers receiving 2.0k citations

Erik McDermott's Hit Papers

align trajectories log scale

Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss 2020 · 290 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2020 Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss
2014 Deep neural networks for small footprint text-dependent speaker verification

Peers

Countries citing papers authored by Erik McDermott

Since Specialization

Citations

This map shows the geographic impact of Erik McDermott's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Erik McDermott with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Erik McDermott more than expected).

Fields of papers citing papers by Erik McDermott

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Erik McDermott. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Erik McDermott. The network helps show where Erik McDermott may publish in the future.

Co-authors

The 25 scholars most cited alongside Erik McDermott, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Erik McDermott Line = papers co-authored together Erik McDermott links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Showing the 20 most-cited of 67 papers — load more, or switch the sort, to bring in the rest.

#	Work
1	Deep neural networks for small footprint text-dependent speaker verification Ehsan Variani, Xin Lei, Erik McDermott, Ignacio López Moreno, Javier Gónzalez-Domínguez Hit paper breakdown →	2014	654
2	Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss Qian Zhang, Lu Han, Haşim Sak, Anshuman Tripathi, Erik McDermott, Stephen Koo, Shankar Kumar Hit paper breakdown →	2020	290
3	Speech production knowledge in automatic speech recognition The Journal of the Acoustical Society of America ·Simon King, Joe Frankel, Karen Livescu, Erik McDermott, Korin Richmond, Mirjam Wester	2007	149
4	Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error IEEE Transactions on Audio Speech and Language Processing ·Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura, Shigeru Katagiri	2006	129
5	Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription Hank Liao, Erik McDermott, Andrew Senior	2013	125
6	Acoustic Modeling for Google Home Bo Li, Tara N. Sainath, Arun Narayanan, Joe Caroselli, Michiel Bacchiani, Ananya Misra, Izhak Shafran, Haşim Sak, Golan Pundak, K. K. Chin, Khe Chai Sim, Ron J. Weiss, Kevin Wilson, Ehsan Variani, Chanwoo Kim, Olivier Siohan, M. Weintraub, Erik McDermott, Richard C. Rose, Matt Shannon	2017	100
7	Sequence discriminative distributed training of long short-term memory recurrent neural networks Haşim Sak, Oriol Vinyals, Georg Heigold, Andrew Senior, Erik McDermott, Rajat Monga, M. Mao	2014	95
8	An application of discriminative feature extraction to filter-bank-based speech recognition IEEE Transactions on Speech and Audio Processing ·Alain Biem, Shigeru Katagiri, Erik McDermott, Biing‐Hwang Juang	2001	60
9	Asynchronous stochastic optimization for sequence training of deep neural networks Georg Heigold, Erik McDermott, Vincent Vanhoucke, Andrew Senior, Michiel Bacchiani	2014	46
10	Prototype-based minimum classification error/generalized probabilistic descent training for various speech units Computer Speech & Language ·Erik McDermott, Shigeru Katagiri	1994	38
11	Training conditional random fields with multivariate evaluation measures Jun Suzuki, Erik McDermott, Hideki Isozaki	2006	37
12	Discriminative training based on an integrated view of MPE and MMI in margin and error space Erik McDermott, Shinji Watanabe, Atsushi Nakamura	2010	31
13	A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture Ehsan Variani, Erik McDermott, Georg Heigold	2015	29
14	LVQ-based shift-tolerant phoneme recognition IEEE Transactions on Signal Processing ·Erik McDermott, Shigeru Katagiri	1991	26
15	A hybrid speech recognition system using HMMs with an LVQ-trained codebook. Journal of the Acoustical Society of Japan (E) ·Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott, Yoh’ichi Tohkura	1990	25
16	Optimization methods for discriminative training Jonathan Le Roux, Erik McDermott	2005	22
17	Minimum classification error training of landmark models for real-time continuous speech recognition Erik McDermott, Timothy J. Hazen	2004	21
18	A derivation of minimum classification error from the theoretical classification risk using Parzen estimation Computer Speech & Language ·Erik McDermott, Shigeru Katagiri	2003	21
19	Prototype-based discriminative training for various speech units Erik McDermott, Shigeru Katagiri	1992	21
20	Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott	1991	21

About Erik McDermott

Erik McDermott is a scholar working on Artificial Intelligence, Signal Processing, Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology and Control and Systems Engineering, having authored 67 papers that have together received 2.2k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (49 papers), Speech and Audio Processing (34 papers), Music and Audio Processing (21 papers), Neural Networks and Applications (14 papers), Natural Language Processing Techniques (10 papers), Topic Modeling (7 papers), Speech and dialogue systems (6 papers) and Phonetics and Phonology Research (4 papers). The work is most often cited by research in Signal Processing (1.5k citations), Artificial Intelligence (2.0k citations), Computer Vision and Pattern Recognition (266 citations), Experimental and Cognitive Psychology (157 citations) and Human-Computer Interaction (21 citations). Erik McDermott has collaborated with scholars based in Japan, United States and Italy. Frequent co-authors include Shigeru Katagiri, Ehsan Variani, Xin Lei, Javier Gónzalez-Domínguez, Ignacio López Moreno, Andrew Senior, Haşim Sak, Atsushi Nakamura, Hank Liao and Qian Zhang. Their work appears in journals such as The Journal of the Acoustical Society of America, Computer Speech & Language, Applied Intelligence, IEEE Transactions on Speech and Audio Processing and Speech Communication.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Erik McDermott

Impact in

Papers in i

In The Last Decade

Erik McDermott

Erik McDermott's Hit Papers

Peers

Countries citing papers authored by Erik McDermott

Fields of papers citing papers by Erik McDermott

All Works

About Erik McDermott

Explore authors with similar magnitude of impact

Papers in