H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 36 Citations 7,622 122 World Ranking 5635 National Ranking 2781

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Machine learning

George Saon mainly investigates Speech recognition, Artificial intelligence, Word error rate, Language model and Convolutional neural network. His Speech recognition research is multidisciplinary, incorporating perspectives in Artificial neural network and Decoding methods. George Saon works mostly in the field of Artificial neural network, limiting it down to topics relating to FMLLR and, in certain cases, Covariance, as a part of the same area of interest.

George Saon has included themes like Natural language processing and Pattern recognition in his Artificial intelligence study. His study looks at the relationship between Language model and topics such as Word, which overlap with Statement and Feature. As a member of one scientific family, George Saon mostly works in the field of Convolutional neural network, focusing on Dropout and, on occasion, Pooling and Recurrent neural network.

His most cited work include:

  • Speaker adaptation of neural network acoustic models using i-vectors (501 citations)
  • Boosted MMI for model and feature-space discriminative training (341 citations)
  • Deep Convolutional Neural Networks for Large-scale Speech Tasks (295 citations)

What are the main themes of his work throughout his whole career to date?

George Saon mostly deals with Speech recognition, Artificial intelligence, Word error rate, Pattern recognition and Language model. As part of one scientific family, he deals mainly with the area of Speech recognition, narrowing it down to issues related to the Artificial neural network, and often Convolutional neural network. His Artificial intelligence research includes themes of Machine learning and Natural language processing.

His Word error rate research incorporates themes from FMLLR, Recurrent neural network, Contrast and Test set. His Pattern recognition research includes elements of Subspace topology and Covariance. His work in Language model tackles topics such as Word which are related to areas like Feature.

He most often published in these fields:

  • Speech recognition (76.43%)
  • Artificial intelligence (59.29%)
  • Word error rate (33.57%)

What were the highlights of his more recent work (between 2018-2021)?

  • Speech recognition (76.43%)
  • Artificial intelligence (59.29%)
  • Deep learning (15.71%)

In recent papers he was focusing on the following fields of study:

George Saon mainly focuses on Speech recognition, Artificial intelligence, Deep learning, Word error rate and Benchmark. His work deals with themes such as Transducer, State and Lexicon, which intersect with Speech recognition. His study connects Identifier and Artificial intelligence.

His Deep learning research integrates issues from Supercomputer and Stochastic gradient descent. His Word error rate research is multidisciplinary, incorporating elements of Contrast, Set and Joint. His Language model study combines topics from a wide range of disciplines, such as Decoding methods and Conversational speech.

Between 2018 and 2021, his most popular works were:

  • Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard (16 citations)
  • Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition. (14 citations)
  • Advancing Sequence-to-Sequence Based Speech Recognition. (14 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Machine learning
  • Statistics

The scientist’s investigation covers issues in Speech recognition, Word error rate, Artificial intelligence, Contrast and Benchmark. Among his Speech recognition studies, you can observe a synthesis of other disciplines of science such as Sequence, Bit, Forgetting and Pronunciation. His Word error rate study integrates concerns from other disciplines, such as Language model, Regularization, State and Lexicon.

In his articles, George Saon combines various disciplines, including Artificial intelligence and Asynchronous communication. In his study, Recurrent neural network is strongly linked to Decoding methods, which falls under the umbrella field of Contrast. His biological study spans a wide range of topics, including Acoustic model, Set, Hidden Markov model and Test set.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Speaker adaptation of neural network acoustic models using i-vectors

George Saon;Hagen Soltau;David Nahamoo;Michael Picheny.
ieee automatic speech recognition and understanding workshop (2013)

611 Citations

Boosted MMI for model and feature-space discriminative training

D. Povey;D. Kanevsky;B. Kingsbury;B. Ramabhadran.
international conference on acoustics, speech, and signal processing (2008)

453 Citations

Deep Convolutional Neural Networks for Large-scale Speech Tasks

Tara N. Sainath;Brian Kingsbury;George Saon;Hagen Soltau.
Neural Networks (2015)

428 Citations

fMPE: discriminatively trained features for speech recognition

D. Povey;B. Kingsbury;L. Mangu;G. Saon.
international conference on acoustics, speech, and signal processing (2005)

370 Citations

Maximum likelihood discriminant feature spaces

G. Saon;M. Padmanabhan;R. Gopinath;S. Chen.
international conference on acoustics, speech, and signal processing (2000)

287 Citations

Improvements to Deep Convolutional Neural Networks for LVCSR

Tara N. Sainath;Brian Kingsbury;Abdel-rahman Mohamed;George E. Dahl.
ieee automatic speech recognition and understanding workshop (2013)

173 Citations

English Conversational Telephone Speech Recognition by Humans and Machines

George Saon;Gakuto Kurata;Tom Sercu;Kartik Audhkhasi.
conference of the international speech communication association (2017)

169 Citations

The IBM Attila speech recognition toolkit

Hagen Soltau;George Saon;Brian Kingsbury.
spoken language technology workshop (2010)

167 Citations

Advances in speech transcription at IBM under the DARPA EARS program

S.F. Chen;B. Kingsbury;Lidia Mangu;D. Povey.
IEEE Transactions on Audio, Speech, and Language Processing (2006)

161 Citations

The IBM 2004 conversational telephony system for rich transcription

H. Soltau;B. Kingsbury;L. Mangu;D. Povey.
international conference on acoustics, speech, and signal processing (2005)

148 Citations

If you think any of the details on this page are incorrect, let us know.

Contact us

Best Scientists Citing George Saon

Bhuvana Ramabhadran

Bhuvana Ramabhadran

Google (United States)

Publications: 91

Tara N. Sainath

Tara N. Sainath

Google (United States)

Publications: 69

Yifan Gong

Yifan Gong

Microsoft (United States)

Publications: 69

Dong Yu

Dong Yu

Tencent (China)

Publications: 67

Jinyu Li

Jinyu Li

Microsoft (United States)

Publications: 66

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 62

Shinji Watanabe

Shinji Watanabe

Carnegie Mellon University

Publications: 52

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 52

Daniel Povey

Daniel Povey

Xiaomi (China)

Publications: 51

Brian Kingsbury

Brian Kingsbury

IBM (United States)

Publications: 50

Sanjeev Khudanpur

Sanjeev Khudanpur

Johns Hopkins University

Publications: 49

Steve Renals

Steve Renals

University of Edinburgh

Publications: 48

Ralf Schlüter

Ralf Schlüter

RWTH Aachen University

Publications: 46

Li Deng

Li Deng

Citadel

Publications: 43

Tomohiro Nakatani

Tomohiro Nakatani

NTT (Japan)

Publications: 41

Philip C. Woodland

Philip C. Woodland

University of Cambridge

Publications: 36

Something went wrong. Please try again later.