D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 62 Citations 16,790 216 World Ranking 1377 National Ranking 77

Research.com Recognitions

Awards & Achievements

2013 - IEEE Fellow For contributions to large vocabulary speech recognition

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Machine learning

His primary scientific interests are in Speech recognition, Artificial intelligence, Word error rate, Hidden Markov model and Natural language processing. His Speech recognition study incorporates themes from Mutual information, Vocabulary and Cluster analysis. His Artificial intelligence research is multidisciplinary, incorporating elements of Decoding methods and Pattern recognition.

His Word error rate research focuses on subjects like Phone, which are linked to Reduction and Smoothing. The concepts of his Hidden Markov model study are interwoven with issues in Decision tree, Context and Markov model. His Natural language processing study integrates concerns from other disciplines, such as Acoustic model and Speech synthesis.

His most cited work include:

  • Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models (2172 citations)
  • The HTK book (1543 citations)
  • Tree-based state tying for high accuracy acoustic modelling (653 citations)

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

Philip C. Woodland mainly investigates Speech recognition, Artificial intelligence, Natural language processing, Word error rate and Hidden Markov model. His Speech recognition research integrates issues from Word, Artificial neural network, Vocabulary and Discriminative model. The study incorporates disciplines such as Context, Machine learning and Pattern recognition in addition to Artificial intelligence.

His Natural language processing research includes elements of Transcription, Speech corpus and Mandarin Chinese. His Word error rate research is multidisciplinary, incorporating perspectives in Speaker diarisation, Reduction, Transcription, Acoustic model and Robustness. Philip C. Woodland combines subjects such as Decision tree, Estimation theory, Markov model and Speech synthesis with his study of Hidden Markov model.

He most often published in these fields:

  • Speech recognition (69.14%)
  • Artificial intelligence (55.39%)
  • Natural language processing (27.88%)

What were the highlights of his more recent work (between 2014-2021)?

  • Speech recognition (69.14%)
  • Artificial intelligence (55.39%)
  • Word error rate (27.88%)

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

Philip C. Woodland mainly focuses on Speech recognition, Artificial intelligence, Word error rate, Artificial neural network and Language model. His Speech recognition study deals with Word intersecting with Sigmoid function. He has included themes like Natural language processing, Machine learning and Pattern recognition in his Artificial intelligence study.

His Word error rate research is multidisciplinary, relying on both Transcription, Acoustic model, Transcription and Embedding. His research in Artificial neural network intersects with topics in Algorithm, Discriminative model and Hidden Markov model. His study looks at the intersection of Hidden Markov model and topics like Lexicon with Connectionism.

Between 2014 and 2021, his most popular works were:

  • The MGB challenge: Evaluating multi-genre broadcast media recognition (76 citations)
  • Recurrent neural network language model adaptation for multi-genre broadcast speech recognition (70 citations)
  • Recurrent neural network language model training with noise contrastive estimation for speech recognition (67 citations)

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

  • Artificial intelligence
  • Machine learning
  • Speech recognition

His scientific interests lie mostly in Speech recognition, Artificial intelligence, Artificial neural network, Word error rate and Language model. His Speech recognition study combines topics from a wide range of disciplines, such as Decoding methods, Activation function and Hybrid system. Philip C. Woodland interconnects Machine learning, Vocabulary and Pattern recognition in the investigation of issues within Artificial intelligence.

His studies in Artificial neural network integrate themes in fields like Feature extraction and Cluster analysis. His Word error rate study integrates concerns from other disciplines, such as Acoustic model and Reduction. His research investigates the connection between Language model and topics such as Recurrent neural network that intersect with issues in Natural language processing, Class and Source code.

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

The HTK book

SJ Young;J Jansen;JJ Odell;DG Ollason.
(1995)

6502 Citations

Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models

C. J. Leggetter;Philip C. Woodland.
Computer Speech & Language (1995)

3320 Citations

Tree-Based State Tying for High Accuracy Modelling.

Steve J. Young;J. J. Odell;Philip C. Woodland.
HLT (1994)

1032 Citations

Tree-based state tying for high accuracy acoustic modelling

S. J. Young;J. J. Odell;P. C. Woodland.
human language technology (1994)

1020 Citations

The HTK book version 3.4

SJ Young;G Evermann;Mjf Gales;D Kershaw.
(2006)

977 Citations

Minimum Phone Error and I-smoothing for improved discriminative training

D. Povey;P.C. Woodland.
international conference on acoustics, speech, and signal processing (2002)

895 Citations

Mean and variance adaptation within the MLLR framework

Mark J. F. Gales;Philip C. Woodland.
Computer Speech & Language (1996)

617 Citations

Large scale discriminative training of hidden Markov models for speech recognition

P.C. Woodland;D. Povey.
Computer Speech & Language (2002)

540 Citations

Large vocabulary continuous speech recognition using HTK

P.C. Woodland;J.J. Odell;V. Valtchev;S.J. Young.
international conference on acoustics, speech, and signal processing (1994)

368 Citations

MMIE training of large vocabulary recognition systems

V. Valtchev;J. J. Odell;P. C. Woodland;S. J. Young.
Speech Communication (1997)

256 Citations

Best Scientists Citing Philip C. Woodland

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 137

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 105

Jean-Luc Gauvain

Jean-Luc Gauvain

Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

Publications: 83

Chin-Hui Lee

Chin-Hui Lee

Georgia Institute of Technology

Publications: 82

Steve Renals

Steve Renals

University of Edinburgh

Publications: 77

Lori Lamel

Lori Lamel

University of Paris-Saclay

Publications: 75

Thomas Hain

Thomas Hain

University of Sheffield

Publications: 68

Ralf Schlüter

Ralf Schlüter

RWTH Aachen University

Publications: 67

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 65

Sadaoki Furui

Sadaoki Furui

Toyota Institute of Technology

Publications: 58

Mari Ostendorf

Mari Ostendorf

University of Washington

Publications: 57

Daniel Povey

Daniel Povey

Xiaomi (China)

Publications: 56

Shinji Watanabe

Shinji Watanabe

Carnegie Mellon University

Publications: 55

Li Deng

Li Deng

Citadel

Publications: 53

John Hansen

John Hansen

The University of Texas at Dallas

Publications: 53

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-index is inferred from publications deemed to belong to the considered discipline.

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

Contact us
Something went wrong. Please try again later.