H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 59 Citations 10,743 291 World Ranking 1656 National Ranking 95

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Machine learning

His primary areas of study are Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Artificial neural network. His Speech recognition study integrates concerns from other disciplines, such as Automatic summarization, Feature extraction and Microphone. His Artificial intelligence research integrates issues from Context and Natural language processing.

His Hidden Markov model study incorporates themes from Parametric statistics, Decoding methods, Time delay neural network, Acoustic model and Machine learning. The concepts of his Pattern recognition study are interwoven with issues in Maximum likelihood and Markov model. Steve Renals combines subjects such as Smoothing, Mixture distribution, Adaptation and Speaker adaptation with his study of Artificial neural network.

His most cited work include:

  • WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition (282 citations)
  • Connectionist probability estimators in HMM speech recognition (214 citations)
  • Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models (196 citations)

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

His scientific interests lie mostly in Speech recognition, Artificial intelligence, Natural language processing, Hidden Markov model and Artificial neural network. The Speech recognition study which covers Mixture model that intersects with Subspace topology. His studies deal with areas such as Context, Machine learning and Pattern recognition as well as Artificial intelligence.

Steve Renals focuses mostly in the field of Natural language processing, narrowing it down to matters related to Task and, in some cases, Segmentation. His work carried out in the field of Hidden Markov model brings together such families of science as Speech synthesis, Posterior probability, Connectionism and Markov model. His Word error rate research includes themes of Transcription, Feature and Feature extraction.

He most often published in these fields:

  • Speech recognition (59.34%)
  • Artificial intelligence (48.23%)
  • Natural language processing (22.98%)

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

  • Speech recognition (59.34%)
  • Artificial neural network (19.19%)
  • Adaptation (6.31%)

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

Steve Renals focuses on Speech recognition, Artificial neural network, Adaptation, Artificial intelligence and Word error rate. In the subject of general Speech recognition, his work in Speaker diarisation is often linked to Set, thereby combining diverse domains of study. His Artificial neural network research is multidisciplinary, relying on both UTC offset, Classifier, Task, Phone and Acoustic model.

His Adaptation research includes elements of Algorithm, Stress and Hidden Markov model. His study in Artificial intelligence is interdisciplinary in nature, drawing from both Parametric statistics and Pattern recognition. He has included themes like Pearson product-moment correlation coefficient, Mel-frequency cepstrum, Mean squared error, Sentence and Joint in his Word error rate study.

Between 2018 and 2021, his most popular works were:

  • Dynamic Evaluation of Transformer Language Models. (21 citations)
  • Windowed Attention Mechanisms for Speech Recognition (13 citations)
  • European Language Grid: An Overview. (12 citations)

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

  • Artificial intelligence
  • Statistics
  • Machine learning

Steve Renals mainly focuses on Speech recognition, Artificial neural network, Adaptation, Task and Acoustic model. His multidisciplinary approach integrates Speech recognition and Invariant in his work. He has researched Artificial neural network in several fields, including Transfer of learning and Phone.

His Adaptation research incorporates elements of Gradient descent, Schedule and Meta learning. Steve Renals interconnects Speech transcription, Arabic speech recognition, Arabic and Identification in the investigation of issues within Task. The Acoustic model study combines topics in areas such as Feature extraction, Waveform, Filter and Orders of magnitude.

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

WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition

T. Robinson;J. Fransen;D. Pye;J. Foote.
international conference on acoustics, speech, and signal processing (1995)

407 Citations

Connectionist probability estimators in HMM speech recognition

S. Renals;N. Morgan;H. Bourlard;M. Cohen.
IEEE Transactions on Speech and Audio Processing (1994)

357 Citations

Speaker verification using sequence discriminant support vector machines

V. Wan;S. Renals.
IEEE Transactions on Speech and Audio Processing (2005)

297 Citations

Document space models using latent semantic analysis.

Yoshihiko Gotoh;Steve Renals.
conference of the international speech communication association (1997)

282 Citations

Extractive summarization of meeting recordings.

Gabriel Murray;Steve Renals;Jean Carletta.
conference of the international speech communication association (2005)

266 Citations

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

J. Yamagishi;T. Nose;H. Zen;Zhen-Hua Ling.
IEEE Transactions on Audio, Speech, and Language Processing (2009)

232 Citations

Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models

Pawel Swietojanski;Steve Renals.
spoken language technology workshop (2014)

228 Citations

Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System

João Paulo Neto;Luís B. Almeida;Mike Hochberg;Ciro Martins.
conference of the international speech communication association (1995)

225 Citations

Multilingual training of deep neural networks

Arnab Ghoshal;Pawel Swietojanski;Steve Renals.
international conference on acoustics, speech, and signal processing (2013)

218 Citations

THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION

Tony Robinson;Mike Hochberg;Steve Renals.
(1996)

215 Citations

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

Contact us

Best Scientists Citing Steve Renals

Hervé Bourlard

Hervé Bourlard

Idiap Research Institute

Publications: 73

Dong Yu

Dong Yu

Tencent (China)

Publications: 60

Junichi Yamagishi

Junichi Yamagishi

National Institute of Informatics

Publications: 56

Simon King

Simon King

University of Edinburgh

Publications: 51

Li Deng

Li Deng

Citadel

Publications: 47

Yang Liu

Yang Liu

Nanyang Technological University

Publications: 46

Thomas Hain

Thomas Hain

University of Sheffield

Publications: 46

Shinji Watanabe

Shinji Watanabe

Carnegie Mellon University

Publications: 44

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 41

Tomohiro Nakatani

Tomohiro Nakatani

NTT (Japan)

Publications: 40

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 39

Jinyu Li

Jinyu Li

Microsoft (United States)

Publications: 39

Philip C. Woodland

Philip C. Woodland

University of Cambridge

Publications: 36

Yifan Gong

Yifan Gong

Microsoft (United States)

Publications: 35

Thierry Dutoit

Thierry Dutoit

University of Mons

Publications: 35

Nelson Morgan

Nelson Morgan

International Computer Science Institute

Publications: 34

Something went wrong. Please try again later.