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 52 Citations 11,817 230 World Ranking 2649 National Ranking 1405

Research.com Recognitions

Awards & Achievements

2017 - IEEE Fellow For contributions to speech recognition and language processing

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Speech recognition

His primary areas of investigation include Speech recognition, Artificial intelligence, Natural language processing, Vocabulary and Artificial neural network. His Speech recognition research includes themes of Word and Phone. The concepts of his Artificial intelligence study are interwoven with issues in Machine learning and Pattern recognition.

His Natural language processing research incorporates themes from Context, Keyword search, Search engine indexing and Speaker adaptation. Within one scientific family, he focuses on topics pertaining to Task under Vocabulary, and may sometimes address concerns connected to Perceptron, Variety and Speaker recognition. His studies deal with areas such as Pooling and Convolutional neural network as well as Artificial neural network.

His most cited work include:

  • Deep convolutional neural networks for LVCSR (728 citations)
  • Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets (414 citations)
  • Boosted MMI for model and feature-space discriminative training (341 citations)

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

Bhuvana Ramabhadran focuses on Artificial intelligence, Speech recognition, Natural language processing, Language model and Word error rate. His Artificial intelligence research integrates issues from Machine learning, Vocabulary and Pattern recognition. His Speech recognition study frequently links to adjacent areas such as Feature.

His work is dedicated to discovering how Natural language processing, Speech corpus are connected with Speech technology and other disciplines. His n-gram study in the realm of Language model interacts with subjects such as Cache language model. His Word error rate research incorporates elements of Natural language and Phone.

He most often published in these fields:

  • Artificial intelligence (62.63%)
  • Speech recognition (58.59%)
  • Natural language processing (31.99%)

What were the highlights of his more recent work (between 2017-2021)?

  • Speech recognition (58.59%)
  • Artificial intelligence (62.63%)
  • Speech synthesis (8.42%)

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

Bhuvana Ramabhadran mostly deals with Speech recognition, Artificial intelligence, Speech synthesis, Language model and Word error rate. His specific area of interest is Speech recognition, where Bhuvana Ramabhadran studies Utterance. Specifically, his work in Artificial intelligence is concerned with the study of Artificial neural network.

His Speech synthesis study combines topics from a wide range of disciplines, such as Embedding, Prosody, Selection and Cloning. His Language model research also works with subjects such as

  • Recurrent neural network and Sentence most often made with reference to Word,
  • Principle of maximum entropy which intersects with area such as Vocabulary and Context. He has researched Word error rate in several fields, including Pronunciation, Transliteration, Acoustic model and Hidden Markov model, Pattern recognition.

Between 2017 and 2021, his most popular works were:

  • Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition (86 citations)
  • Speech Recognition with Augmented Synthesized Speech (28 citations)
  • Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning (28 citations)

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

  • Artificial intelligence
  • Machine learning
  • Speech recognition

His primary scientific interests are in Speech recognition, Speech synthesis, Word error rate, Language model and Natural language processing. Bhuvana Ramabhadran does research in Speech recognition, focusing on Utterance specifically. His study in Word error rate is interdisciplinary in nature, drawing from both Acoustic model and Hidden Markov model.

In his study, Initialization, Context, Recurrent neural network, Principle of maximum entropy and Sentence is strongly linked to Word, which falls under the umbrella field of Language model. His Natural language processing research includes elements of Mandarin Chinese, Foreign language, Artificial intelligence and Representation. The study incorporates disciplines such as Identity and Cloning in addition to Artificial intelligence.

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

Deep convolutional neural networks for LVCSR

Tara N. Sainath;Abdel-rahman Mohamed;Brian Kingsbury;Bhuvana Ramabhadran.
international conference on acoustics, speech, and signal processing (2013)

1127 Citations

Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets

Tara N. Sainath;Brian Kingsbury;Vikas Sindhwani;Ebru Arisoy.
international conference on acoustics, speech, and signal processing (2013)

509 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

Deep Belief Networks using discriminative features for phone recognition

Abdel-rahman Mohamed;Tara N. Sainath;George Dahl;Bhuvana Ramabhadran.
international conference on acoustics, speech, and signal processing (2011)

365 Citations

Vocabulary independent spoken term detection

Jonathan Mamou;Bhuvana Ramabhadran;Olivier Siohan.
international acm sigir conference on research and development in information retrieval (2007)

242 Citations

Deep Neural Network Language Models

Ebru Arisoy;Tara N. Sainath;Brian Kingsbury;Bhuvana Ramabhadran.
north american chapter of the association for computational linguistics (2012)

240 Citations

Making Deep Belief Networks effective for large vocabulary continuous speech recognition

Tara N. Sainath;Brian Kingsbury;Bhuvana Ramabhadran;Petr Fousek.
ieee automatic speech recognition and understanding workshop (2011)

227 Citations

Method and apparatus for a communication device for use by a hearing impaired/mute or deaf person or in silent environments

Peter Thomas Brunet;Abraham P. Ittycheriah;Chandrasekhar Narayanaswami;Michael Alan Picheny.
(1998)

211 Citations

Auto-encoder bottleneck features using deep belief networks

Tara N. Sainath;Brian Kingsbury;Bhuvana Ramabhadran.
international conference on acoustics, speech, and signal processing (2012)

207 Citations

Best Scientists Citing Bhuvana Ramabhadran

Jinyu Li

Jinyu Li

Microsoft (United States)

Publications: 88

Yifan Gong

Yifan Gong

Microsoft (United States)

Publications: 80

Dong Yu

Dong Yu

Tencent (China)

Publications: 79

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 63

Li Deng

Li Deng

Citadel

Publications: 59

Tara N. Sainath

Tara N. Sainath

Google (United States)

Publications: 58

George Saon

George Saon

IBM (United States)

Publications: 51

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 49

Ralf Schlüter

Ralf Schlüter

RWTH Aachen University

Publications: 47

Steve Renals

Steve Renals

University of Edinburgh

Publications: 46

Brian Kingsbury

Brian Kingsbury

IBM (United States)

Publications: 42

Shinji Watanabe

Shinji Watanabe

Carnegie Mellon University

Publications: 41

Michael Picheny

Michael Picheny

IBM (United States)

Publications: 37

Florian Metze

Florian Metze

Carnegie Mellon University

Publications: 37

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 35

Andrew W. Senior

Andrew W. Senior

Google (United States)

Publications: 33

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.