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 61 Citations 13,466 185 World Ranking 1451 National Ranking 812

Research.com Recognitions

Awards & Achievements

2001 - IEEE Fellow For contributions to speech recognition systems and products.

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Machine learning

Speech recognition, Artificial intelligence, Vocabulary, Natural language processing and Word are his primary areas of study. His Speech recognition study frequently links to related topics such as Markov model. Michael Picheny has included themes like Context, Set and Pattern recognition in his Artificial intelligence study.

He interconnects Training set, Information retrieval, Phone, Telephone call and Feature extraction in the investigation of issues within Vocabulary. His Natural language processing study incorporates themes from Decision tree, Speech synthesis and Document retrieval. His work in Hidden Markov model covers topics such as Pronunciation which are related to areas like Nonverbal communication.

His most cited work include:

  • Speaking Clearly for the Hard of Hearing II: Acoustic Characteristics of Clear and Conversational Speech. (501 citations)
  • Speaker adaptation of neural network acoustic models using i-vectors (501 citations)
  • Automatic indexing and aligning of audio and text using speech recognition (370 citations)

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

Michael Picheny focuses on Speech recognition, Artificial intelligence, Natural language processing, Vocabulary and Word. His research on Speech recognition often connects related topics like Artificial neural network. His study looks at the relationship between Artificial intelligence and topics such as Pattern recognition, which overlap with Feature.

His Natural language processing research is multidisciplinary, relying on both Speech corpus, Speech synthesis and Search engine indexing. His Word study which covers Markov model that intersects with Substring. Michael Picheny usually deals with Feature vector and limits it to topics linked to Speech coding and Value.

He most often published in these fields:

  • Speech recognition (74.09%)
  • Artificial intelligence (56.68%)
  • Natural language processing (30.77%)

What were the highlights of his more recent work (between 2016-2021)?

  • Speech recognition (74.09%)
  • Artificial intelligence (56.68%)
  • Deep learning (6.48%)

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

Michael Picheny mainly focuses on Speech recognition, Artificial intelligence, Deep learning, Artificial neural network and Word. His research in Word error rate and Hidden Markov model are components of Speech recognition. His Artificial intelligence research incorporates elements of Machine learning, Supercomputer, Pattern recognition and Natural language processing.

In his study, Task and CUDA is inextricably linked to Asynchronous communication, which falls within the broad field of Deep learning. His Artificial neural network research focuses on Training set and how it relates to Transfer of learning, End-to-end principle and Leverage. Michael Picheny combines subjects such as Language model and Set with his study of Word.

Between 2016 and 2021, his most popular works were:

  • English Conversational Telephone Speech Recognition by Humans and Machines (167 citations)
  • Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition (86 citations)
  • Direct Acoustics-to-Word Models for English Conversational Speech Recognition (74 citations)

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

  • Artificial intelligence
  • Machine learning
  • Speech recognition

His primary areas of study are Speech recognition, Artificial intelligence, Word error rate, Word and Language model. His work on Hidden Markov model is typically connected to Bit as part of general Speech recognition study, connecting several disciplines of science. His studies in Artificial intelligence integrate themes in fields like Machine learning, Natural sounds and Natural language processing.

His Word error rate research includes elements of Feature, Polynomial kernel, Kernel method, Tree kernel and Benchmark. The Language model study combines topics in areas such as Evolutionary algorithm, Variety, Stochastic gradient descent and Deep neural networks. His Vocabulary study combines topics in areas such as Set and Word embedding.

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

Speaking Clearly for the Hard of Hearing II: Acoustic Characteristics of Clear and Conversational Speech.

Michael A. Picheny;Nathaniel I. Durlach;Louis D. Braida.
Journal of Speech Language and Hearing Research (1986)

789 Citations

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

Speaking clearly for the hard of hearing I: Intelligibility differences between clear and conversational speech.

Michael A. Picheny;Nathaniel I. Durlach;Louis D. Braida.
Journal of Speech Language and Hearing Research (1985)

600 Citations

Automatic indexing and aligning of audio and text using speech recognition

Hamed A. Ellozy;Dimitri Kanevsky;Michelle Y. Kim;David Nahamoo.
(1995)

486 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

Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments

Lalit Rai Bahl;Peter Vincent Desouza;Robert Leroy Mercer;Michael Alan Picheny.
Journal of the Acoustical Society of America (1987)

306 Citations

Automatic determination of labels and markov word models in a speech recognition system

Peter F. Brown;Peter V. De Souza;David Nahomoo;Michael A. Picheny.
Journal of the Acoustical Society of America (1988)

303 Citations

Speech recognition apparatus having a speech coder outputting acoustic prototype ranks

Lalit R. Bahl;Peter Vincent De Souza;Ponani S. Gopalakrishnan;Michael Alan Picheny.
Journal of the Acoustical Society of America (1992)

291 Citations

Speech recognition using noise-adaptive prototypes

A. Nadas;D. Nahamoo;M.A. Picheny.
IEEE Transactions on Acoustics, Speech, and Signal Processing (1989)

270 Citations

The metamorphic algorithm: a speaker mapping approach to data augmentation

J.R. Bellegarda;P.V. de Souza;A. Nadas;D. Nahamoo.
IEEE Transactions on Speech and Audio Processing (1994)

269 Citations

Best Scientists Citing Michael Picheny

Bhuvana Ramabhadran

Bhuvana Ramabhadran

Google (United States)

Publications: 57

Dong Yu

Dong Yu

Tencent (China)

Publications: 49

Yifan Gong

Yifan Gong

Microsoft (United States)

Publications: 45

Jinyu Li

Jinyu Li

Microsoft (United States)

Publications: 40

Brian Kingsbury

Brian Kingsbury

IBM (United States)

Publications: 38

Li Deng

Li Deng

Citadel

Publications: 36

Chin-Hui Lee

Chin-Hui Lee

Georgia Institute of Technology

Publications: 34

Jerome R. Bellegarda

Jerome R. Bellegarda

Apple (United States)

Publications: 33

Alex Waibel

Alex Waibel

Carnegie Mellon University

Publications: 32

Martin T. King

Martin T. King

Google (United States)

Publications: 31

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 30

Thomas R. Gruber

Thomas R. Gruber

Apple (United States)

Publications: 30

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 29

Florian Metze

Florian Metze

Carnegie Mellon University

Publications: 28

Steve Renals

Steve Renals

University of Edinburgh

Publications: 28

Shrikanth S. Narayanan

Shrikanth S. Narayanan

University of Southern California

Publications: 28

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.