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 56 Citations 28,226 225 World Ranking 2035 National Ranking 1109

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Statistics

His primary scientific interests are in Speech recognition, Artificial intelligence, Artificial neural network, Natural language processing and Machine learning. He has included themes like Time delay neural network and Robustness in his Speech recognition study. He has included themes like Vocabulary, Task and Pattern recognition in his Artificial intelligence study.

His Artificial neural network study combines topics in areas such as Speaker verification and Lattice, Topology. The Machine learning study combines topics in areas such as Work, Probability distribution and Training set. His Perplexity study in the realm of Language model interacts with subjects such as Scalability.

His most cited work include:

  • Recurrent neural network based language model (3552 citations)
  • Librispeech: An ASR corpus based on public domain audio books (1658 citations)
  • Extensions of recurrent neural network language model (1183 citations)

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

The scientist’s investigation covers issues in Artificial intelligence, Speech recognition, Natural language processing, Language model and Machine translation. The Artificial intelligence study which covers Pattern recognition that intersects with Set. His Speech recognition study incorporates themes from Artificial neural network, Vocabulary and Word.

His Natural language processing research incorporates elements of Pronunciation, Speech corpus and Mandarin Chinese. His work on Perplexity as part of general Language model research is frequently linked to Cache language model, thereby connecting diverse disciplines of science. His Machine translation research is multidisciplinary, relying on both Translation, Parsing and Rule-based machine translation.

He most often published in these fields:

  • Artificial intelligence (53.54%)
  • Speech recognition (51.18%)
  • Natural language processing (31.65%)

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

  • Speech recognition (51.18%)
  • Artificial intelligence (53.54%)
  • Speaker diarisation (7.07%)

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

His primary areas of investigation include Speech recognition, Artificial intelligence, Speaker diarisation, Language model and Artificial neural network. His study in Speaker recognition and Word error rate is done as part of Speech recognition. His Artificial intelligence study integrates concerns from other disciplines, such as Natural language processing, Set and Pattern recognition.

Sanjeev Khudanpur combines subjects such as Cluster analysis, Conversational speech and Voice activity detection with his study of Speaker diarisation. A large part of his Language model studies is devoted to Perplexity. His Artificial neural network study combines topics from a wide range of disciplines, such as Transcription, Baseline and Utterance.

Between 2018 and 2021, his most popular works were:

  • Speaker Recognition for Multi-speaker Conversations Using X-vectors (94 citations)
  • CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings (49 citations)
  • State-of-the-Art Speaker Recognition for Telephone and Video Speech: The JHU-MIT Submission for NIST SRE18. (42 citations)

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

  • Artificial intelligence
  • Statistics
  • Machine learning

His primary areas of study are Speech recognition, Speaker diarisation, Speaker recognition, Artificial neural network and Language model. His research integrates issues of Time delay neural network and Open source in his study of Speech recognition. His Artificial neural network research includes elements of Baseline and Hidden Markov model.

His studies deal with areas such as Text corpus, Empirical research, Transformer and Machine translation as well as Language model. Machine translation is a subfield of Artificial intelligence that Sanjeev Khudanpur explores. His biological study spans a wide range of topics, including Embedding and Measure.

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

Recurrent neural network based language model

Tomas Mikolov;Martin Karafiát;Lukás Burget;Jan Cernocký.
conference of the international speech communication association (2010)

5539 Citations

Extensions of recurrent neural network language model

Tomas Mikolov;Stefan Kombrink;Lukas Burget;Jan Cernocky.
international conference on acoustics, speech, and signal processing (2011)

5404 Citations

Librispeech: An ASR corpus based on public domain audio books

Vassil Panayotov;Guoguo Chen;Daniel Povey;Sanjeev Khudanpur.
international conference on acoustics, speech, and signal processing (2015)

1868 Citations

X-Vectors: Robust DNN Embeddings for Speaker Recognition

David Snyder;Daniel Garcia-Romero;Gregory Sell;Daniel Povey.
international conference on acoustics, speech, and signal processing (2018)

1099 Citations

A time delay neural network architecture for efficient modeling of long temporal contexts.

Vijayaditya Peddinti;Daniel Povey;Sanjeev Khudanpur.
conference of the international speech communication association (2015)

766 Citations

Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI.

Daniel Povey;Vijayaditya Peddinti;Daniel Galvez;Pegah Ghahremani.
conference of the international speech communication association (2016)

631 Citations

Audio augmentation for speech recognition.

Tom Ko;Vijayaditya Peddinti;Daniel Povey;Sanjeev Khudanpur.
conference of the international speech communication association (2015)

618 Citations

Deep Neural Network Embeddings for Text-Independent Speaker Verification.

David Snyder;Daniel Garcia-Romero;Daniel Povey;Sanjeev Khudanpur.
conference of the international speech communication association (2017)

547 Citations

Improving deep neural network acoustic models using generalized maxout networks

Xiaohui Zhang;Jan Trmal;Daniel Povey;Sanjeev Khudanpur.
international conference on acoustics, speech, and signal processing (2014)

342 Citations

A Smorgasbord of Features for Statistical Machine Translation

Franz Josef Och;Daniel Gildea;Sanjeev Khudanpur;Anoop Sarkar.
north american chapter of the association for computational linguistics (2004)

336 Citations

Best Scientists Citing Sanjeev Khudanpur

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 84

Dong Yu

Dong Yu

Tencent (China)

Publications: 77

Shinji Watanabe

Shinji Watanabe

Carnegie Mellon University

Publications: 72

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 71

Li Deng

Li Deng

Citadel

Publications: 62

James Glass

James Glass

MIT

Publications: 56

Steve Renals

Steve Renals

University of Edinburgh

Publications: 49

Lukas Burget

Lukas Burget

Brno University of Technology

Publications: 46

Murat Saraclar

Murat Saraclar

Boğaziçi University

Publications: 43

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 43

Yoshua Bengio

Yoshua Bengio

University of Montreal

Publications: 41

Ralf Schlüter

Ralf Schlüter

RWTH Aachen University

Publications: 38

William Byrne

William Byrne

University of Cambridge

Publications: 38

Shrikanth S. Narayanan

Shrikanth S. Narayanan

University of Southern California

Publications: 38

Bhuvana Ramabhadran

Bhuvana Ramabhadran

Google (United States)

Publications: 34

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.