D-Index & Metrics Best Publications

Najim Dehak

Johns Hopkins University
United States

D-Index & Metrics 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.

Discipline name Citations Publications World Ranking National Ranking

Computer Science D-index 35 Citations 10,719 174 World Ranking 7382 National Ranking 3467

Overview

What is he best known for?

The fields of study Najim Dehak is best known for:

Speech recognition
Politics
Statistics

As part of his inquiry into Speaker verification and Speaker diarisation, Najim Dehak is doing Speaker recognition research. By researching both Speaker diarisation and Speaker recognition, he produces research that crosses academic boundaries. Statistics is intertwined with Energy (signal processing) and Mixture model in his research. Najim Dehak performs multidisciplinary study in Mixture model and Statistics in his work. His Linguistics study frequently links to other fields, such as Syllable and Feature (linguistics). Syllable is closely attributed to Speech recognition in his research. Many of his studies involve connections with topics such as Speaker verification and Speech recognition. Feature (linguistics) is frequently linked to Linguistics in his study. Najim Dehak connects relevant research areas such as Energy (signal processing) and Gaussian in the domain of Quantum mechanics.

His most cited work include:

Front-End Factor Analysis for Speaker Verification (2729 citations)
A Study of Interspeaker Variability in Speaker Verification (521 citations)
Deep Neural Network Approaches to Speaker and Language Recognition (320 citations)

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

His research on Algorithm often connects related areas such as Computation, Decoding methods and State (computer science). His Algorithm research extends to the thematically linked field of State (computer science). While working in this field, Najim Dehak studies both Speech recognition and Recurrent neural network. In his works, Najim Dehak undertakes multidisciplinary study on Recurrent neural network and Speech recognition. Many of his studies on Artificial intelligence apply to Mixture model as well. He performs multidisciplinary studies into Natural language processing and Language model in his work. Najim Dehak performs multidisciplinary study on Language model and Machine learning in his works. In his research, he performs multidisciplinary study on Machine learning and Natural language processing. His Speaker verification research extends to the thematically linked field of Speaker recognition.

Najim Dehak most often published in these fields:

Speech recognition (88.00%)
Artificial intelligence (76.00%)
Natural language processing (40.00%)

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

Front-End Factor Analysis for Speaker Verification

Najim Dehak;Patrick J Kenny;Réda Dehak;Pierre Dumouchel.
IEEE Transactions on Audio, Speech, and Language Processing (2011)

4216 Citations

A Study of Interspeaker Variability in Speaker Verification

P. Kenny;P. Ouellet;N. Dehak;V. Gupta.
IEEE Transactions on Audio, Speech, and Language Processing (2008)

859 Citations

Language Recognition via i-vectors and Dimensionality Reduction.

Najim Dehak;Pedro A. Torres-Carrasquillo;Douglas A. Reynolds;Réda Dehak.
conference of the international speech communication association (2011)

539 Citations

Deep Neural Network Approaches to Speaker and Language Recognition

Fred Richardson;Douglas Reynolds;Najim Dehak.
IEEE Signal Processing Letters (2015)

480 Citations

Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification

Najim Dehak;Reda Dehak;Patrick Kenny;Niko Brummer.
conference of the international speech communication association (2009)

458 Citations

Cosine Similarity Scoring without Score Normalization Techniques.

Najim Dehak;Réda Dehak;James R. Glass;Douglas A. Reynolds.
Odyssey (2010)

221 Citations

Comparison of scoring methods used in speaker recognition with Joint Factor Analysis

Ondrej Glembek;Lukas Burget;Najim Dehak;Niko Brummer.
international conference on acoustics, speech, and signal processing (2009)

182 Citations

A unified deep neural network for speaker and language recognition.

Fred Richardson;Douglas A. Reynolds;Najim Dehak.
conference of the international speech communication association (2015)

180 Citations

Diarization is hard: Some experiences and lessons learned for the JHU team in the inaugural dihard challenge

Gregory Sell;David Snyder;Alan McCree;Daniel Garcia-Romero.
conference of the international speech communication association (2018)

176 Citations

Modeling Prosodic Features With Joint Factor Analysis for Speaker Verification

N. Dehak;P. Dumouchel;P. Kenny.
IEEE Transactions on Audio, Speech, and Language Processing (2007)

173 Citations

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

Frequent Co-Authors

External Links

Personal Website for Najim Dehak