Najim Dehak

10.2k total citations · 3 hit papers
170 papers, 6.4k citations indexed

About

Najim Dehak is a scholar working on Artificial Intelligence, Signal Processing and Physiology. According to data from OpenAlex, Najim Dehak has authored 170 papers receiving a total of 6.4k indexed citations (citations by other indexed papers that have themselves been cited), including 132 papers in Artificial Intelligence, 96 papers in Signal Processing and 26 papers in Physiology. Recurrent topics in Najim Dehak's work include Speech Recognition and Synthesis (121 papers), Speech and Audio Processing (77 papers) and Music and Audio Processing (65 papers). Najim Dehak is often cited by papers focused on Speech Recognition and Synthesis (121 papers), Speech and Audio Processing (77 papers) and Music and Audio Processing (65 papers). Najim Dehak collaborates with scholars based in United States, Canada and France. Najim Dehak's co-authors include Patrick Kenny, Pierre Dumouchel, Réda Dehak, Pierre Ouellet, Jesús Villalba, Douglas A. Reynolds, Fred Richardson, Laureano Moro-Velázquez, James Glass and V. Gupta and has published in prestigious journals such as PLoS ONE, Scientific Reports and IEEE Access.

In The Last Decade

Najim Dehak

153 papers receiving 5.8k citations

Hit Papers

Front-End Factor Analysis for Speaker Verification 2008 2026 2014 2020 2010 2008 2015 500 1000 1.5k 2.0k

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Najim Dehak United States 33 5.4k 4.9k 567 514 489 170 6.4k
Mark Hasegawa‐Johnson United States 33 2.5k 0.5× 2.5k 0.5× 534 0.9× 901 1.8× 1.3k 2.7× 296 4.8k
Juan Ignacio Godino-Llorente Spain 34 1.6k 0.3× 1.4k 0.3× 1.8k 3.1× 202 0.4× 497 1.0× 129 3.1k
Hynek Heřmanský United States 40 6.7k 1.2× 7.1k 1.4× 142 0.3× 927 1.8× 636 1.3× 242 8.4k
Aren Jansen United States 24 2.2k 0.4× 3.2k 0.6× 79 0.1× 1.5k 2.9× 373 0.8× 68 4.6k
Felix Weninger Germany 30 2.2k 0.4× 2.4k 0.5× 221 0.4× 658 1.3× 1.5k 3.0× 100 4.2k
Martin Wöllmer Germany 28 2.6k 0.5× 2.2k 0.4× 137 0.2× 969 1.9× 2.6k 5.3× 80 5.0k
S. R. Mahadeva Prasanna India 28 2.1k 0.4× 2.3k 0.5× 195 0.3× 476 0.9× 582 1.2× 290 3.1k
Douglas O’Shaughnessy Canada 26 2.2k 0.4× 2.2k 0.4× 193 0.3× 541 1.1× 703 1.4× 258 3.4k
Michael Picheny United States 31 2.9k 0.5× 2.2k 0.5× 130 0.2× 365 0.7× 855 1.7× 142 4.0k
Thierry Dutoit Belgium 34 2.0k 0.4× 1.6k 0.3× 390 0.7× 803 1.6× 852 1.7× 204 4.2k

Countries citing papers authored by Najim Dehak

Since Specialization
Citations

This map shows the geographic impact of Najim Dehak's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Najim Dehak with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Najim Dehak more than expected).

Fields of papers citing papers by Najim Dehak

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Najim Dehak. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Najim Dehak. The network helps show where Najim Dehak may publish in the future.

Co-authorship network of co-authors of Najim Dehak

This figure shows the co-authorship network connecting the top 25 collaborators of Najim Dehak. A scholar is included among the top collaborators of Najim Dehak based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Najim Dehak. Najim Dehak is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Villalba, Jesús, et al.. (2024). End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors. IEEE/ACM Transactions on Audio Speech and Language Processing. 32. 3960–3973. 2 indexed citations
2.
Moro-Velázquez, Laureano, et al.. (2024). Odyssey 2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results. 247–254. 9 indexed citations
3.
Moro-Velázquez, Laureano, et al.. (2023). Handwriting characteristics analysis for Alzheimer’s Disease and Mild Cognitive Impairments Assessment. Alzheimer s & Dementia. 19(S15). 1 indexed citations
4.
Villalba, Jesús, et al.. (2023). Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning. 431–435. 4 indexed citations
5.
Pappagari, Raghavendra, Jaejin Cho, Laureano Moro-Velázquez, et al.. (2021). Automatic Detection and Assessment of Alzheimer Disease Using Speech and Language Technologies in Low-Resource Scenarios. 3825–3829. 37 indexed citations
6.
Moro-Velázquez, Laureano, Estefanía Hernández‐García, Jorge A. Gómez-García, Juan Ignacio Godino-Llorente, & Najim Dehak. (2020). Analysis of the Effects of Supraglottal Tract Surgical Procedures in Automatic Speaker Recognition Performance. IEEE/ACM Transactions on Audio Speech and Language Processing. 28. 798–812. 2 indexed citations
7.
Moro-Velázquez, Laureano, Jorge A. Gómez-García, Najim Dehak, & Juan Ignacio Godino-Llorente. (2019). Analysis of phonatory features for the automatic detection of Parkinson's Disease in two different corpora. UPM Digital Archive (Technical University of Madrid). 3 indexed citations
8.
Cho, Jaejin, Raghavendra Pappagari, Purva Kulkarni, et al.. (2018). Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts. 247–251. 61 indexed citations
9.
Wiesner, Matthew, Adithya Renduchintala, Shinji Watanabe, et al.. (2018). Low Resource Multi-modal Data Augmentation for End-to-end ASR.. arXiv (Cornell University). 1 indexed citations
10.
Dehak, Najim. (2016). I-Vector Representation Based on GMM and DNN for Audio Classification.. 3 indexed citations
11.
Hill, Edward E., David K. Han, Pierre Dumouchel, et al.. (2013). Correction: Long Term Suboxone™ Emotional Reactivity As Measured by Automatic Detection in Speech. PLoS ONE. 8(8). 6 indexed citations
12.
Han, David, Pierre Dumouchel, Najim Dehak, et al.. (2013). Long Term Suboxone™ Emotional Reactivity As Measured by Automatic Detection in Speech. PLoS ONE. 8(7). e69043–e69043. 28 indexed citations
13.
Senoussaoui, Mohammed, Najim Dehak, Patrick Kenny, Réda Dehak, & Pierre Dumouchel. (2012). First attempt of boltzmann machines for speaker verification.. Espace ÉTS (ETS). 117–121. 35 indexed citations
14.
Singer, Elliot, Pedro A. Torres‐Carrasquillo, Douglas A. Reynolds, et al.. (2012). The MITLL NIST LRE 2011 language recognition system.. 209–215. 32 indexed citations
15.
Dehak, Najim, Pedro A. Torres‐Carrasquillo, Douglas A. Reynolds, & Réda Dehak. (2011). Language recognition via i-vectors and dimensionality reduction. 857–860. 58 indexed citations
16.
Shum, Stephen, Najim Dehak, Réda Dehak, & James Glass. (2010). Unsupervised Speaker Adaptation based on the Cosine Similarity for Text-Independent Speaker Verification.. 16. 38 indexed citations
17.
Dehak, Najim, Réda Dehak, Patrick Kenny, et al.. (2009). Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification. 1559–1562. 228 indexed citations
18.
Kenny, Patrick, Najim Dehak, Réda Dehak, Vishwa Gupta, & Pierre Dumouchel. (2008). The role of speaker factors in the NIST extended data task.. 11. 9 indexed citations
19.
Dehak, Réda, Najim Dehak, Patrick Kenny, & Pierre Dumouchel. (2008). Kernel combination for SVM speaker verification. 21. 9 indexed citations
20.
Dehak, Najim, Réda Dehak, Patrick Kenny, & Pierre Dumouchel. (2008). Comparison between factor analysis and GMM support vector machines for speaker verification. 9. 8 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026