Réda Dehak

4.9k total citations · 1 hit paper
25 papers, 3.3k citations indexed

About

Réda Dehak is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Réda Dehak has authored 25 papers receiving a total of 3.3k indexed citations (citations by other indexed papers that have themselves been cited), including 22 papers in Artificial Intelligence, 21 papers in Signal Processing and 2 papers in Computer Vision and Pattern Recognition. Recurrent topics in Réda Dehak's work include Speech Recognition and Synthesis (22 papers), Speech and Audio Processing (19 papers) and Music and Audio Processing (13 papers). Réda Dehak is often cited by papers focused on Speech Recognition and Synthesis (22 papers), Speech and Audio Processing (19 papers) and Music and Audio Processing (13 papers). Réda Dehak collaborates with scholars based in France, United States and Canada. Réda Dehak's co-authors include Najim Dehak, Patrick Kenny, Pierre Dumouchel, Pierre Ouellet, James Glass, Douglas A. Reynolds, Stephen Shum, Niko Brümmer, Pedro A. Torres‐Carrasquillo and Nanxin Chen and has published in prestigious journals such as Scientific Reports, IEEE Transactions on Audio Speech and Language Processing and Computer Speech & Language.

In The Last Decade

Réda Dehak

22 papers receiving 3.0k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Front-End Factor Analysis for Speaker Verification

2010 2.4k citations Najim Dehak, Patrick Kenny et al. IEEE Transactions on Audio Speech and Language Processing profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Réda Dehak France	13	3.1k	2.8k	255	170	88	25	3.3k
Pierre Ouellet Canada	18	4.2k 1.4×	3.9k 1.4×	326 1.3×	158 0.9×	106 1.2×	31	4.5k
Kong Aik Lee Singapore	26	2.5k 0.8×	2.8k 1.0×	436 1.7×	70 0.4×	102 1.2×	178	3.3k
Gregory Sell United States	17	2.4k 0.8×	2.1k 0.7×	159 0.6×	122 0.7×	99 1.1×	38	2.6k
Nanxin Chen United States	19	2.0k 0.7×	1.6k 0.6×	207 0.8×	86 0.5×	74 0.8×	29	2.3k
Massimiliano Todisco France	22	1.8k 0.6×	1.9k 0.7×	584 2.3×	174 1.0×	187 2.1×	90	2.4k
Thomas Hain United Kingdom	24	2.0k 0.6×	1.4k 0.5×	236 0.9×	280 1.6×	128 1.5×	187	2.3k
Ignacio López Moreno United States	16	2.2k 0.7×	1.9k 0.7×	188 0.7×	61 0.4×	41 0.5×	56	2.5k
K. Sri Rama Murty India	14	1.1k 0.4×	1.1k 0.4×	177 0.7×	316 1.9×	134 1.5×	58	1.5k
Pavel Matějka Czechia	26	2.0k 0.7×	1.9k 0.7×	259 1.0×	103 0.6×	20 0.2×	63	2.3k
Kris Demuynck Belgium	21	1.8k 0.6×	1.3k 0.5×	197 0.8×	163 1.0×	51 0.6×	114	2.1k

Countries citing papers authored by Réda Dehak

Since Specialization

Citations

This map shows the geographic impact of Réda 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 Réda Dehak with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Réda Dehak more than expected).

Fields of papers citing papers by Réda Dehak

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Réda 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 Réda Dehak. The network helps show where Réda Dehak may publish in the future.

Co-authorship network of co-authors of Réda Dehak

This figure shows the co-authorship network connecting the top 25 collaborators of Réda Dehak. A scholar is included among the top collaborators of Réda 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 Réda Dehak. Réda Dehak is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Dehak, Réda, et al.. (2024). Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations. SPIRE - Sciences Po Institutional REpository. 38–42.

2.

Dehak, Réda, et al.. (2024). Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models. SPIRE - Sciences Po Institutional REpository. 2660–2664. 1 indexed citations

3.

Dehak, Réda, et al.. (2023). Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification. SPIRE - Sciences Po Institutional REpository. 4708–4712.

4.

Dehak, Réda, et al.. (2022). Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning. Interspeech 2022. 4018–4022. 5 indexed citations

5.

Villalba, Jesús, Nanxin Chen, David Snyder, et al.. (2019). State-of-the-Art Speaker Recognition for Telephone and Video Speech: The JHU-MIT Submission for NIST SRE18. 1488–1492. 50 indexed citations

6.

Bureau, Sylvie, et al.. (2019). Use of Machine Learning and Infrared Spectra for Rheological Characterization and Application to the Apricot. Scientific Reports. 9(1). 19197–19197. 9 indexed citations

7.

Villalba, Jesús, Nanxin Chen, David Snyder, et al.. (2019). State-of-the-art speaker recognition with neural network embeddings in NIST SRE18 and Speakers in the Wild evaluations. Computer Speech & Language. 60. 101026–101026. 78 indexed citations

8.

Torres‐Carrasquillo, Pedro A., Fred Richardson, Douglas Sturim, et al.. (2017). The MIT-LL, JHU and LRDE NIST 2016 Speaker Recognition Evaluation System. 1333–1337. 9 indexed citations

9.

Shum, Stephen, Najim Dehak, Réda Dehak, & James Glass. (2013). Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach. IEEE Transactions on Audio Speech and Language Processing. 21(10). 2015–2028. 115 indexed citations

10.

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

11.

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

12.

Dehak, Najim, Zahi N. Karam, Douglas A. Reynolds, et al.. (2011). A channel-blind system for speaker verification. 4536–4539. 24 indexed citations

13.

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

14.

Dehak, Najim, Réda Dehak, James Glass, Douglas A. Reynolds, & Patrick Kenny. (2010). Cosine Similarity Scoring without Score Normalization Techniques.. 15. 119 indexed citations

15.

Dehak, Najim, Patrick Kenny, Réda Dehak, Pierre Dumouchel, & Pierre Ouellet. (2010). Front-End Factor Analysis for Speaker Verification. IEEE Transactions on Audio Speech and Language Processing. 19(4). 788–798. 2417 indexed citations breakdown →

16.

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

17.

Dumouchel, Pierre, et al.. (2009). Cepstral and long-term features for emotion recognition. 344–347. 45 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