World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
48
Citations
14211
World Ranking
6046
National Ranking
2727

Overview

Najim Dehak is affiliated with Johns Hopkins University in the United States and specializes primarily in computer science. Their research spans several subfields including artificial intelligence, signal processing, physiology, cognitive neuroscience, and computer vision and pattern recognition. The focus of their work covers multiple topics related to speech and audio technologies, notably speech recognition and synthesis, speech and audio processing, music and audio processing, voice and speech disorders, speech and dialogue systems, natural language processing techniques, and adversarial robustness in machine learning.

Najim Dehak has contributed to a range of recent publications reflecting these interests. Notable works include:

  • "Advances in Parkinson's Disease detection and assessment using voice and speech: A review of the articulatory and phonatory aspects" (2021, Biomedical Signal Processing and Control)
  • "Non-Autoregressive Transformer for Speech Recognition" (2020, IEEE Signal Processing Letters)
  • "Interpretable speech features vs. DNN embeddings: What to use in the automatic assessment of Parkinson's disease in multi-lingual scenarios" (2023, Computers in Biology and Medicine)
  • "Multilingual evaluation of interpretable biomarkers to represent language and speech patterns in Parkinson's disease" (2023, Frontiers in Neurology)
  • "Unclonable photonic keys hardened against machine learning attacks" (2020, APL Photonics)

Their frequent collaborators include Laureano Moro-Velázquez, Jesús Villalba, Thomas Thebaud, Piotr Żelasko, and Ankur Butala.

Najim Dehak's work is often published in venues such as arXiv (Cornell University), Alzheimer s & Dementia, Interspeech 2022, IEEE/ACM Transactions on Audio Speech and Language Processing, and bioRxiv (Cold Spring Harbor Laboratory).

The primary area of study for Najim Dehak is computer science, with a substantial number of publications in artificial intelligence and signal processing. Their research addresses challenges at the intersection of speech technology and biomedical applications, especially Parkinson's disease diagnosis and assessment, as reflected in multiple recent publications.

Best Publications

  • Front-End Factor Analysis for Speaker Verification

    Najim Dehak;Patrick J Kenny;Réda Dehak;Pierre Dumouchel

  • A Study of Interspeaker Variability in Speaker Verification

    P. Kenny;P. Ouellet;N. Dehak;V. Gupta

  • Language Recognition via i-vectors and Dimensionality Reduction.

    Najim Dehak;Pedro A. Torres-Carrasquillo;Douglas A. Reynolds;Réda Dehak

  • Deep Neural Network Approaches to Speaker and Language Recognition

    Fred Richardson;Douglas Reynolds;Najim Dehak

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

    Najim Dehak;Reda Dehak;Patrick Kenny;Niko Brummer

  • Cosine Similarity Scoring without Score Normalization Techniques.

    Najim Dehak;Réda Dehak;James R. Glass;Douglas A. Reynolds

  • 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

  • Hierarchical Transformers for Long Document Classification

    Raghavendra Pappagari;Piotr Zelasko;Jesus Villalba;Yishay Carmiel

  • Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach

    Stephen H. Shum;Najim Dehak;Reda Dehak;James R. Glass

  • Modeling Prosodic Features With Joint Factor Analysis for Speaker Verification

    N. Dehak;P. Dumouchel;P. Kenny

  • A unified deep neural network for speaker and language recognition.

    Fred Richardson;Douglas A. Reynolds;Najim Dehak

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

    Ondrej Glembek;Lukas Burget;Najim Dehak;Niko Brummer

  • Advances in Parkinson's Disease detection and assessment using voice and speech: A review of the articulatory and phonatory aspects

    Laureano Moro-Velazquez;Jorge A. Gomez-Garcia;Julian D. Arias-Londoño;Najim Dehak

  • ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks.

    Cheng-I Lai;Nanxin Chen;Jesús Villalba;Najim Dehak

  • Automatic Dialect Detection in Arabic Broadcast Speech

    Ahmed Ali;Najim Dehak;Najim Dehak;Patrick Cardinal;Sameer Khurana

  • An i-vector extractor suitable for speaker recognition with both microphone and telephone speech

    Mohammed Senoussaoui;Patrick Kenny;Najim Dehak;Pierre Dumouchel

  • Exploiting Intra-Conversation Variability for Speaker Diarization

    Stephen Shum;Najim Dehak;Ekapol Chuangsuwanich;Douglas A. Reynolds

  • Emotion Identification from Raw Speech Signals Using DNNs.

    Mousmita Sarma;Pegah Ghahremani;Daniel Povey;Nagendra Kumar Goel

  • rVAD: An unsupervised segment-based robust voice activity detection method

    Zheng-Hua Tan;Achintya Kumar Sarkar;Najim Dehak

  • Support vector machines and Joint Factor Analysis for speaker verification

    Najim Dehak;Patrick Kenny;Reda Dehak;Ondrej Glembek

  • Discriminative and generative approaches for long- and short-term speaker characteristics modeling: application to speaker verification

    Najim Dehak

  • Language Recognition via Ivectors and Dimensionality Reduction

    Najim Dehak;Pedro A. Torres-Carrasquillo;Douglas Reynolds;Reda Dehak

Frequent Co-Authors

Sanjeev Khudanpur
Sanjeev Khudanpur Johns Hopkins University
Patrick Kenny
Patrick Kenny École de Technologie Supérieure
Shinji Watanabe
Shinji Watanabe Carnegie Mellon University
Juan Ignacio Godino-Llorente
Juan Ignacio Godino-Llorente Technical University of Madrid
Lukas Burget
Lukas Burget Brno University of Technology
Mark Hasegawa-Johnson
Mark Hasegawa-Johnson University of Illinois at Urbana-Champaign
Daniel Povey
Daniel Povey Xiaomi (China)
Alan V. McCree
Alan V. McCree Johns Hopkins University

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

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA can open doors to a range of related fields and flexible career paths. Many students now choose online degree programs to balance study with work or family commitments. These programs span disciplines—each offering unique career opportunities and addressing evolving industry demands.

If you’re interested in fields that intersect with technology and analysis, consider a data master online program. This advanced degree focuses on big data, analytics, and data-driven decision making. Meanwhile, those drawn to business essentials may pursue an online accountant degree to develop vital financial and accounting skills sought by employers everywhere.

For students passionate about social impact, the cheapest online master's degree in criminal justice is a budget-friendly way to deepen your understanding of law, security, and public service. Likewise, if you envision a future in project coordination or the building industry, an construction management bachelor degree offers core expertise in both leadership and technical areas.

No matter your direction, these online paths offer flexible study while preparing you for rapidly changing job markets and specialized roles.

Best Scientists Citing Najim Dehak

Trending Scientists

Recently Published Articles