Hemlata Tak

1.4k total citations · 2 hit papers
19 papers, 592 citations indexed

About

Hemlata Tak is a scholar working on Signal Processing, Artificial Intelligence and Computer Vision and Pattern Recognition. According to data from OpenAlex, Hemlata Tak has authored 19 papers receiving a total of 592 indexed citations (citations by other indexed papers that have themselves been cited), including 16 papers in Signal Processing, 16 papers in Artificial Intelligence and 4 papers in Computer Vision and Pattern Recognition. Recurrent topics in Hemlata Tak's work include Speech Recognition and Synthesis (12 papers), Speech and Audio Processing (11 papers) and Music and Audio Processing (6 papers). Hemlata Tak is often cited by papers focused on Speech Recognition and Synthesis (12 papers), Speech and Audio Processing (11 papers) and Music and Audio Processing (6 papers). Hemlata Tak collaborates with scholars based in France, India and Finland. Hemlata Tak's co-authors include Massimiliano Todisco, José Patino, Nicholas Evans, Andreas Nautsch, Anthony Larcher, Nicholas Evans, Madhu R. Kamble, Jee-weon Jung, Ha-Jin Yu and Hee-Soo Heo and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Speech Communication and HAL (Le Centre pour la Communication Scientifique Directe).

In The Last Decade

Hemlata Tak

19 papers receiving 561 citations

Hit Papers

End-to-End anti-spoofing with RawNet2 2021 2026 2022 2024 2021 2022 50 100 150
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.

  1. End-to-End anti-spoofing with RawNet2
    2021 191 citations Hemlata Tak, José Patino et al. profile →
  2. AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks
    2022 156 citations Jee-weon Jung, Hee-Soo Heo et al. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) profile →

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Hemlata Tak France 10 472 461 182 51 15 19 592
Jee-weon Jung South Korea 15 600 1.3× 617 1.3× 150 0.8× 28 0.5× 12 0.8× 58 764
Hee-Soo Heo South Korea 11 485 1.0× 485 1.1× 106 0.6× 23 0.5× 10 0.7× 29 586
Hye-jin Shim South Korea 12 475 1.0× 444 1.0× 118 0.6× 22 0.4× 11 0.7× 22 560
Federico Alegre France 6 499 1.1× 504 1.1× 66 0.4× 53 1.0× 24 1.6× 10 579
Sergey Novoselov Russia 9 333 0.7× 324 0.7× 75 0.4× 19 0.4× 7 0.5× 24 398
Madhu R. Kamble India 13 418 0.9× 394 0.9× 70 0.4× 63 1.2× 26 1.7× 28 469
Galina Lavrentyeva Russia 6 256 0.5× 237 0.5× 83 0.5× 23 0.5× 8 0.5× 9 313
Xiaohai Tian Singapore 13 426 0.9× 469 1.0× 47 0.3× 37 0.7× 19 1.3× 41 515
Vishwa Gupta Canada 12 469 1.0× 427 0.9× 155 0.9× 5 0.1× 7 0.5× 45 589
Tanvina Patel India 9 301 0.6× 318 0.7× 38 0.2× 39 0.8× 24 1.6× 27 349

Countries citing papers authored by Hemlata Tak

Since Specialization
Citations

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

Fields of papers citing papers by Hemlata Tak

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Hemlata Tak

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

All Works

19 of 19 papers shown
1.
Sivaraman, Ganesh, Hemlata Tak, & Elie Khoury. (2025). Investigating voiced and unvoiced regions of speech for audio deepfake detection. 1–5. 1 indexed citations
2.
Delgado, Héctor, Hemlata Tak, Jee-weon Jung, et al.. (2024). ASVspoof 5: crowdsourced speech data, deepfakes, and adversarial attacks at scale. SPIRE - Sciences Po Institutional REpository. 1–8. 15 indexed citations
3.
Jung, Jee-weon, Nicholas Evans, Shinji Watanabe, et al.. (2024). To what extent can ASV systems naturally defend against spoofing attacks?. 3240–3244. 2 indexed citations
4.
Evans, Nicholas, et al.. (2024). Harder or Different? Understanding Generalization of Audio Deepfake Detection. Fraunhofer-Publica (Fraunhofer-Gesellschaft). 2705–2709. 1 indexed citations
5.
Kinnunen, Tomi, Kong Aik Lee, Hemlata Tak, Nicholas Evans, & Andreas Nautsch. (2023). t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators. IEEE Transactions on Pattern Analysis and Machine Intelligence. 46(5). 2622–2637. 1 indexed citations
6.
Ge, Wanying, Hemlata Tak, Massimiliano Todisco, & Nicholas Evans. (2023). Can Spoofing Countermeasure And Speaker Verification Systems Be Jointly Optimised?. 1–5. 1 indexed citations
7.
Shim, Hye-jin, Hemlata Tak, Xin Wang, et al.. (2023). Towards Single Integrated Spoofing-aware Speaker Verification Embeddings. 3989–3993. 5 indexed citations
8.
9.
Jung, Jee-weon, Hemlata Tak, Hye-jin Shim, et al.. (2022). SASV 2022: The First Spoofing-Aware Speaker Verification Challenge. Interspeech 2022. 2893–2897. 26 indexed citations
10.
Jung, Jee-weon, Hee-Soo Heo, Hemlata Tak, et al.. (2022). AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6367–6371. 156 indexed citations breakdown →
11.
Tak, Hemlata, Madhu R. Kamble, José Patino, Massimiliano Todisco, & Nicholas Evans. (2022). Rawboost: A Raw Data Boosting and Augmentation Method Applied to Automatic Speaker Verification Anti-Spoofing. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6382–6386. 44 indexed citations
12.
Tak, Hemlata, Orhan Ermiş, Madhu R. Kamble, et al.. (2021). Privacy-Preserving Voice Anti-Spoofing Using Secure Multi-Party Computation. HAL (Le Centre pour la Communication Scientifique Directe). 856–860. 1 indexed citations
13.
Tak, Hemlata, José Patino, Massimiliano Todisco, et al.. (2021). End-to-End anti-spoofing with RawNet2. 6369–6373. 191 indexed citations breakdown →
14.
Tak, Hemlata, José Patino, Andreas Nautsch, Nicholas Evans, & Massimiliano Todisco. (2020). Spoofing Attack Detection Using the Non-Linear Fusion of Sub-Band Classifiers. HAL (Le Centre pour la Communication Scientifique Directe). 1106–1110. 40 indexed citations
15.
Kamble, Madhu R., Hemlata Tak, & Hemant A. Patil. (2020). Amplitude and Frequency Modulation-based features for detection of replay Spoof Speech. Speech Communication. 125. 114–127. 16 indexed citations
16.
Tak, Hemlata, José Patino, Andreas Nautsch, Nicholas Evans, & Massimiliano Todisco. (2020). An Explainability Study of the Constant Q Cepstral Coefficient Spoofing Countermeasure for Automatic Speaker Verification. 333–340. 23 indexed citations
17.
Kamble, Madhu R., et al.. (2018). Novel Demodulation-Based Features using Classifier-level Fusion of GMM and CNN for Replay Detection. 4. 334–338. 3 indexed citations
18.
Tak, Hemlata & Hemant A. Patil. (2018). Novel Linear Frequency Residual Cepstral Features for Replay Attack Detection. 726–730. 21 indexed citations
19.
Kamble, Madhu R., Hemlata Tak, & Hemant A. Patil. (2018). Effectiveness of Speech Demodulation-Based Features for Replay Detection. 40 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

Breakdown of academic impact, for papers by Jee-weon Jung Breakdown of academic impact, for papers by Hee-Soo Heo Breakdown of academic impact, for papers by Hye-jin Shim Breakdown of academic impact, for papers by Federico Alegre Breakdown of academic impact, for papers by Sergey Novoselov Breakdown of academic impact, for papers by Madhu R. Kamble Breakdown of academic impact, for papers by Galina Lavrentyeva Breakdown of academic impact, for papers by Xiaohai Tian Breakdown of academic impact, for papers by Vishwa Gupta Breakdown of academic impact, for papers by Tanvina Patel
Rankless by CCL
2026