Profile picture

Eklavya Sarkar

Nationalité: Swiss

EPFL STI IEM LIDIAP
ELD 241 (Bâtiment ELD)
Station 11
1015 Lausanne

EPFLSTIIEMLIDIAP

Site web: https://idiap.epfl.ch/

Expertise

- Deep Learning, Self-Supervised Learning, Representation Learning.
- Speech and Audio Processing, Bioacoustics, Animal vocalizations.
- Generative Adversarial Networks, Deepfakes, Face Morphing.
- Kohonen Self-Organizing Maps.

Expertise

- Deep Learning, Self-Supervised Learning, Representation Learning.
- Speech and Audio Processing, Bioacoustics, Animal vocalizations.
- Generative Adversarial Networks, Deepfakes, Face Morphing.
- Kohonen Self-Organizing Maps.
Eklavya Sarkar is currently a Research Assistant and Doctoral Student at EPFL, working in the Speech and Audio Processing group at Idiap Research Institute, under the supervision of Dr. Mathew Magimai Doss. His project is funded by the SNSF's NCCR Evolving Languages project, under the Automatic Speech Recognition (ASR) Work Package of the Transversal Task Force (TTF) Technology.
Previously, he was a Research Intern in the Biometrics Security and Privacy lab at Idiap, under Dr. Sébastien Marcel, working on the Generation, Detection, and Vulnerability Analysis of Face Recognition Systems to Face Morphing Presentation Attacks, particularly on novel methods involving StyleGAN2.
He also worked as an intern at CERN, under Dr. Archana Sharma, on the 'CMS-GEM' collaboration at the CMS Experiment Lab.
He was affiliated with Prof. and Nobel Laureate Didier Queloz and supervised by Dr. Daniel Kessler for a project on Exoplanets during high-school, which was selected for the TM-TPE Colloque Transfrontalier 2013, also at CERN.
He holds:
  • MSc in Data Science from the University of Bath (2018-19), with a thesis supervised by Dr. Wenbin Li.
  • BSc in Computer Science from the University of Liverpool (2015-18), with a thesis supervised by Dr. Irina Biktasheva.

  • He is a Swiss citizen who grew up in Geneva, Switzerland after moving from New Delhi, India at the age of 10. In his free time he enjoys making and publishing silly indie games made on Unity, Swimming, Skiing, and holds a diploma in Film-Making from Brighton Film School.

Formation

PhD

| Machine Learning

2021 – 2021 EPFL

MSc

| Data Science

2018 – 2018 University of Bath

BSc

| Computer Science

2015 – 2015 University of Liverpool

Expériences professionnelles

Research Assistant

Research Intern

Intern

Publications représentatives

On feature representations for marmoset vocal communication analysis

E. Sarkar, K. Wierucka, A. B. Bosshard, J. M. Bukart, M. Magimai Doss
Published in Bioacoustics Journal in

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

E. Sarkar, M. Magimai Doss
Published in Interspeech 2024 in

Feature Representations for Automatic Meerkat Vocalization Classification

I. Ben Mahoud, E. Sarkar, M. Magimai Doss
Published in Interspeech 2024 in

Are GAN-based Morphs Threatening Face Recognition?

E. Sarkar, P. Korschunov, L. Colbois, S. Marcel
Published in ICASSP 2022 in

Vulnerability Analysis of Face Morphing Attacks from Landmarks and Generative Adversarial Networks

E. Sarkar, P. Korschunov, L. Colbois, S. Marcel
Published in ArXiv in

Recherche

Research Summary

The Swiss National Centre of Competence in Research (NCCR) Evolving Language is a nationwide interdisciplinary research consortium bringing together research groups from the humanities, from language and computer science, the social sciences, and the natural sciences at an unprecedented level. Together, we aim at solving one of humanity's great mysteries: How did our species develop the ca­pa­city for linguistic expression, for processing language in the brain, and for con­sist­ently passing down new variations to the next generation? How will our capacity for language change in the face of digital com­munication and neuroengineering?
The NCCR Evolving Language explores the evolutionary origins and future development of linguistic communication with an unprecedented transdisciplinary research programme. We conceptualise language as a system of components with distinct evolutionary trajectories and adopt a large-scale comparative framework to study these trajectories in nature and function along three thematic axes. These three lines of research are complemented by Transversal Task Forces (TTFs). TTFs will stimulate interdisciplinary collaboration by sharing methods, databases, technologies, and equipment and by fostering NCCR-wide discussions on conceptual and ethical issues.

Enseignement et PhD

Reviewer

- IEEE Signal Processing Letters
- IEEE Transactions on Technology and Society
- Hindawi Journal of Mathematics

Teaching Assistant

UniDistance's Master in Artificial Intelligence:
- 2021-24: M09 Introduction to Speech Processing (4 ETCS)