Human Language Technology

Rohan Kumar Das

Research Fellow


Personal Profile:

Rohan Kumar Das received Ph.D degree from Indian Institute of Technology (IIT) Guwahati in the year 2017 and Bachelor of Technology degree in Electronics and Communication Engineering from North-Eastern Hill University (NEHU), Shillong, India in the year 2010. His Ph.D. work focused on speaker verification using short utterances from the perspective of practical application oriented systems. Prior to his research in the field of speech processing, he has been a Project Scientist at Assam Science Technology and Environment Council from 2010 to 2011. After completing doctoral studies, he worked as a Data Scientist in a multinational company called Kovid Research Labs (now acquired by Kaliber Labs) and involved in speech analytics based application services in 2017. Currently, he is a Research Fellow at Human Language Technology Laboratory, National University of Singapore and continuing postdoctoral research work. He is one of the organizers for special sessions on “The Attacker’s Perspective on Automatic Speaker Verification”, “Far-Field Speaker Verification Challenge 2020” at Interspeech 2020, and the Voice Conversion Challenge 2020. He has been awarded several travel fellowships from organizations such as IEEE Signal Processing Society, International Speech Communication Association, Microsoft Research India, Xerox Research Centre India and Science and Engineering Research Board (SERB), Government of India to present research works in top tier conferences such as ICASSP and Interspeech. He has published over 70 research papers in peer-reviewed journals and conferences. He is a Senior Member of IEEE, a member of ISCA and APSIPA.


  • Neuromorphic Computing
  • Text-dependent Speaker Verification and Identification
  • Anti-spoofing of Voice Print Systems
  • Speech Synthesis and Synthetic Speech Detection

Research interests

  • Speech & audio signal processing
  • Speaker verification
  • Anti-spoofing
  • Machine learning and pattern recognition