I am currently a Research Scientist at 3M Health (Solventum) in the Speech Research and Development group. Our team’s research is focused on developing AI-driven healthcare solutions that leverage advanced speech and natural language processing (NLP) technologies to automate clinical visit workflows, enabling doctors to reduce documentation burden and focus more on patient care.

RESEARCH:

• Machine Learning (2019 - present)
  • Core machine learning: Confidence calibration of neural networks, reliable and trustworthy AI (NeurIPS 2022)
  • Speech: Self-supervised learning; Transducer-based ASR; Joint ASR and Speaker-Role Diarization (Interspeech 2025); low-resource, low-footprint wake-word detection (Interspeech 2022)
  • NLP: Automatic summarization of doctor-patient conversations (EMNLP 2021)
• Wireless Communication (2012 - 2018)
  • Interference modeling in wireless networks (IEEE Communication Letters 2017 and 2018)
  • Error correction and automatic repeat request (ARQ) schemes for underwater wireless sensor networks (Sensors 2013)
  • Signal modulation schemes for free-space optical communication (IEEE SPCOM 2014)

EDUCATION:

• Master of Science in Electrical and Computer Engineering, Carnegie Mellon University, USA (2019 - 2019)
• Bachelor of Technology in Electronics and Communication Engineering, NIT Durgapur, India (2009 - 2013)

REVIEWER:

• IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2026
• Neural Information Processing Systems (NeurIPS) 2025 (Top Reviewer award)
• INTERSPEECH 2025
• IEEE Spoken Language Technology Workshop (SLT) 202