Profile Picture

Dr. Nagarathna Ravi

Senior Scientist, Department of Big Data Research and Supercomputing Division

CSIR National Institute of Data Science and AI

Bengaluru, India

Email: rathna (.) 4pi (AT) csir (.) res (.) in

Office location: Cabin No: C1, Room No. 308, Network Building, CSIR, National Institute of Data Science and AI, NAL Belur campus, Karnataka Pin: 560037 India

About Me:

My research focuses on the development of learning-based methods for speech and language systems, network security, and generative AI. I am particularly interested in research in these areas, with a strong emphasis on real-world applications.

Key Contributions:

  • Speech and Language Systems: Encompasses automatic speech recognition, language modeling, and applications in low-resource languages and sign language.
  • Trustworthy AI: Covers uncertainty estimation and explainable machine learning models across various applications.
  • Generative AI: Involves research in video synthesis and image generation.
  • Network Security: Involves AI-driven security models for intrusion detection, anomaly detection, and cyber defense.
  • Information Retrieval: Includes representation learning for identifying similar patterns in text, speech, and video data.
  • Human-Machine Collaboration: Focuses on enhancing interaction between humans and machines through AI techniques such as active learning.

Education & Postdoctoral Research:

I completed my B.Tech. from Madras Institute of Technology, Anna University, followed by an M.E. from Thiagarajar College of Engineering, and a Ph.D. in Network Security from Anna University. After completing my doctoral studies, I pursued postdoctoral research at IIT Kanpur, where I focused on automatic speech recognition. My work there included improving speech modeling, low-resource language transcription, confidence estimation, and active learning.

Current Research Interests:

Core Areas:

  • Speech and Language Processing
  • Generative AI
  • Trustworthy AI
  • Network Security
  • Information Retrieval

Applications:

  • Automatic Speech Recognition (ASR)
  • Large Language Models (LLMs)
  • Text-to-Speech (TTS)
  • Natural Language Processing (NLP)
  • Sign Language Processing
  • Video/Image Generation
  • Uncertainty Estimation
  • AI for Cybersecurity (Intrusion Detection and Anomaly Detection)
  • Information Retrieval (Text, speech, and video search)
  • Human-Machine Learning and Collaboration