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, audio search)
• Human-Machine Learning and Collaboration