Ameenudeen P E

I am a PhD student at the Department of Electrical Engineering, Indian Institute of Science, Bangalore. I work as an Assistant Professor in the Department of Electronics and Communication Engineering, College of Engineering Trivandrum.

I am working with Dr. Sriram Ganapathy, on the applications of Deep Learning for various speech processing applications. I am associated with the wonderful group of people (and researchers) at LEAP Lab.

I am curious about how machines can learn meaningful, efficient, and generalizable representations from audio,particularly representations that enable robust audio encoders and support a wide range of speech and acoustic understanding tasks. I am particularly interested in building self-supervised audio encoders and small audio language models from scratch, including their end-to-end pre-training, architectural design, and learning objectives. My research also explores discrete audio codecs and their role in compact audio modeling. I am deeply intrigued by the mathematical foundations of machine learning, especially information theory, probability, linear algebra, calculus, and communication theory, and by how these principles can guide the development of more efficient and principled audio learning systems.

I remain open to discussions and collaborations with researchers and practitioners working in deep learning, large language models, information theory, and related areas, and I welcome the opportunity to mentor students who wish to pursue research in these directions. If you would like to connect, please feel free to write to me at ameenudeen@cet.ac.in.