Welcome!
Hello! I am A F M Saif, a Ph.D. student at Rensselaer Polytechnic Institute (RPI). I have a background in Electrical and Electronic Engineering from BUET, where I graduated in 2018. My current research focuses on Machine Learning, Automatic Speech Recognition (ASR), and Optimization. I am fortunate to be guided by Professor Tianyi Chen.
📖 Education
- 2023 - Present: Ph.D. in Computer & Systems Engineering, Rensselaer Polytechnic Institute
- 2013 - 2018: BSc in Electrical and Electronic Engineering, BUET
💬 Current Project
- 2023 - Now: Applications: Machine learning, speech processing, LLM alignment for speech data, generative AI, and foundation models. Theory: Mathematical optimization including distributed, bilevel, multi-objective optimization, and nonconvex optimization for high-dimensional statistical learning.
🗣️ Recent News
-
December 2024: Our paper is accepted to IEEE/ACM Transactions on Audio, Speech, and Language Processing 🥳🥳🥳
Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition -
September 2024: Our paper is accepted to NeurIPS 2024 🥳🥳🥳
FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning - June 2024: Our paper is accepted to INTERSPEECH 2024 🥳🥳🥳
multilingual speech recognition, speech-to-text translation, multi-objective learning, multi-task learning - Dec 2023: Our paper is accepted to ICASSP 2024 🥳🥳🥳
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
📝 Publications
Journal Papers
- Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition
- CapsCovNet: A Modified Capsule Network to Diagnose COVID-19 From Multimodal Medical Imaging
- Abnormality Detection in Musculoskeletal Radiographs Using Capsule Network
- Exploiting Cascaded Ensemble of Features for the Detection of Tuberculosis Using Chest Radiographs
Conference Papers
- Accepted to NeurIPS 2024: FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
- Accepted to INTERSPEECH 2024: multilingual speech recognition, speech-to-text translation, multi-objective learning, multi-task learning
- Accepted to ICASSP 2024: Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
Feel free to explore my website to learn more about my research, projects, and achievements. Let’s embark on this intellectual adventure together!