Embedded Files
Picture Taken at - Coex Auditorium, ICASSP -2024, Seoul
Muhammad Sudipto Siam Dip
Muhammad Sudipto Siam Dip
Research Interest: Biomedical Signal Processing and Imaging, Audio Signal Processing, Deep Learning, Computational Neuroscience, Wearable Devices for Healthcare Monitoring
Expertise: Electroencephalogram (EEG) Signal Processing, Audio Signal Processing, Deep Learning
Muhammad Sudipto Siam Dip is a researcher specializing in machine learning and signal processing. He earned his Bachelor’s degree in Electrical and Electronic Engineering (EEE) from Rajshahi University of Engineering & Technology (RUET), one of the top engineering universities in Bangladesh. During his undergrad years, he served as an undergraduate research assistant in the Signal Processing and Machine Learning (SPML) Lab at RUET.
He is currently conducting his research on automatic sleep stage scoring using PSG signals, with a focus on building interpretable and explainable models for human-centered AI. Previously, He worked on sleep apnea detection using ECG signals.
His broader interests include TinyML, interpretable AI, and developing resource-efficient ML systems for deployment in clinical and low-resource settings. He was awarded 3rd place at the IEEE Signal Processing Cup 2024 World Finals, held at ICASSP in Seoul, South Korea. He was also featured by Mathworks in their Winners Circle for his contributions to the field of signal processing.
Outside of research, he has volunteered with IEEE, served as a departmental representative, and completed an internship at Think Ltd., Bangladesh. During his free time, he plays musical instruments.
He is always open to discussions—whether it’s about collaborative research, technology for healthcare, or just a good cup of coffee!
Email: siamdip13@gmail.com
My Profiles:
📰 Recent News
📰 Recent News
Our recent research titled "Cognitive Workload Classification Using Electroencephalogram Signal" is now published and available in IEEE Xplore.
🔗 Link to the document: https://doi.org/10.1109/ICCIT64611.2024.11022139
Our recent research titled "DeepApneaNet: A Multistage CNN-Bi-LSTM Hybrid Model for Sleep Apnea Detection From Single-Lead ECG Signal" is now published in IEEE Sensors Letters and available in IEEE Xplore.
🔗Link to the document: https://ieeexplore.ieee.org/abstract/document/10955462
Team Pseudo Spectrum from RUET became 2nd Runner Up (Global Finalist) at the IEEE Signal Processing Cup 2024 at ICASSP, Seoul, South Korea.
Task: “ROBOVOX: Far-Field Speaker Recognition by a Mobile Robot”
Team Name – Team Pseudo Spectrum, RUET
Team Pseudo Spectrum became 1st Runner Up at Project Showcasing, EEE Day, RUET Project Name: AI-based personalized health monitoring system: Instant feedback on cardiac & respiratory health.
🔗Find More: EEE Day 2023 , Code: Project Code
Constructed a framework that can perform photoplethysmography(PPG) signal acquisition and processing simultaneously and estimate insights such as CO2 respiratory level and heart rate with the help of deep learning. We also developed an IoT-based telemetry system to show the feedback to the subject's cell phone in real-time via a mobile app.
Team SP Cup 2024 - 3rd position Winner paper is now available in arXiv
🔗DOI: https://arxiv.org/pdf/2409.10240
In this study, we address the challenge of speaker recognition using a novel data augmentation technique of adding noise to enrollment files. This technique efficiently aligns the sources of test and enrollment files, enhancing comparability. Various pre-trained models were employed, with the Resnet model achieving the highest DCF of 0.84 and an EER of 13.44. The augmentation technique notably improved these results to 0.75 DCF and 12.79 EER for the Resnet model. Comparative analysis revealed the superiority of Resnet over models such as ECPA, Mel-spectrogram, Payonnet, and Titanet large. Results, along with different augmentation schemes, contribute to the success of RoboVox far-field speaker recognition in this paper.
Featured in Mathwork’s Winner Circle 2024, Signal Processing
Featured in Mathwork’s Winner Circle 2024, Signal Processing
The MathWorks Winner’s Circle is a recognition program that highlights outstanding student projects and competition teams that use MATLAB and Simulink. These teams participate in various technical fields such as automotive design, aerospace engineering, robotics, and more. The program showcases their innovative projects, raw talent, and the effective use of MathWorks tools to achieve success in global competitions.
Page updated
Google Sites
Report abuse