Research | Sabbir Ahmed

Current Research Areas:

Motion Compensation in Free Breathing Pulmonary MRI
Medical Imaging and Machine Learning
Algorithm Development and Optimizations
Inverse Problems and MR Image Reconstruction

Research Interests:

My research interests broadly lies in the area of Signal Processing and Deep Learning. Some of the areas I wish to work are:

Audio Signal Processing, Signal Denoising, Speech Enhancement, Speech Recognition, Speaker Recognition, Speech Disorder, Speech Emotion Recognition, Speaker Diarization.
Image Recognition, Image Processing, Medical Imaging, Image Segmentation.
Sentiment and Emotion Analysis, QA Answering, Conversational AI.
Multimodal Signal Processing (combining textual, acoustic & visual features) to build intelligent system.
Audio Steganalysis, Audio Steganography, DeepFake Detecion.

Publications:

2021

IEEE

Cochleagram based speaker identification using noise adapted CNN

Sabbir Ahmed, Nursadul Mamun, and Md Azad Hossain

In 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2021

Bib

@inproceedings{ahmed2021cochleagram,
  title = {Cochleagram based speaker identification using noise adapted CNN},
  author = {Ahmed, Sabbir and Mamun, Nursadul and Hossain, Md Azad},
  booktitle = {2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT)},
  pages = {1--5},
  year = {2021},
  organization = {IEEE}
}