Tarek Hasan Al Mahmud
Papers
1
Total Citations
3
H-Index
1
About
Tarek Hasan Al Mahmud is a researcher advancing the field of speech processing, with a focus on single-channel speech separation and dictionary learning. His work addresses the challenging problem of isolating individual speech signals from mixed audio recordings, a critical task for applications in hearing aids, voice-controlled systems, and telecommunications. Al Mahmud’s key contribution is the development of a dual transform-based joint learning framework, which leverages generative joint dictionary learning to enhance separation performance. This approach integrates multiple signal representations to capture both temporal and spectral features, enabling more robust and accurate speech separation in noisy environments. His most-cited paper, “Dual transform based joint learning single channel speech separation using generative joint dictionary learning” (2022), has garnered 3 citations, reflecting its emerging impact in the field. By pushing the boundaries of dictionary learning and transform-based methods, Al Mahmud is contributing to more intelligent and adaptive audio processing systems, with potential to improve real-world speech technologies. His work represents a promising step toward clearer communication in complex acoustic settings.
Research Focus
Key Achievements
Top Papers
- 1