3 papers
cs.SD2026
CIS-BWE: Chaos-Informed Speech Bandwidth Extension
Tarikul Islam Tamiti, Tonmoy Das, Nursadul Mamun +1
Recovering high-frequency components lost to bandwidth constraints is crucial for applications ranging from telecommunications to high-fidelity audio on limited resources. We intro…
eess.AS2026
DAT-CFTNet: Speech Enhancement for Cochlear Implant Recipients using Attention-based Dual-Path Recurrent Neural Network
Nursadul Mamun, John H. L. Hansen
The human auditory system has the ability to selectively focus on key speech elements in an audio stream while giving secondary attention to less relevant areas such as noise or di…
cs.SD2025
A High-Fidelity Speech Super Resolution Network using a Complex Global Attention Module with Spectro-Temporal Loss
Tarikul Islam Tamiti, Biraj Joshi, Rida Hasan +4
Speech super-resolution (SSR) enhances low-resolution speech by increasing the sampling rate. While most SSR methods focus on magnitude reconstruction, recent research highlights t…