Showing cs.SDShow all
2 papers · 1 filter
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…
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…