Papers
1
Total Citations
3
H-Index
1
About
Rashid Khan is a researcher specializing in speech signal processing, with a particular focus on single-channel speech separation and dictionary learning techniques. His most notable contribution, the 2022 paper "Dual transform based joint learning single channel speech separation using generative joint dictionary learning," introduces an innovative dual-transform framework that integrates generative joint dictionary learning to enhance the separation of overlapping speech signals from a single microphone input. This work, which has garnered 3 citations, addresses a critical challenge in audio processing—isolating individual speakers in noisy, multi-talker environments—with potential applications in hearing aids, telecommunications, and voice-activated systems. Khan’s approach leverages the synergy between time-frequency transforms and learned dictionaries, offering a more robust and adaptive solution compared to traditional methods. Though early in his career, his research demonstrates a strong commitment to advancing machine learning-driven audio enhancement. His work is particularly relevant for students and researchers exploring deep learning architectures for source separation, as it highlights the promise of joint optimization strategies in improving speech intelligibility and system performance.
Research Focus
Key Achievements
Top Papers
- 1