Papers
2
Total Citations
34
H-Index
2
About
Shelza Dua is a researcher at the forefront of speech processing and industrial automation, whose work bridges the gap between robust audio technology and the demands of Industry 4.0. Her primary research areas include noise-robust automatic speech recognition (ASR) and automatic speaker verification (ASV) systems, with a focus on making these technologies practical for real-world, noisy environments. Dua’s most impactful contribution is her comprehensive review and analysis of noise-robust ASR, which has garnered 29 citations and serves as a critical resource for researchers tackling the challenge of speech recognition in adverse acoustic conditions. Additionally, her work on audio classification models for ASV systems—cited 5 times—directly addresses the growing need for reliable biometric identification in automated industrial settings, where robots and machines increasingly rely on voice commands and speaker verification. By exploring how speech processing can streamline production tasks and enhance security in smart factories, Dua is helping to shape the future of human-machine interaction. Her research is particularly notable for its practical orientation, offering solutions that are not only theoretically sound but also deployable in the noisy, dynamic environments of modern industry.
Research Focus
Key Achievements
Top Papers
- 1Noise robust automatic speech recognition: review and analysis29 citations · 2023
- 2