Papers
1
Total Citations
55
H-Index
1
About
Huma Israr is a researcher whose work sits at the intersection of speech processing and machine learning, with a particular focus on making automatic speech recognition systems more resilient in real-world conditions. Her most impactful contribution, the 2020 paper "Incorporating Noise Robustness in Speech Command Recognition by Noise Augmentation of Training Data," has garnered 55 citations and addresses a critical challenge: how to ensure voice-controlled devices understand commands accurately even in noisy environments. By demonstrating that augmenting training data with diverse noise profiles can significantly improve model performance, Israr provided a practical, data-driven solution that has informed subsequent work in robust speech recognition. Her research is especially relevant to the development of smart assistants, hearing aids, and hands-free interfaces, where reliability under acoustic variability is paramount. Through her focus on noise robustness and data augmentation strategies, Huma Israr has contributed a valuable methodology that helps bridge the gap between controlled laboratory conditions and the unpredictable acoustic landscapes of everyday life.
Research Focus
Key Achievements
Top Papers
- 1