Mohamed Seghir Boumaza

Papers

Total Citations

H-Index

About

Mohamed Seghir Boumaza is a researcher whose work sits at the intersection of robotics, artificial intelligence, and human-computer interaction, with a particular focus on voice-controlled systems. His most-cited paper, "Voice command system based on pipelining classifiers GMM-HMM" (2012, 5 citations), introduces a novel hybrid classification method that pipelines Gaussian Mixture Models and Hidden Markov Models to enhance speech recognition for robotic control. This work demonstrates his key contribution: improving the accuracy of voice-guided robotic systems by investigating feature combination techniques and showing that increasing the number of acoustic features significantly boosts recognition rates. Boumaza's research has practical implications for assistive technologies and industrial automation, where reliable voice commands can streamline human-robot collaboration. While his citation count reflects a focused, early-career impact, his methodological approach—pipelining classifiers for robust performance—offers a valuable foundation for students and researchers exploring multimodal interaction systems. His work underscores the importance of feature engineering in achieving real-world voice control reliability.