Mohammad Shami

About

Mohammad Shami is a leading researcher in affective computing and speech emotion recognition, with a focus on the robustness and generalizability of machine learning approaches. His seminal 2007 work, "An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech," has garnered 131 citations, establishing a critical benchmark for evaluating how well emotion classification systems perform across different datasets and conditions. Shami’s research addresses the fundamental challenge of expressiveness in speech, as demonstrated in his multi-corpus study on automatic classification of expressiveness, which has been cited 54 times. By systematically testing the limits of supervised learning methods, he has provided essential insights into the reliability of emotion recognition technologies, influencing subsequent developments in human-computer interaction and affective systems. His work is notable for its rigorous methodological approach, emphasizing the importance of cross-corpus validation to ensure real-world applicability. Shami’s contributions have helped shape the field’s understanding of how to build more resilient and accurate emotion classification systems, making him a key figure in advancing speech-based affective computing.

Research Focus

Key Achievements

Top Papers

1. 1
   An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech

   131 citations · 2007
2. 2
   Automatic Classification of Expressiveness in Speech: A Multi-corpus Study

   54 citations · 2007

Key Collaborators

Contact & Links