Muhammad Shehryar Khan

Papers

Total Citations

H-Index

About

Muhammad Shehryar Khan is a pioneering researcher in speech emotion recognition (SER) and natural language processing, with a particular focus on under-resourced languages. His most notable contribution is the creation of SEMOUR (Scripted Emotional Speech Repository for Urdu), the first scripted emotional speech dataset for the Urdu language, which has garnered 11 citations since its publication in 2021. This foundational work addresses a critical gap in SER research, where most datasets exist only for languages like English, German, and Italian. By providing a reliable, scripted corpus for Urdu, Khan has enabled the development of more accurate and culturally relevant emotion recognition systems, opening doors for applications in mental health monitoring, human-computer interaction, and multilingual AI. His work highlights the importance of linguistic diversity in machine learning and has inspired further research into low-resource language processing. Khan’s contributions are particularly impactful for students and researchers interested in bridging the gap between high-resource and under-resourced languages, demonstrating how targeted dataset creation can drive innovation in affective computing and speech technology.