Acoustics Lab

A Center of Spoken Language and Acoustics Signal Processing

Welcome to the Acoustics Lab! The lab was established in 2019, with research interests in audio signal processing, spatial audio reality, and sound perception.

We, at ITU Lahore, are working on Sound signals processing and speech perception. We are in pursuit of prime datasets collection to fashion an across the board speech emotion recognition (SER) system. Our work is highly research-oriented that leads to many important applications like personalized robot assistants, diagnosis of psychological disorders, and getting feedback from a low-tech-enabled population. Currently, we are working on speaker profiling, multi-lingual SER, and domain adapted and domain generalized SER.

Dr. Mudassir Shabbir is an Assistant Professor at Information Technology University, Lahore. He leads the TheoryGroup and the Acoustics Lab. He is also the Director of Crime Investigation and Prevention Lab (CIPL) at ITU, Lahore. His research interests include Algorithmic and Discrete Geometry, Combinatorics, Extremal Graph Theory, and Machine Learning with Graphs. Dr. Mudassir Shabbir received his Ph.D. from the Division of Computer Science, Rutgers University, NJ USA. 

Nimra Zaheer

PhD fellow, TheoryGroup

Obaid Ullah Ahmad

Research Assistant, TheoryGroup

Ammar Ahmad

Research Assistant, TheoryGroup

Shehryar Khan

Research Assistant, TheoryGroup

SEMOUR: A Scripted Emotional Speech Repository for Urdu. N. Zaheer, O. Ahmad, A. Ahmed, S. Khan and M. Shabbir, International conference of Human Computer Interaction (CHI), 2021 [Archive Link]

The Scripted Emotional Speech Repository for Urdu (SEMOUR) is the first scripted database of emotion-tagged speech in the Urdu language. This gender-balanced dataset contains 15, 040 unique instances recorded by eight actors eliciting a syntactically complex script.