Distillation-Based Layer Dropping (DLD): Effective end-to-end Framework for Dynamic Speech Networks
Proceedings of the 51st IEEE International Conference on Acoustics, Speech, and Signal Processing
Assistant Professor
Shah Nawaz
Johannes Kepler University Linz
About
I am an assistant professor at Johannes Kepler University - JKU. Prior to it, I was a researcher at IMEC, Leuven Belgium. Moreover, I was a post doctorate at Italian Institute of Technology, Genova, Italy and Deutsches Elektronen-Synchrotron DESY, Hamburg, Germany I explore deep learning and computer vision with focus on combining multiple modalities in multimodal settings.
Research output
Publications
Face-Voice Association with Inductive Bias for Maximum Class Separation
Proceedings of the 51st IEEE International Conference on Acoustics, Speech, and Signal Processing
Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challenge
Proceedings of the 51st IEEE International Conference on Acoustics, Speech, and Signal Processing
Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning
Proceedings of the 1st Workshop on Applied AI and Multimodal Visualization Technologies
SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions
Proceedings of the IEEE International Conference on Image Processing (ICIP)
An Effective Training Framework for Light-Weight Automatic Speech Recognition Models
Proceedings of the Annual Conference of the International Speech Communication Association
BreastCare application: Moroccan Breast cancer diagnosis through deep learning-based image segmentation and classification
BreastCare application: Moroccan Breast cancer diagnosis through deep learning-based image segmentation and classification
Development of a bilingual healthcare chatbot for pregnant women: A comparative study of deep learning models with BiGRU optimization
Development of a bilingual healthcare chatbot for pregnant women: A comparative study of deep learning models with BiGRU optimization
ESC-UNET: A hybrid CNN and Swin Transformers for skin lesion segmentation.
ESC-UNET: A hybrid CNN and Swin Transformers for skin lesion segmentation
First International Workshop on Data Quality-Aware Multimodal Recommendation (DaQuaMRec)
RecSys '25: Proceedings of the Nineteenth ACM Conference on Recommender Syste
Music4All A+A: A Multimodal Dataset for Music Information Retrieval Tasks
Proceedings of the 22nd IEEE International Conference on Content-based Multimedia Indexing (CBMI 2025)
PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association
Proceedings of the Annual Conference of the International Speech Communication Association
Parameter-Efficient Single Collaborative Branch for Recommendation
Proceedings of the Nineteenth ACM Conference on Recommender Systems
Single-Branch Network Architectures to Close the Modality Gap in Multimodal Recommendation
ACM Transactions on Recommender Systems
A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarios
Proceedings of the 18th ACM Conference on Recommender Systems (RecSys)
A Synopsis of FAME 2024 Challenge: Associating Faces with Voices in Multilingual Environments
Companion of the 32nd ACM International Conference on Multimedia (MM)
Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Single Stage Adaptive Multi-Attention Network for Image Restoration
IEEE Transactions on Image Processing