The Audio and Speech Processing with Deep Learning (ASPDL) Group is a team of young researchers focused on basic and applied research within the area of Digital Speech Processing. The group is mainly focused on modern deep-learning models for processing single and multimodal speech signals, observed through a single sensor. From the application point of view, the group is mainly interested in the processing of audio and biomedical signals for various real-time speech applications. 

Research Grants and Collaborations:

1. Co-Principle Investigator with Princess Nourah Bint Abdulrahman University on an AI-Driven Real-Time Processing in Application to Speech Enhancement \& Joint Optimization for ASR Systems Project (Grant No: RPFAP-30-1445)

2. Co-Principle Investigator with Princess Nourah Bint Abdulrahman University on a Deep Neural Networks-based Multimodal Prediction of Alzheimer’s Disease and Its Progression Systems Project (Grant No: RPFAP-75-1445).

3. Supervised the Deep Neural Network-based COVID-19 Mask and Temperature Detection, Funded by National ICT RD, Ministry of IT, Government of Pakistan.

4. Collaborating with the National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China, on real-time speech enhancement systems on embedded systems using compact neural models.

5. Collaborating with the Texas Instruments DSP Joint Laboratory, School of Electrical and Information Engineering, Tianjin University, China, on speech enhancement systems using novel neural models. 

6. Research Fellow in Towards Cognitively Inspired 5G-IoT Enabled, Multi-Modal Hearing Aids (COG-MHEAR, EPSRC Programme Grant (2021-2026) (EP/T021063/1).