Engr. Dr. Nasir Saleem (Assistant Professor)


  • Postdoctorate Fellow Neural Speech and Audio Processing (Islamic International University, Malaysia).
  • Ph.D. Electrical Engineering (University of Engineering & Technology, Peshawar, Pakistan).
  • M.Sc Electrical Engineering (CECOS University of IT & Emerging Sciences, Peshawar, Pakistan).
  • B.Sc Telecommunication Engineering (University of Engineering & Technology, Peshawar, Pakistan).

Email: nasirsaleem@gu.edu.pk

Contact: +92-333-0613347

Research Group Audio and Speech Processing With Deep Learning (ASPDL)

Research Interests

My main research interests are in the area of Audio/Speech Processing and Deep Learning. During my Ph.D the focus was to build intelligent models that can tackle challenging audio and speech processing problems. More specifically, I was interested in designing learning models to analyze speech enhancement and speech recognition systems. My current research includes working on Speech Synthesis, Visual Speech Recognition (VSR), Speech Emotion Recognition (SER), Audio-Visual Speech Enhancement/Recognition systems and deep learning models. I have published 51 Journal articles and conferences. 04 are under peer review process. My current research areas are:

  • Robust Neural Models for Speech Enhancement (Audio-Only/Audio-Video).
  • High-Performance Neural Model for Speech Processing (Emotion Recognition/Speech Recognition).
  • Neural Speech Synthesis from Silent Videos.
  • Neural Video Processings.

Selected Publications

  1. E2E-DASR: End-to-end deep learning-based dysarthric automatic speech recognition, Expert Systems with Applications.
  2. DeepCNN: Spectro‐temporal feature representation for speech emotion recognition, CAAI Transactions on Intelligence Technology.
  3. NSE-CATNet: Deep Neural Speech Enhancement using Convolutional Attention Transformer Network. IEEE ACCESS.
  4. E2E-V2SResNet: Deep residual convolutional neural networks for end-to-end video driven speech synthesis. Image and Vision Computing.
  5. DeepResGRU: Residual gated recurrent neural network-augmented Kalman filtering for speech enhancement and recognition. Knowledge-Based Systems.