Dr Ahmad Salman
Assistant Professor
Department of Electrical Engineering

School of Electrical Engineering and Computer Science (SEECS)
National University of Sciences and Technology (NUST)
NUST Campus H-12, Islamabad
Tel: 051-90852559
Email: ahmad.salman at seecs.edu.pk
Web: http://seecs.nust.edu.pk/faculty/ahmadsalman.html

Machine learning, speech information processing

PhD Computer Science – Machine Learning, Speech Information Processing – University of Manchester, United Kingdom (2011)

Research Experience

Assistant Professor, SEECS
January 2015 – January 2015 ()

Details: Research Interests

Deep Learning
Neural Networks
Speech Processing
Computer Vision

Current Research Projects

- Forensic Speaker Recognition
- Generic Object Recognition Using Deep Architecture
- Robust Fish Specie Classification with Deep Hierarchical Learning

Previous Select Projects

- Object Detection & Categorization for Blind Using Deep Architecture.
- Text Narrator for Visually Impaired People.
- Human-Computer Interface Using Electroencephalographic (EEG) Signals.

Research Collaborations

University of New South Wales, Australia (Current)
University of Manchester, UK (Previous)

Research Lab

PAI-Research, SEECS

Journal Papers

Ahmad Salman, Ahsan Jalal, Faisal Shafait, Ajmal Mian, Mark Shortis, James Seager and Euan Harvey, "Fish species classification in unconstrained underwater environment based on deep learning", Limnology and Oceanography: Methods, May, 2016.

K. Chen,A. Salman, "Learning speaker-specific characteristics with a deep neural architecture", IEEE Trans. Neural Networks, Vol. 22, No. 11, pp. 1744-1756, 2011.

K. Shah,A. J. Pinkerton, A. Salman, L. Li, "Effects of melt pool variables and process parameters in laser direct metal deposition of aerospace alloys", Materials and Manufacturing Processes, Vol. 22, No. 12, pp. 1372-1380, 2010.

Conference Papers

K. Chen,A. Salman, "Extracting speaker-specific information with a regularized Siamese deep network", Proceedings of the NIPS, pp. 1-9, 2012, Granada Spain.

A. Salman,K. Chen, "Exploring speaker-specific characteristics with deep learning", Proceedings of the IJCNN, pp. 103-110, 2011, San Jose United States.

A. Salman, M. Ejaz, K. Khurshid, "Speaker verification using boosted cepstral features with Gaussian distributions", Proceedings of the INMIC, pp. 1-5, 2007, Lahore Pakistan.

A. Salman,M. Ejaz,K. Khurshid, "A subspace approach for speech enhancement using frame-level AdaBoost classification", Proceedings of the ICEE, pp. 1-6, 2007, Lahore Pakistan.

Assistant Professor , NUST
September 2012 – Present (4 years 8 months )

Details: Courses:-

Machine Learning
Speech Processing
Digital Signal Processing
Microprocessor Based Systems
Computer Organization & Assembly Language

Assistant Manager, SUPARCO
June 2003 – June 2004 (1 year )

Details: Worked as Assistant Manager on the high frequency filter designing for Paksat satellite transponder